Search

Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit from a second pass rescoring using LLM. Recently multi-modal large language models, particularly speech and text foundational models have demonstrated strong spoken language understanding. Speech-Text foundational models leverage large amounts of unlabelled and labelled data both in speech and text modalities to model human language. In this work, we propose novel techniques to use multi-modal LLM for ASR rescoring. We also explore discriminative training to further improve the foundational model rescoring performance. We demonstrate cross-modal knowledge transfer in speech-text LLM can benefit rescoring. Our experiments demonstrate up-to 20% relative improvements over Whisper large ASR and up-to 15% relative improvements over text-only LLM.

Dialog systems, such as voice assistants, are expected to engage with users in complex, evolving conversations. Unfortunately, traditional automatic speech recognition (ASR) systems deployed in such applications are usually trained to recognize each turn independently and lack the ability to adapt to the conversational context or incorporate user feedback. In this work, we introduce a general framework for ASR in dialog systems that can go beyond learning from single-turn utterances and learn over time how to adapt to both explicit supervision and implicit user feedback present in multi-turn conversations. We accomplish that by leveraging advances in student-teacher learning and context-aware dialog processing, and designing contrastive self-supervision approaches with Ohm, a new online hard-negative mining approach. We show that leveraging our new framework compared to traditional training leads to relative WER reductions of close to 10% in real-world dialog systems, and up to 26% on public synthetic data., Comment: Presented at ICML 2024

Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important to extend the pure text based methods to incorporate other modalities in retrieval as well for applications across the wide spectrum of machine learning tasks and data types. In this work, we propose multi-modal retrieval with two approaches: kNN-LM and cross-attention techniques. We demonstrate the effectiveness of our retrieval approaches empirically by applying them to automatic speech recognition tasks with access to external information. Under this setting, we show that speech-based multi-modal retrieval outperforms text based retrieval, and yields up to 50 % improvement in word error rate over the multi-modal language model baseline. Furthermore, we achieve state-of-the-art recognition results on the Spoken-Squad question answering dataset.

Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of users being cut-off early. We propose a novel two-pass solution for endpointing, where the utterance endpoint detected from a first pass endpointer is verified by a 2nd-pass model termed EP Arbitrator. Our method improves the trade-off between early cut-offs and latency over a baseline endpointer, as tested on datasets including voice-assistant transactional queries, conversational speech, and the public SLURP corpus. We demonstrate that our method shows improvements regardless of the first-pass EP model used., Comment: ASRU 2023

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In real-world scenarios, prior to input into an LLM, an automated speech recognition (ASR) system generates an output transcript hypothesis, where inherent errors can degrade subsequent SLU tasks. Here we introduce a method that utilizes the ASR system's lattice output instead of relying solely on the top hypothesis, aiming to encapsulate speech ambiguities and enhance SLU outcomes. Our in-context learning experiments, covering spoken question answering and intent classification, underline the LLM's resilience to noisy speech transcripts with the help of word confusion networks from lattices, bridging the SLU performance gap between using the top ASR hypothesis and an oracle upper bound. Additionally, we delve into the LLM's robustness to varying ASR performance conditions and scrutinize the aspects of in-context learning which prove the most influential., Comment: Accepted to ICASSP 2024

While word error rates of automatic speech recognition (ASR) systems have consistently fallen, natural language understanding (NLU) applications built on top of ASR systems still attribute significant numbers of failures to low-quality speech recognition results. Existing assistant systems collect large numbers of these unsuccessful interactions, but these systems usually fail to learn from these interactions, even in an offline fashion. In this work, we introduce CLC: Contrastive Learning for Conversations, a family of methods for contrastive fine-tuning of models in a self-supervised fashion, making use of easily detectable artifacts in unsuccessful conversations with assistants. We demonstrate that our CLC family of approaches can improve the performance of ASR models on OD3, a new public large-scale semi-synthetic meta-dataset of audio task-oriented dialogues, by up to 19.2%. These gains transfer to real-world systems as well, where we show that CLC can help to improve performance by up to 6.7% over baselines. We make OD3 publicly available at https://github.com/amazon-science/amazon-od3 ., Comment: To appear in ICASSP 2024

Second pass rescoring is a critical component of competitive automatic speech recognition (ASR) systems. Large language models have demonstrated their ability in using pre-trained information for better rescoring of ASR hypothesis. Discriminative training, directly optimizing the minimum word-error-rate (MWER) criterion typically improves rescoring. In this study, we propose and explore several discriminative fine-tuning schemes for pre-trained LMs. We propose two architectures based on different pooling strategies of output embeddings and compare with probability based MWER. We conduct detailed comparisons between pre-trained causal and bidirectional LMs in discriminative settings. Experiments on LibriSpeech demonstrate that all MWER training schemes are beneficial, giving additional gains upto 8.5\% WER. Proposed pooling variants achieve lower latency while retaining most improvements. Finally, our study concludes that bidirectionality is better utilized with discriminative training., Comment: ASRU 2023

Federated Learning (FL) is a privacy-preserving paradigm, allowing edge devices to learn collaboratively without sharing data. Edge devices like Alexa and Siri are prospective sources of unlabeled audio data that can be tapped to learn robust audio representations. In this work, we bring Self-supervised Learning (SSL) and FL together to learn representations for Automatic Speech Recognition respecting data privacy constraints. We use the speaker and chapter information in the unlabeled speech dataset, Libri-Light, to simulate non-IID speaker-siloed data distributions and pre-train an LSTM encoder with the Contrastive Predictive Coding framework with FedSGD. We show that the pre-trained ASR encoder in FL performs as well as a centrally pre-trained model and produces an improvement of 12-15% (WER) compared to no pre-training. We further adapt the federated pre-trained models to a new language, French, and show a 20% (WER) improvement over no pre-training., Comment: Accepted at ISCA SPSC Symposium 3rd Symposium on Security and Privacy in Speech Communication, 2023

Recognition of personalized content remains a challenge in end-to-end speech recognition. We explore three novel approaches that use personalized content in a neural rescoring step to improve recognition: gazetteers, prompting, and a cross-attention based encoder-decoder model. We use internal de-identified en-US data from interactions with a virtual voice assistant supplemented with personalized named entities to compare these approaches. On a test set with personalized named entities, we show that each of these approaches improves word error rate by over 10%, against a neural rescoring baseline. We also show that on this test set, natural language prompts can improve word error rate by 7% without any training and with a marginal loss in generalization. Overall, gazetteers were found to perform the best with a 10% improvement in word error rate (WER), while also improving WER on a general test set by 1%.

Recent studies have found that model performance has a smooth power-law relationship, or scaling laws, with training data and model size, for a wide range of problems. These scaling laws allow one to choose nearly optimal data and model sizes. We study whether this scaling property is also applicable to second-pass rescoring, which is an important component of speech recognition systems. We focus on RescoreBERT as the rescoring model, which uses a pre-trained Transformer-based architecture fined tuned with an ASR discriminative loss. Using such a rescoring model, we show that the word error rate (WER) follows a scaling law for over two orders of magnitude as training data and model size increase. In addition, it is found that a pre-trained model would require less data than a randomly initialized model of the same size, representing effective data transferred from pre-training step. This effective data transferred is found to also follow a scaling law with the data and model size.

Automatic speech recognition (ASR) models with low-footprint are increasingly being deployed on edge devices for conversational agents, which enhances privacy. We study the problem of federated continual incremental learning for recurrent neural network-transducer (RNN-T) ASR models in the privacy-enhancing scheme of learning on-device, without access to ground truth human transcripts or machine transcriptions from a stronger ASR model. In particular, we study the performance of a self-learning based scheme, with a paired teacher model updated through an exponential moving average of ASR models. Further, we propose using possibly noisy weak-supervision signals such as feedback scores and natural language understanding semantics determined from user behavior across multiple turns in a session of interactions with the conversational agent. These signals are leveraged in a multi-task policy-gradient training approach to improve the performance of self-learning for ASR. Finally, we show how catastrophic forgetting can be mitigated by combining on-device learning with a memory-replay approach using selected historical datasets. These innovations allow for 10% relative improvement in WER on new use cases with minimal degradation on other test sets in the absence of strong-supervision signals such as ground-truth transcriptions., Comment: Proceedings of ICASSP 2023

Second-pass rescoring is employed in most state-of-the-art speech recognition systems. Recently, BERT based models have gained popularity for re-ranking the n-best hypothesis by exploiting the knowledge from masked language model pre-training. Further, fine-tuning with discriminative loss such as minimum word error rate (MWER) has shown to perform better than likelihood-based loss. Streaming applications with low latency requirements impose significant constraints on the size of the models, thereby limiting the word error rate (WER) performance gains. In this paper, we propose effective strategies for distilling from large models discriminatively trained with the MWER objective. We experiment on Librispeech and production scale internal dataset for voice-assistant. Our results demonstrate relative improvements of upto 7% WER over student models trained with MWER. We also show that the proposed distillation can reduce the WER gap between the student and the teacher by 62% upto 100%., Comment: Accepted at INTERSPEECH 2023

In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming ASR architecture that outputs a confusion network while maintaining limited latency, as needed for interactive applications. We show that 1-best results of our model are on par with a comparable RNN-T system, while the richer hypothesis set allows second-pass rescoring to achieve 10-20\% lower word error rate on the LibriSpeech task. We also show that our model outperforms a strong RNN-T baseline on a far-field voice assistant task., Comment: Submitted to Interspeech 2023

Streaming Automatic Speech Recognition (ASR) in voice assistants can utilize prefetching to partially hide the latency of response generation. Prefetching involves passing a preliminary ASR hypothesis to downstream systems in order to prefetch and cache a response. If the final ASR hypothesis after endpoint detection matches the preliminary one, the cached response can be delivered to the user, thus saving latency. In this paper, we extend this idea by introducing predictive automatic speech recognition, where we predict the full utterance from a partially observed utterance, and prefetch the response based on the predicted utterance. We introduce two personalization approaches and investigate the tradeoff between potential latency gains from successful predictions and the cost increase from failed predictions. We evaluate our methods on an internal voice assistant dataset as well as the public SLURP dataset., Comment: Accepted for Interspeech 2023

Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network accelerator (NNA) chips, which leverage highly parallelized fixed-point arithmetic to improve runtime memory and latency. In this work, we replicate the NNA operators during the training phase, accounting for the degradation due to low-precision inference on the NNA in back-propagation. Our proposed method efficiently emulates NNA operations, thus foregoing the need to transfer quantization error-prone data to the Central Processing Unit (CPU), ultimately reducing the user perceived latency (UPL). We apply our approach to Recurrent Neural Network-Transducer (RNN-T), an attractive architecture for on-device streaming speech recognition tasks. We train and evaluate models on 270K hours of English data and show a 5-7% improvement in engine latency while saving up to 10% relative degradation in WER., Comment: Accepted to SLT 2022

Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past signal, while non-causal models are exposed to a window of future frames at each step to increase predictive accuracy. This dichotomy amounts to a trade-off for real-time Automatic Speech Recognition (ASR) system design: profit from the low-latency benefit of strictly-causal architectures while accepting predictive performance limitations, or realize the modeling benefits of future-context models accompanied by their higher latency penalty. In this work, we relax the constraints of this choice and present the Adaptive Non-Causal Attention Transducer (ANCAT). Our architecture is non-causal in the traditional sense, but executes in a low-latency, streaming manner by dynamically choosing when to rely on future context and to what degree within the audio stream. The resulting mechanism, when coupled with our novel regularization algorithms, delivers comparable accuracy to non-causal configurations while improving significantly upon latency, closing the gap with their causal counterparts. We showcase our design experimentally by reporting comparative ASR task results with measures of accuracy and latency on both publicly accessible and production-scale, voice-assistant datasets., Comment: Accepted to ICML 2023

We present dual-attention neural biasing, an architecture designed to boost Wake Words (WW) recognition and improve inference time latency on speech recognition tasks. This architecture enables a dynamic switch for its runtime compute paths by exploiting WW spotting to select which branch of its attention networks to execute for an input audio frame. With this approach, we effectively improve WW spotting accuracy while saving runtime compute cost as defined by floating point operations (FLOPs). Using an in-house de-identified dataset, we demonstrate that the proposed dual-attention network can reduce the compute cost by $90\%$ for WW audio frames, with only $1\%$ increase in the number of parameters. This architecture improves WW F1 score by $16\%$ relative and improves generic rare word error rate by $3\%$ relative compared to the baselines., Comment: Accepted to Proc. IEEE ICASSP 2023

End-to-End (E2E) automatic speech recognition (ASR) systems used in voice assistants often have difficulties recognizing infrequent words personalized to the user, such as names and places. Rare words often have non-trivial pronunciations, and in such cases, human knowledge in the form of a pronunciation lexicon can be useful. We propose a PROnunCiation-aware conTextual adaptER (PROCTER) that dynamically injects lexicon knowledge into an RNN-T model by adding a phonemic embedding along with a textual embedding. The experimental results show that the proposed PROCTER architecture outperforms the baseline RNN-T model by improving the word error rate (WER) by 44% and 57% when measured on personalized entities and personalized rare entities, respectively, while increasing the model size (number of trainable parameters) by only 1%. Furthermore, when evaluated in a zero-shot setting to recognize personalized device names, we observe 7% WER improvement with PROCTER, as compared to only 1% WER improvement with text-only contextual attention, Comment: To appear in Proc. IEEE ICASSP

Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating increased data collection), and rapidly shifting data distributions (requiring more frequent model fine-tuning). In this work, we investigate the potential of leveraging external knowledge, particularly through off-policy key-value stores generated with text-to-speech methods, to allow for flexible post-training adaptation to new data distributions. In our approach, audio embeddings captured from text-to-speech, along with semantic text embeddings, are used to bias ASR via an approximate k-nearest-neighbor (KNN) based attentive fusion step. Our experiments on LibiriSpeech and in-house voice assistant/search datasets show that the proposed approach can reduce domain adaptation time by up to 1K GPU-hours while providing up to 3% WER improvement compared to a fine-tuning baseline, suggesting a promising approach for adapting production ASR systems in challenging zero and few-shot scenarios.

Incremental learning is one paradigm to enable model building and updating at scale with streaming data. For end-to-end automatic speech recognition (ASR) tasks, the absence of human annotated labels along with the need for privacy preserving policies for model building makes it a daunting challenge. Motivated by these challenges, in this paper we use a cloud based framework for production systems to demonstrate insights from privacy preserving incremental learning for automatic speech recognition (ILASR). By privacy preserving, we mean, usage of ephemeral data which are not human annotated. This system is a step forward for production levelASR models for incremental/continual learning that offers near real-time test-bed for experimentation in the cloud for end-to-end ASR, while adhering to privacy-preserving policies. We show that the proposed system can improve the production models significantly(3%) over a new time period of six months even in the absence of human annotated labels with varying levels of weak supervision and large batch sizes in incremental learning. This improvement is 20% over test sets with new words and phrases in the new time period. We demonstrate the effectiveness of model building in a privacy-preserving incremental fashion for ASR while further exploring the utility of having an effective teacher model and use of large batch sizes., Comment: 9 pages

We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization. Our architecture creates sparse computation pathways dynamically at inference time, resulting in selective use of compute resources throughout decoding, enabling significant reductions in compute with minimal impact on accuracy. The fully differentiable architecture is trained end-to-end with an accompanying lightweight arbitrator mechanism operating at the frame-level to make dynamic decisions on each input while a tunable loss function is used to regularize the overall level of compute against predictive performance. We report empirical results from experiments using the compute amortized Transformer-Transducer (T-T) model conducted on LibriSpeech data. Our best model can achieve a 60% compute cost reduction with only a 3% relative word error rate (WER) increase.

We present a novel sub-8-bit quantization-aware training (S8BQAT) scheme for 8-bit neural network accelerators. Our method is inspired from Lloyd-Max compression theory with practical adaptations for a feasible computational overhead during training. With the quantization centroids derived from a 32-bit baseline, we augment training loss with a Multi-Regional Absolute Cosine (MRACos) regularizer that aggregates weights towards their nearest centroid, effectively acting as a pseudo compressor. Additionally, a periodically invoked hard compressor is introduced to improve the convergence rate by emulating runtime model weight quantization. We apply S8BQAT on speech recognition tasks using Recurrent Neural NetworkTransducer (RNN-T) architecture. With S8BQAT, we are able to increase the model parameter size to reduce the word error rate by 4-16% relatively, while still improving latency by 5%., Comment: Accepted for publication in INTERSPEECH 2022

Second-pass rescoring is an important component in automatic speech recognition (ASR) systems that is used to improve the outputs from a first-pass decoder by implementing a lattice rescoring or $n$-best re-ranking. While pretraining with a masked language model (MLM) objective has received great success in various natural language understanding (NLU) tasks, it has not gained traction as a rescoring model for ASR. Specifically, training a bidirectional model like BERT on a discriminative objective such as minimum WER (MWER) has not been explored. Here we show how to train a BERT-based rescoring model with MWER loss, to incorporate the improvements of a discriminative loss into fine-tuning of deep bidirectional pretrained models for ASR. Specifically, we propose a fusion strategy that incorporates the MLM into the discriminative training process to effectively distill knowledge from a pretrained model. We further propose an alternative discriminative loss. This approach, which we call RescoreBERT, reduces WER by 6.6%/3.4% relative on the LibriSpeech clean/other test sets over a BERT baseline without discriminative objective. We also evaluate our method on an internal dataset from a conversational agent and find that it reduces both latency and WER (by 3 to 8% relative) over an LSTM rescoring model., Comment: Accepted to ICASSP 2022

Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional text-based natural language understanding systems, current E2E SLU approaches have not yet incorporated such critical contextual signals in multi-turn and task-oriented dialogues. In this work, we propose a contextual E2E SLU model architecture that uses a multi-head attention mechanism over encoded previous utterances and dialogue acts (actions taken by the voice assistant) of a multi-turn dialogue. We detail alternative methods to integrate these contexts into the state-ofthe-art recurrent and transformer-based models. When applied to a large de-identified dataset of utterances collected by a voice assistant, our method reduces average word and semantic error rates by 10.8% and 12.6%, respectively. We also present results on a publicly available dataset and show that our method significantly improves performance over a noncontextual baseline

End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, to improve the recognition accuracy on such rare words, is to latch onto personalized/contextual information at inference. In this work, we present a novel context-aware transformer transducer (CATT) network that improves the state-of-the-art transformer-based ASR system by taking advantage of such contextual signals. Specifically, we propose a multi-head attention-based context-biasing network, which is jointly trained with the rest of the ASR sub-networks. We explore different techniques to encode contextual data and to create the final attention context vectors. We also leverage both BLSTM and pretrained BERT based models to encode contextual data and guide the network training. Using an in-house far-field dataset, we show that CATT, using a BERT based context encoder, improves the word error rate of the baseline transformer transducer and outperforms an existing deep contextual model by 24.2% and 19.4% respectively., Comment: Accepted to ASRU 2021

Spoken language understanding (SLU) systems translate voice input commands to semantics which are encoded as an intent and pairs of slot tags and values. Most current SLU systems deploy a cascade of two neural models where the first one maps the input audio to a transcript (ASR) and the second predicts the intent and slots from the transcript (NLU). In this paper, we introduce FANS, a new end-to-end SLU model that fuses an ASR audio encoder to a multi-task NLU decoder to infer the intent, slot tags, and slot values directly from a given input audio, obviating the need for transcription. FANS consists of a shared audio encoder and three decoders, two of which are seq-to-seq decoders that predict non null slot tags and slot values in parallel and in an auto-regressive manner. FANS neural encoder and decoders architectures are flexible which allows us to leverage different combinations of LSTM, self-attention, and attenders. Our experiments show compared to the state-of-the-art end-to-end SLU models, FANS reduces ICER and IRER errors relatively by 30 % and 7 %, respectively, when tested on an in-house SLU dataset and by 0.86 % and 2 % absolute when tested on a public SLU dataset., Comment: Published in Interspeech 2021

We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks. The architecture enables a dynamic pivot for its runtime compute pathway, namely taking advantage of keyword spotting to select which component of the network to execute for a given audio frame. To accomplish this, we leverage a recurrent cell we call the Bifocal LSTM (BFLSTM), which we detail in the paper. The architecture is compatible with other optimization strategies such as quantization, sparsification, and applying time-reduction layers, making it especially applicable for deployed, real-time speech recognition settings. We present the architecture and report comparative experimental results on voice-assistant speech recognition tasks. Specifically, we show our proposed Bifocal RNN-T can improve inference cost by 29.1% with matching word error rates and only a minor increase in memory size., Comment: Accepted at ICASSP 2021

We introduce Amortized Neural Networks (AmNets), a compute cost- and latency-aware network architecture particularly well-suited for sequence modeling tasks. We apply AmNets to the Recurrent Neural Network Transducer (RNN-T) to reduce compute cost and latency for an automatic speech recognition (ASR) task. The AmNets RNN-T architecture enables the network to dynamically switch between encoder branches on a frame-by-frame basis. Branches are constructed with variable levels of compute cost and model capacity. Here, we achieve variable compute for two well-known candidate techniques: one using sparse pruning and the other using matrix factorization. Frame-by-frame switching is determined by an arbitrator network that requires negligible compute overhead. We present results using both architectures on LibriSpeech data and show that our proposed architecture can reduce inference cost by up to 45\% and latency to nearly real-time without incurring a loss in accuracy., Comment: Accepted at Interspeech 2021

As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered. In this work we address one of these constraints, namely over-the-network data budgets for transferring models from server to device. We present neural update approaches for release of subsequent speech model generations abiding by a data budget. We detail two architecture-agnostic methods which learn compact representations for transmission to devices. We experimentally validate our techniques with results on two tasks (automatic speech recognition and spoken language understanding) on open source data sets by demonstrating when applied in succession, our budgeted updates outperform comparable model compression baselines by significant margins., Comment: Accepted at Interspeech 2021

Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances. SLU systems usually consist of (1) an automatic speech recognition (ASR) module, (2) an interface module that exposes relevant outputs from ASR, and (3) a natural language understanding (NLU) module. Interfaces in SLU systems carry information on text transcriptions or richer information like neural embeddings from ASR to NLU. In this paper, we study how interfaces affect joint-training for spoken language understanding. Most notably, we obtain the state-of-the-art results on the publicly available 50-hr SLURP dataset. We first leverage large-size pretrained ASR and NLU models that are connected by a text interface, and then jointly train both models via a sequence loss function. For scenarios where pretrained models are not utilized, the best results are obtained through a joint sequence loss training using richer neural interfaces. Finally, we show the overall diminishing impact of leveraging pretrained models with increased training data size., Comment: Proc. Interspeech 2022

Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design decision assumes the primary input data source does not change and if an additional (auxiliary) data source is occasionally available, it cannot be used. An ASR model that operates on both primary and auxiliary data can achieve better accuracy compared to a primary-only solution; and a model that can serve both primary-only (PO) and primary-plus-auxiliary (PPA) modes is highly desirable. In this work, we propose a unified ASR model that can serve both modes. We demonstrate its efficacy in a realistic scenario where a set of devices typically stream a single primary audio channel, and two additional auxiliary channels only when upload bandwidth allows it. The architecture enables a unique methodology that uses both types of input audio during training time. Our proposed approach achieves up to 12.5% relative word-error-rate reduction (WERR) compared to a PO baseline, and up to 16.0% relative WERR in low-SNR conditions. The unique training methodology achieves up to 2.5% relative WERR compared to a PPA baseline.

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance was spoken, provides a rich input signal. We introduce an attention mechanism for training neural speech recognition language models on both text and non-linguistic contextual data. When applied to a large de-identified dataset of utterances collected by a popular voice assistant platform, our method reduces perplexity by 7.0% relative over a standard LM that does not incorporate contextual information. When evaluated on utterances extracted from the long tail of the dataset, our method improves perplexity by 9.0% relative over a standard LM and by over 2.8% relative when compared to a state-of-the-art model for contextual LM.

Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly incorporating intent representations as additional information to improve a recurrent neural network-transducer (RNN-T) based automatic speech recognition (ASR) system. An audio-to-intent (A2I) model encodes the intent of the utterance in the form of embeddings or posteriors, and these are used as auxiliary inputs for RNN-T training and inference. Experimenting with a 50k-hour far-field English speech corpus, this study shows that when running the system in non-streaming mode, where intent representation is extracted from the entire utterance and then used to bias streaming RNN-T search from the start, it provides a 5.56% relative word error rate reduction (WERR). On the other hand, a streaming system using per-frame intent posteriors as extra inputs for the RNN-T ASR system yields a 3.33% relative WERR. A further detailed analysis of the streaming system indicates that our proposed method brings especially good gain on media-playing related intents (e.g. 9.12% relative WERR on PlayMusicIntent)., Comment: To appear in Interspeech 2021

Wav2vec-C introduces a novel representation learning technique combining elements from wav2vec 2.0 and VQ-VAE. Our model learns to reproduce quantized representations from partially masked speech encoding using a contrastive loss in a way similar to Wav2vec 2.0. However, the quantization process is regularized by an additional consistency network that learns to reconstruct the input features to the wav2vec 2.0 network from the quantized representations in a way similar to a VQ-VAE model. The proposed self-supervised model is trained on 10k hours of unlabeled data and subsequently used as the speech encoder in a RNN-T ASR model and fine-tuned with 1k hours of labeled data. This work is one of only a few studies of self-supervised learning on speech tasks with a large volume of real far-field labeled data. The Wav2vec-C encoded representations achieves, on average, twice the error reduction over baseline and a higher codebook utilization in comparison to wav2vec 2.0, Comment: To appear in Interspeech 2021

The recognition of personalized content, such as contact names, remains a challenging problem for end-to-end speech recognition systems. In this work, we demonstrate how first and second-pass rescoring strategies can be leveraged together to improve the recognition of such words. Following previous work, we use a shallow fusion approach to bias towards recognition of personalized content in the first-pass decoding. We show that such an approach can improve personalized content recognition by up to 16% with minimum degradation on the general use case. We describe a fast and scalable algorithm that enables our biasing models to remain at the word-level, while applying the biasing at the subword level. This has the advantage of not requiring the biasing models to be dependent on any subword symbol table. We also describe a novel second-pass de-biasing approach: used in conjunction with a first-pass shallow fusion that optimizes on oracle WER, we can achieve an additional 14% improvement on personalized content recognition, and even improve accuracy for the general use case by up to 2.5%., Comment: 5 pages, 5 tables, 1 figure

Spoken language understanding (SLU) systems extract transcriptions, as well as semantics of intent or named entities from speech, and are essential components of voice activated systems. SLU models, which either directly extract semantics from audio or are composed of pipelined automatic speech recognition (ASR) and natural language understanding (NLU) models, are typically trained via differentiable cross-entropy losses, even when the relevant performance metrics of interest are word or semantic error rates. In this work, we propose non-differentiable sequence losses based on SLU metrics as a proxy for semantic error and use the REINFORCE trick to train ASR and SLU models with this loss. We show that custom sequence loss training is the state-of-the-art on open SLU datasets and leads to 6% relative improvement in both ASR and NLU performance metrics on large proprietary datasets. We also demonstrate how the semantic sequence loss training paradigm can be used to update ASR and SLU models without transcripts, using semantic feedback alone., Comment: Proc. IEEE ICASSP 2021

In order to achieve high accuracy for machine learning (ML) applications, it is essential to employ models with a large number of parameters. Certain applications, such as Automatic Speech Recognition (ASR), however, require real-time interactions with users, hence compelling the model to have as low latency as possible. Deploying large scale ML applications thus necessitates model quantization and compression, especially when running ML models on resource constrained devices. For example, by forcing some of the model weight values into zero, it is possible to apply zero-weight compression, which reduces both the model size and model reading time from the memory. In the literature, such methods are referred to as sparse pruning. The fundamental questions are when and which weights should be forced to zero, i.e. be pruned. In this work, we propose a compressed sensing based pruning (CSP) approach to effectively address those questions. By reformulating sparse pruning as a sparsity inducing and compression-error reduction dual problem, we introduce the classic compressed sensing process into the ML model training process. Using ASR task as an example, we show that CSP consistently outperforms existing approaches in the literature., Comment: 5 pages, accepted for publication in (ICASSP 2021) 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing. June 6-12, 2021. Location: Toronto, ON, Canada

As voice assistants become more ubiquitous, they are increasingly expected to support and perform well on a wide variety of use-cases across different domains. We present a domain-aware rescoring framework suitable for achieving domain-adaptation during second-pass rescoring in production settings. In our framework, we fine-tune a domain-general neural language model on several domains, and use an LSTM-based domain classification model to select the appropriate domain-adapted model to use for second-pass rescoring. This domain-aware rescoring improves the word error rate by up to 2.4% and slot word error rate by up to 4.1% on three individual domains -- shopping, navigation, and music -- compared to domain general rescoring. These improvements are obtained while maintaining accuracy for the general use case., Comment: ICASSP 2021

Accents mismatching is a critical problem for end-to-end ASR. This paper aims to address this problem by building an accent-robust RNN-T system with domain adversarial training (DAT). We unveil the magic behind DAT and provide, for the first time, a theoretical guarantee that DAT learns accent-invariant representations. We also prove that performing the gradient reversal in DAT is equivalent to minimizing the Jensen-Shannon divergence between domain output distributions. Motivated by the proof of equivalence, we introduce reDAT, a novel technique based on DAT, which relabels data using either unsupervised clustering or soft labels. Experiments on 23K hours of multi-accent data show that DAT achieves competitive results over accent-specific baselines on both native and non-native English accents but up to 13% relative WER reduction on unseen accents; our reDAT yields further improvements over DAT by 3% and 8% relatively on non-native accents of American and British English., Comment: accepted in ICASSP 2021; final camera-ready version

End-to-end automatic speech recognition (ASR) systems, such as recurrent neural network transducer (RNN-T), have become popular, but rare word remains a challenge. In this paper, we propose a simple, yet effective method called unigram shallow fusion (USF) to improve rare words for RNN-T. In USF, we extract rare words from RNN-T training data based on unigram count, and apply a fixed reward when the word is encountered during decoding. We show that this simple method can improve performance on rare words by 3.7% WER relative without degradation on general test set, and the improvement from USF is additive to any additional language model based rescoring. Then, we show that the same USF does not work on conventional hybrid system. Finally, we reason that USF works by fixing errors in probability estimates of words due to Viterbi search used during decoding with subword-based RNN-T.

We consider the problem of spoken language understanding (SLU) of extracting natural language intents and associated slot arguments or named entities from speech that is primarily directed at voice assistants. Such a system subsumes both automatic speech recognition (ASR) as well as natural language understanding (NLU). An end-to-end joint SLU model can be built to a required specification opening up the opportunity to deploy on hardware constrained scenarios like devices enabling voice assistants to work offline, in a privacy preserving manner, whilst also reducing server costs. We first present models that extract utterance intent directly from speech without intermediate text output. We then present a compositional model, which generates the transcript using the Listen Attend Spell ASR system and then extracts interpretation using a neural NLU model. Finally, we contrast these methods to a jointly trained end-to-end joint SLU model, consisting of ASR and NLU subsystems which are connected by a neural network based interface instead of text, that produces transcripts as well as NLU interpretation. We show that the jointly trained model shows improvements to ASR incorporating semantic information from NLU and also improves NLU by exposing it to ASR confusion encoded in the hidden layer., Comment: Proceedings of INTERSPEECH

In this paper, we propose a streaming model to distinguish voice queries intended for a smart-home device from background speech. The proposed model consists of multiple CNN layers with residual connections, followed by a stacked LSTM architecture. The streaming capability is achieved by using unidirectional LSTM layers and a causal mean aggregation layer to form the final utterance-level prediction up to the current frame. In order to avoid redundant computation during online streaming inference, we use a caching mechanism for every convolution operation. Experimental results on a device-directed vs. non device-directed task show that the proposed model yields an equal error rate reduction of 41% compared to our previous best model on this task. Furthermore, we show that the proposed model is able to accurately predict earlier in time compared to the attention-based models.

Decomposing models into multiple components is critically important in many applications such as language modeling (LM) as it enables adapting individual components separately and biasing of some components to the user's personal preferences. Conventionally, contextual and personalized adaptation for language models, are achieved through class-based factorization, which requires class-annotated data, or through biasing to individual phrases which is limited in scale. In this paper, we propose a system that combines model-defined components, by learning when to activate the generation process from each individual component, and how to combine probability distributions from each component, directly from unlabeled text data., Comment: Self-Supervised Learning for Speech and Audio Processing Workshop @ NeurIPS 2020

Multilingual ASR technology simplifies model training and deployment, but its accuracy is known to depend on the availability of language information at runtime. Since language identity is seldom known beforehand in real-world scenarios, it must be inferred on-the-fly with minimum latency. Furthermore, in voice-activated smart assistant systems, language identity is also required for downstream processing of ASR output. In this paper, we introduce streaming, end-to-end, bilingual systems that perform both ASR and language identification (LID) using the recurrent neural network transducer (RNN-T) architecture. On the input side, embeddings from pretrained acoustic-only LID classifiers are used to guide RNN-T training and inference, while on the output side, language targets are jointly modeled with ASR targets. The proposed method is applied to two language pairs: English-Spanish as spoken in the United States, and English-Hindi as spoken in India. Experiments show that for English-Spanish, the bilingual joint ASR-LID architecture matches monolingual ASR and acoustic-only LID accuracies. For the more challenging (owing to within-utterance code switching) case of English-Hindi, English ASR and LID metrics show degradation. Overall, in scenarios where users switch dynamically between languages, the proposed architecture offers a promising simplification over running multiple monolingual ASR models and an LID classifier in parallel.

Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like "e c h o" to "E k oU"). Most G2P systems are monolingual and based on traditional joint-sequence based n-gram models [1,2]. As an alternative, we present a single end-to-end trained neural G2P model that shares same encoder and decoder across multiple languages. This allows the model to utilize a combination of universal symbol inventories of Latin-like alphabets and cross-linguistically shared feature representations. Such model is especially useful in the scenarios of low resource languages and code switching/foreign words, where the pronunciations in one language need to be adapted to other locales or accents. We further experiment with word language distribution vector as an additional training target in order to improve system performance by helping the model decouple pronunciations across a variety of languages in the parameter space. We show 7.2% average improvement in phoneme error rate over low resource languages and no degradation over high resource ones compared to monolingual baselines., Comment: Published in INTERSPEECH (2019)

This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual speech recognition is to run multiple monolingual ASR systems in parallel and rely on a language identification (LID) component that detects the input language. Conventionally, LID relies on acoustic only information to detect input language. We propose an approach that learns and combines acoustic level representations with embeddings estimated on ASR hypotheses resulting in up to 50% relative reduction of identification error rate, compared to a model that uses acoustic only features. Furthermore, to reduce the processing cost and latency, we exploit a streaming architecture to identify the spoken language early when the system reaches a predetermined confidence level, alleviating the need to run multiple ASR systems until the end of input query. The combined acoustic and text LID, coupled with our proposed streaming runtime architecture, results in an average of 1500ms early identification for more than 50% of utterances, with almost no degradation in accuracy. We also show improved results by adopting a semi-supervised learning (SSL) technique using the newly proposed model architecture as a teacher model., Comment: 5 pages, 2 figures

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these models typically require more data to achieve comparable results. Well-known model adaptation techniques, to account for domain and style adaptation, are not easily applicable to end-to-end systems. Conventional HMM-based systems, on the other hand, have been optimized for various production environments and use cases. In this work, we propose to combine the benefits of end-to-end approaches with a conventional system using an attention-based discriminative language model that learns to rescore the output of a first-pass ASR system. We show that learning to rescore a list of potential ASR outputs is much simpler than learning to generate the hypothesis. The proposed model results in 8% improvement in word error rate even when the amount of training data is a fraction of data used for training the first-pass system., Comment: 4 pages, 1 figure, Accepted at ICASSP 2020

Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be addressed for an NLM to be used in a practical large-scale ASR system. In this paper, we present solutions to some of the challenges, including training NLM from heterogenous corpora, limiting latency impact and handling personalized bias in the second-pass rescorer. Overall, we show that we can achieve a 6.2% relative WER reduction using neural LM in a second-pass n-best rescoring framework with a minimal increase in latency., Comment: Interspeech 2019 (accepted: oral)

Language models (LM) for interactive speech recognition systems are trained on large amounts of data and the model parameters are optimized on past user data. New application intents and interaction types are released for these systems over time, imposing challenges to adapt the LMs since the existing training data is no longer sufficient to model the future user interactions. It is unclear how to adapt LMs to new application intents without degrading the performance on existing applications. In this paper, we propose a solution to (a) estimate n-gram counts directly from the hand-written grammar for training LMs and (b) use constrained optimization to optimize the system parameters for future use cases, while not degrading the performance on past usage. We evaluated our approach on new applications intents for a personal assistant system and find that the adaptation improves the word error rate by up to 15% on new applications even when there is no adaptation data available for an application., Comment: Accepted at SLT 2018

This article presents a whisper speech detector in the far-field domain. The proposed system consists of a long-short term memory (LSTM) neural network trained on log-filterbank energy (LFBE) acoustic features. This model is trained and evaluated on recordings of human interactions with voice-controlled, far-field devices in whisper and normal phonation modes. We compare multiple inference approaches for utterance-level classification by examining trajectories of the LSTM posteriors. In addition, we engineer a set of features based on the signal characteristics inherent to whisper speech, and evaluate their effectiveness in further separating whisper from normal speech. A benchmarking of these features using multilayer perceptrons (MLP) and LSTMs suggests that the proposed features, in combination with LFBE features, can help us further improve our classifiers. We prove that, with enough data, the LSTM model is indeed as capable of learning whisper characteristics from LFBE features alone compared to a simpler MLP model that uses both LFBE and features engineered for separating whisper and normal speech. In addition, we prove that the LSTM classifiers accuracy can be further improved with the incorporation of the proposed engineered features.