Search

Police departments around the world use two-way radio for coordination. These broadcast police communications (BPC) are a unique source of information about everyday police activity and emergency response. Yet BPC are not transcribed, and their naturalistic audio properties make automatic transcription challenging. We collect a corpus of roughly 62,000 manually transcribed radio transmissions (~46 hours of audio) to evaluate the feasibility of automatic speech recognition (ASR) using modern recognition models. We evaluate the performance of off-the-shelf speech recognizers, models fine-tuned on BPC data, and customized end-to-end models. We find that both human and machine transcription is challenging in this domain. Large off-the-shelf ASR models perform poorly, but fine-tuned models can reach the approximate range of human performance. Our work suggests directions for future work, including analysis of short utterances and potential miscommunication in police radio interactions. We make our corpus and data annotation pipeline available to other researchers, to enable further research on recognition and analysis of police communication., Comment: Accepted by SLT 2024

Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the world's 7000+ languages. We propose XEUS, a Cross-lingual Encoder for Universal Speech, trained on over 1 million hours of data across 4057 languages, extending the language coverage of SSL models 4-fold. We combine 1 million hours of speech from existing publicly accessible corpora with a newly created corpus of 7400+ hours from 4057 languages, which will be publicly released. To handle the diverse conditions of multilingual speech data, we augment the typical SSL masked prediction approach with a novel dereverberation objective, increasing robustness. We evaluate XEUS on several benchmarks, and show that it consistently outperforms or achieves comparable results to state-of-the-art (SOTA) SSL models across a variety of tasks. XEUS sets a new SOTA on the ML-SUPERB benchmark: it outperforms MMS 1B and w2v-BERT 2.0 v2 by 0.8% and 4.4% respectively, despite having less parameters or pre-training data. Checkpoints, code, and data are found in https://www.wavlab.org/activities/2024/xeus/., Comment: Updated affiliations; 20 pages

The Spoken Language Understanding Evaluation (SLUE) suite of benchmark tasks was recently introduced to address the need for open resources and benchmarking of complex spoken language understanding (SLU) tasks, including both classification and sequence generation tasks, on natural speech. The benchmark has demonstrated preliminary success in using pre-trained speech foundation models (SFM) for these SLU tasks. However, the community still lacks a fine-grained understanding of the comparative utility of different SFMs. Inspired by this, we ask: which SFMs offer the most benefits for these complex SLU tasks, and what is the most effective approach for incorporating these SFMs? To answer this, we perform an extensive evaluation of multiple supervised and self-supervised SFMs using several evaluation protocols: (i) frozen SFMs with a lightweight prediction head, (ii) frozen SFMs with a complex prediction head, and (iii) fine-tuned SFMs with a lightweight prediction head. Although the supervised SFMs are pre-trained on much more speech recognition data (with labels), they do not always outperform self-supervised SFMs; the latter tend to perform at least as well as, and sometimes better than, supervised SFMs, especially on the sequence generation tasks in SLUE. While there is no universally optimal way of incorporating SFMs, the complex prediction head gives the best performance for most tasks, although it increases the inference time. We also introduce an open-source toolkit and performance leaderboard, SLUE-PERB, for these tasks and modeling strategies., Comment: Accepted at ACL Findings 2024

The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an LLM, trained on diverse tasks. We propose the use of discrete speech units (DSU), rather than continuous-valued speech encoder outputs, that are converted to the LLM token embedding space using the speech adapter. We generate DSU using a self-supervised speech encoder followed by k-means clustering. The proposed model shows robust performance on speech inputs from seen/unseen domains and instruction-following capability in spoken question answering. We also explore various types of DSU extracted from different layers of the self-supervised speech encoder, as well as Mel frequency Cepstral Coefficients (MFCC). Our findings suggest that the ASR task and datasets are not crucial in instruction-tuning for spoken question answering tasks.

The Open Whisper-style Speech Model (OWSM) series was introduced to achieve full transparency in building advanced speech-to-text (S2T) foundation models. To this end, OWSM models are trained on 25 public speech datasets, which are heterogeneous in multiple ways. In this study, we advance the OWSM series by introducing OWSM v3.2, which improves on prior models by investigating and addressing the impacts of this data heterogeneity. Our study begins with a detailed analysis of each dataset, from which we derive two key strategies: data filtering with proxy task to enhance data quality, and the incorporation of punctuation and true-casing using an open large language model (LLM). With all other configurations staying the same, OWSM v3.2 improves performance over the OWSM v3.1 baseline while using 15% less training data.

ML-SUPERB evaluates self-supervised learning (SSL) models on the tasks of language identification and automatic speech recognition (ASR). This benchmark treats the models as feature extractors and uses a single shallow downstream model, which can be fine-tuned for a downstream task. However, real-world use cases may require different configurations. This paper presents ML-SUPERB~2.0, which is a new benchmark for evaluating pre-trained SSL and supervised speech models across downstream models, fine-tuning setups, and efficient model adaptation approaches. We find performance improvements over the setup of ML-SUPERB. However, performance depends on the downstream model design. Also, we find large performance differences between languages and datasets, suggesting the need for more targeted approaches to improve multilingual ASR performance., Comment: Accepted by Interspeech 2024

When performing tasks like automatic speech recognition or spoken language understanding for a given utterance, access to preceding text or audio provides contextual information can improve performance. Considering the recent advances in generative large language models (LLM), we hypothesize that an LLM could generate useful context information using the preceding text. With appropriate prompts, LLM could generate a prediction of the next sentence or abstractive text like titles or topics. In this paper, we study the use of LLM-generated context information and propose an approach to distill the generated information during fine-tuning of self-supervised speech models, which we refer to as generative context-aware fine-tuning. This approach allows the fine-tuned model to make improved predictions without access to the true surrounding segments or to the LLM at inference time, while requiring only a very small additional context module. We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks: automatic speech recognition, named entity recognition, and sentiment analysis. The results show that generative context-aware fine-tuning outperforms a context injection fine-tuning approach that accesses the ground-truth previous text, and is competitive with a generative context injection fine-tuning approach that requires the LLM at inference time.

Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model them jointly. In light of this, we explore joint language modeling for speech units and text. Specifically, we compare different speech tokenizers to transform continuous speech signals into discrete units and use different methods to construct mixed speech-text data. We introduce automatic metrics to evaluate how well the joint LM mixes speech and text. We also fine-tune the LM on downstream spoken language understanding (SLU) tasks with different modalities (speech or text) and test its performance to assess the model's learning of shared representations. Our results show that by mixing speech units and text with our proposed mixing techniques, the joint LM improves over a speech-only baseline on SLU tasks and shows zero-shot cross-modal transferability., Comment: EMNLP findings 2023

We study phrase structure induction from visually-grounded speech. The core idea is to first segment the speech waveform into sequences of word segments, and subsequently induce phrase structure using the inferred segment-level continuous representations. We present the Audio-Visual Neural Syntax Learner (AV-NSL) that learns phrase structure by listening to audio and looking at images, without ever being exposed to text. By training on paired images and spoken captions, AV-NSL exhibits the capability to infer meaningful phrase structures that are comparable to those derived by naturally-supervised text parsers, for both English and German. Our findings extend prior work in unsupervised language acquisition from speech and grounded grammar induction, and present one approach to bridge the gap between the two topics.

Recent studies leverage large language models with multi-tasking capabilities, using natural language prompts to guide the model's behavior and surpassing performance of task-specific models. Motivated by this, we ask: can we build a single model that jointly performs various spoken language understanding (SLU) tasks? We start by adapting a pre-trained automatic speech recognition model to additional tasks using single-token task specifiers. We enhance this approach through instruction tuning, i.e., finetuning by describing the task using natural language instructions followed by the list of label options. Our approach can generalize to new task descriptions for the seen tasks during inference, thereby enhancing its user-friendliness. We demonstrate the efficacy of our single multi-task learning model "UniverSLU" for 12 speech classification and sequence generation task types spanning 17 datasets and 9 languages. On most tasks, UniverSLU achieves competitive performance and often even surpasses task-specific models. Additionally, we assess the zero-shot capabilities, finding that the model generalizes to new datasets and languages for seen task types., Comment: Accepted at NAACL 2024

Speech enhancement systems are typically trained using pairs of clean and noisy speech. In audio-visual speech enhancement (AVSE), there is not as much ground-truth clean data available; most audio-visual datasets are collected in real-world environments with background noise and reverberation, hampering the development of AVSE. In this work, we introduce AV2Wav, a resynthesis-based audio-visual speech enhancement approach that can generate clean speech despite the challenges of real-world training data. We obtain a subset of nearly clean speech from an audio-visual corpus using a neural quality estimator, and then train a diffusion model on this subset to generate waveforms conditioned on continuous speech representations from AV-HuBERT with noise-robust training. We use continuous rather than discrete representations to retain prosody and speaker information. With this vocoding task alone, the model can perform speech enhancement better than a masking-based baseline. We further fine-tune the diffusion model on clean/noisy utterance pairs to improve the performance. Our approach outperforms a masking-based baseline in terms of both automatic metrics and a human listening test and is close in quality to the target speech in the listening test. Audio samples can be found at https://home.ttic.edu/~jcchou/demo/avse/avse_demo.html., Comment: extended version for the accepted paper at ICASSP 2024

Many self-supervised speech models, varying in their pre-training objective, input modality, and pre-training data, have been proposed in the last few years. Despite impressive successes on downstream tasks, we still have a limited understanding of the properties encoded by the models and the differences across models. In this work, we examine the intermediate representations for a variety of recent models. Specifically, we measure acoustic, phonetic, and word-level properties encoded in individual layers, using a lightweight analysis tool based on canonical correlation analysis (CCA). We find that these properties evolve across layers differently depending on the model, and the variations relate to the choice of pre-training objective. We further investigate the utility of our analyses for downstream tasks by comparing the property trends with performance on speech recognition and spoken language understanding tasks. We discover that CCA trends provide reliable guidance to choose layers of interest for downstream tasks and that single-layer performance often matches or improves upon using all layers, suggesting implications for more efficient use of pre-trained models., Comment: Accepted to ICASSP 2023. Code: https://github.com/ankitapasad/layerwise-analysis

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains. Such methods have shown success in natural language processing and computer vision domains, achieving new levels of performance while reducing the number of labels required for many downstream scenarios. Speech representation learning is experiencing similar progress in three main categories: generative, contrastive, and predictive methods. Other approaches rely on multi-modal data for pre-training, mixing text or visual data streams with speech. Although self-supervised speech representation is still a nascent research area, it is closely related to acoustic word embedding and learning with zero lexical resources, both of which have seen active research for many years. This review presents approaches for self-supervised speech representation learning and their connection to other research areas. Since many current methods focus solely on automatic speech recognition as a downstream task, we review recent efforts on benchmarking learned representations to extend the application beyond speech recognition.

Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect for each new task and domain. However, recent advances in self-supervised speech representations have made it feasible to consider learning SLU models with limited labeled data. In this work we focus on low-resource spoken named entity recognition (NER) and address the question: Beyond self-supervised pre-training, how can we use external speech and/or text data that are not annotated for the task? We draw on a variety of approaches, including self-training, knowledge distillation, and transfer learning, and consider their applicability to both end-to-end models and pipeline (speech recognition followed by text NER model) approaches. We find that several of these approaches improve performance in resource-constrained settings beyond the benefits from pre-trained representations alone. Compared to prior work, we find improved F1 scores of up to 16%. While the best baseline model is a pipeline approach, the best performance when using external data is ultimately achieved by an end-to-end model. We provide detailed comparisons and analyses, showing for example that end-to-end models are able to focus on the more NER-specific words., Comment: Accepted at NAACL 2022. Codebase available at https://github.com/asappresearch/spoken-ner

Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in higher-level spoken language understanding tasks, including using end-to-end models, but there are fewer annotated datasets for such tasks. At the same time, recent work shows the possibility of pre-training generic representations and then fine-tuning for several tasks using relatively little labeled data. We propose to create a suite of benchmark tasks for Spoken Language Understanding Evaluation (SLUE) consisting of limited-size labeled training sets and corresponding evaluation sets. This resource would allow the research community to track progress, evaluate pre-trained representations for higher-level tasks, and study open questions such as the utility of pipeline versus end-to-end approaches. We present the first phase of the SLUE benchmark suite, consisting of named entity recognition, sentiment analysis, and ASR on the corresponding datasets. We focus on naturally produced (not read or synthesized) speech, and freely available datasets. We provide new transcriptions and annotations on subsets of the VoxCeleb and VoxPopuli datasets, evaluation metrics and results for baseline models, and an open-source toolkit to reproduce the baselines and evaluate new models., Comment: Updated preprint for SLUE Benchmark v0.2; Toolkit link https://github.com/asappresearch/slue-toolkit

We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and zero-resource languages. Our model, which we refer to as a maximal sampling correspondence variational autoencoder (MCVAE), is a recurrent neural network (RNN) trained with a novel self-supervised correspondence loss that encourages consistency between embeddings of different instances of the same word. Our training scheme improves on previous correspondence training approaches through the use and comparison of multiple samples from the approximate posterior distribution. In the zero-resource setting, the MCVAE can be trained in an unsupervised way, without any ground-truth word pairs, by using the word-like segments discovered via an unsupervised term discovery system. In both this setting and a semi-supervised low-resource setting (with a limited set of ground-truth word pairs), the MCVAE outperforms previous state-of-the-art models, such as Siamese-, CAE- and VAE-based RNNs., Comment: 10 pages, 6 figures, NeurIPS 2020 Workshop Self-Supervised Learning for Speech and Audio Processing

Segmental models are sequence prediction models in which scores of hypotheses are based on entire variable-length segments of frames. We consider segmental models for whole-word ("acoustic-to-word") speech recognition, with the feature vectors defined using vector embeddings of segments. Such models are computationally challenging as the number of paths is proportional to the vocabulary size, which can be orders of magnitude larger than when using subword units like phones. We describe an efficient approach for end-to-end whole-word segmental models, with forward-backward and Viterbi decoding performed on a GPU and a simple segment scoring function that reduces space complexity. In addition, we investigate the use of pre-training via jointly trained acoustic word embeddings (AWEs) and acoustically grounded word embeddings (AGWEs) of written word labels. We find that word error rate can be reduced by a large margin by pre-training the acoustic segment representation with AWEs, and additional (smaller) gains can be obtained by pre-training the word prediction layer with AGWEs. Our final models improve over prior A2W models., Comment: SLT 2021

Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically grounded word embeddings (AGWEs). Such embeddings have been used to improve speech retrieval, recognition, and spoken term discovery. In this work, we extend this idea to multiple low-resource languages. We jointly train an AWE model and an AGWE model, using phonetically transcribed data from multiple languages. The pre-trained models can then be used for unseen zero-resource languages, or fine-tuned on data from low-resource languages. We also investigate distinctive features, as an alternative to phone labels, to better share cross-lingual information. We test our models on word discrimination tasks for twelve languages. When trained on eleven languages and tested on the remaining unseen language, our model outperforms traditional unsupervised approaches like dynamic time warping. After fine-tuning the pre-trained models on one hour or even ten minutes of data from a new language, performance is typically much better than training on only the target-language data. We also find that phonetic supervision improves performance over character sequences, and that distinctive feature supervision is helpful in handling unseen phones in the target language.

We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The pre-trained networks can then be fine-tuned on a smaller amount of supervised data for speech recognition. Experiments with this approach on the LibriSpeech and Wall Street Journal corpora show promising results. We find that the main factors that lead to speech recognition improvements are: masking segments of sufficient width in both time and frequency, pre-training on a much larger amount of unlabeled data than the labeled data, and domain adaptation when the unlabeled and labeled data come from different domains. The gain from pre-training is additive to that of supervised data augmentation., Comment: Final version for ICASSP 2020

Recent work has shown that speech paired with images can be used to learn semantically meaningful speech representations even without any textual supervision. In real-world low-resource settings, however, we often have access to some transcribed speech. We study whether and how visual grounding is useful in the presence of varying amounts of textual supervision. In particular, we consider the task of semantic speech retrieval in a low-resource setting. We use a previously studied data set and task, where models are trained on images with spoken captions and evaluated on human judgments of semantic relevance. We propose a multitask learning approach to leverage both visual and textual modalities, with visual supervision in the form of keyword probabilities from an external tagger. We find that visual grounding is helpful even in the presence of textual supervision, and we analyze this effect over a range of sizes of transcribed data sets. With ~5 hours of transcribed speech, we obtain 23% higher average precision when also using visual supervision.

A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode retrieval. Here we consider how such models can be used for query-by-example (QbE) search, the task of retrieving utterances relevant to a given spoken query. We are particularly interested in semantic QbE, where the task is not only to retrieve utterances containing exact instances of the query, but also utterances whose meaning is relevant to the query. We follow a segmental QbE approach where variable-duration speech segments (queries, search utterances) are mapped to fixed-dimensional embedding vectors. We show that a QbE system using an embedding function trained on visually grounded speech data outperforms a purely acoustic QbE system in terms of both exact and semantic retrieval performance., Comment: Accepted to ICASSP 2019

Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and requires only a parallel corpus of speech and text for training. However, unlike in conventional approaches that combine separate acoustic and language models, it is not clear how to use additional (unpaired) text. While there has been previous work on methods addressing this problem, a thorough comparison among methods is still lacking. In this paper, we compare a suite of past methods and some of our own proposed methods for using unpaired text data to improve encoder-decoder models. For evaluation, we use the medium-sized Switchboard data set and the large-scale Google voice search and dictation data sets. Our results confirm the benefits of using unpaired text across a range of methods and data sets. Surprisingly, for first-pass decoding, the rather simple approach of shallow fusion performs best across data sets. However, for Google data sets we find that cold fusion has a lower oracle error rate and outperforms other approaches after second-pass rescoring on the Google voice search data set., Comment: Accepted in SLT 2018

Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at a time. Neural segmental models are segmental models that use neural network-based weight functions. Neural segmental models have achieved competitive results for speech recognition, and their end-to-end training has been explored in several studies. In this work, we review neural segmental models, which can be viewed as consisting of a neural network-based acoustic encoder and a finite-state transducer decoder. We study end-to-end segmental models with different weight functions, including ones based on frame-level neural classifiers and on segmental recurrent neural networks. We study how reducing the search space size impacts performance under different weight functions. We also compare several loss functions for end-to-end training. Finally, we explore training approaches, including multi-stage vs. end-to-end training and multitask training that combines segmental and frame-level losses.

In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features using a convolutional neural network over energy and pitch trajectories coupled with an attention-based recurrent neural network that accepts text and prosodic features. We find that different types of acoustic-prosodic features are individually helpful, and together give statistically significant improvements in parse and disfluency detection F1 scores over a strong text-only baseline. For this study with known sentence boundaries, error analyses show that the main benefit of acoustic-prosodic features is in sentences with disfluencies, attachment decisions are most improved, and transcription errors obscure gains from prosody., Comment: Accepted in NAACL HLT 2018