Search

This paper proposes a method to effectively perform joint training-and-pruning based on adaptive dropout layers with unit-wise retention probabilities. The proposed method is based on the estimation of a unit-wise retention probability in a dropout layer. A unit that is estimated to have a small retention probability can be considered to be prunable. The retention probability of the unit is estimated using back-propagation and the Gumbel-Softmax technique. This pruning method is applied at several application points in Conformers such that the effective number of parameters can be significantly reduced. Specifically, adaptive dropout layers are introduced in three locations in each Conformer block: (a) the hidden layer of the feed-forward-net component, (b) the query vectors and the value vectors of the self-attention component, and (c) the input vectors of the LConv component. The proposed method is evaluated by conducting a speech recognition experiment on the LibriSpeech task. It was shown that this approach could simultaneously achieve a parameter reduction and accuracy improvement. The word error rates improved by approx 1% while reducing the number of parameters by 54%.

This paper introduces FLEURS-R, a speech restoration applied version of the Few-shot Learning Evaluation of Universal Representations of Speech (FLEURS) corpus. FLEURS-R maintains an N-way parallel speech corpus in 102 languages as FLEURS, with improved audio quality and fidelity by applying the speech restoration model Miipher. The aim of FLEURS-R is to advance speech technology in more languages and catalyze research including text-to-speech (TTS) and other speech generation tasks in low-resource languages. Comprehensive evaluations with the restored speech and TTS baseline models trained from the new corpus show that the new corpus obtained significantly improved speech quality while maintaining the semantic contents of the speech. The corpus is publicly released via Hugging Face.

This paper introduces a new speech dataset called ``LibriTTS-R'' designed for text-to-speech (TTS) use. It is derived by applying speech restoration to the LibriTTS corpus, which consists of 585 hours of speech data at 24 kHz sampling rate from 2,456 speakers and the corresponding texts. The constituent samples of LibriTTS-R are identical to those of LibriTTS, with only the sound quality improved. Experimental results show that the LibriTTS-R ground-truth samples showed significantly improved sound quality compared to those in LibriTTS. In addition, neural end-to-end TTS trained with LibriTTS-R achieved speech naturalness on par with that of the ground-truth samples. The corpus is freely available for download from \url{http://www.openslr.org/141/}., Comment: Accepted to Interspeech 2023

Speech restoration (SR) is a task of converting degraded speech signals into high-quality ones. In this study, we propose a robust SR model called Miipher, and apply Miipher to a new SR application: increasing the amount of high-quality training data for speech generation by converting speech samples collected from the Web to studio-quality. To make our SR model robust against various degradation, we use (i) a speech representation extracted from w2v-BERT for the input feature, and (ii) a text representation extracted from transcripts via PnG-BERT as a linguistic conditioning feature. Experiments show that Miipher (i) is robust against various audio degradation and (ii) enable us to train a high-quality text-to-speech (TTS) model from restored speech samples collected from the Web. Audio samples are available at our demo page: google.github.io/df-conformer/miipher/, Comment: Accepted to WASPAA 2023

Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characterized by the iterative denoising framework and adversarial training, respectively. This study proposes a fast and high-quality neural vocoder called \textit{WaveFit}, which integrates the essence of GANs into a DDPM-like iterative framework based on fixed-point iteration. WaveFit iteratively denoises an input signal, and trains a deep neural network (DNN) for minimizing an adversarial loss calculated from intermediate outputs at all iterations. Subjective (side-by-side) listening tests showed no statistically significant differences in naturalness between human natural speech and those synthesized by WaveFit with five iterations. Furthermore, the inference speed of WaveFit was more than 240 times faster than WaveRNN. Audio demos are available at \url{google.github.io/df-conformer/wavefit/}., Comment: Accepted to IEEE SLT 2022

Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, we propose SpecGrad that adapts the diffusion noise so that its time-varying spectral envelope becomes close to the conditioning log-mel spectrogram. This adaptation by time-varying filtering improves the sound quality especially in the high-frequency bands. It is processed in the time-frequency domain to keep the computational cost almost the same as the conventional DDPM-based neural vocoders. Experimental results showed that SpecGrad generates higher-fidelity speech waveform than conventional DDPM-based neural vocoders in both analysis-synthesis and speech enhancement scenarios. Audio demos are available at wavegrad.github.io/specgrad/., Comment: Accepted to Interspeech 2022

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of end-to-end speech recognizers always requires transcribed utterances. Since end-to-end models are also known to be severely data hungry, this constraint is crucial especially because obtaining transcribed utterances is costly and can possibly be impractical or impossible. This paper proposes a method for alleviating this issue by transferring knowledge from a language model neural network that can be pretrained with text-only data. Specifically, this paper attempts to transfer semantic knowledge acquired in embedding vectors of large-scale language models. Since embedding vectors can be assumed as implicit representations of linguistic information such as part-of-speech, intent, and so on, those are also expected to be useful modeling cues for ASR decoders. This paper extends two types of ASR decoders, attention-based decoders and neural transducers, by modifying training loss functions to include embedding prediction terms. The proposed systems were shown to be effective for error rate reduction without incurring extra computational costs in the decoding phase., Comment: To be presented in ICASSP 2022

Speech enhancement (SE) is used as a frontend in speech applications including automatic speech recognition (ASR) and telecommunication. A difficulty in using the SE frontend is that the appropriate noise reduction level differs depending on applications and/or noise characteristics. In this study, we propose "signal-to-noise ratio improvement (SNRi) target training"; the SE frontend is trained to output a signal whose SNRi is controlled by an auxiliary scalar input. In joint training with a backend, the target SNRi value is estimated by an auxiliary network. By training all networks to minimize the backend task loss, we can estimate the appropriate noise reduction level for each noisy input in a data-driven scheme. Our experiments showed that the SNRi target training enables control of the output SNRi. In addition, the proposed joint training relatively reduces word error rate by 4.0\% and 5.7\% compared to a Conformer-based standard ASR model and conventional SE-ASR joint training model, respectively. Furthermore, by analyzing the predicted target SNRi, we observed the jointly trained network automatically controls the target SNRi according to noise characteristics. Audio demos are available in our demo page: google.github.io/df-conformer/snri_target/., Comment: Submitted to Interspeech 2022 (v1 has been rejected from ICASSP 2022)

Single-channel speech enhancement (SE) is an important task in speech processing. A widely used framework combines an analysis/synthesis filterbank with a mask prediction network, such as the Conv-TasNet architecture. In such systems, the denoising performance and computational efficiency are mainly affected by the structure of the mask prediction network. In this study, we aim to improve the sequential modeling ability of Conv-TasNet architectures by integrating Conformer layers into a new mask prediction network. To make the model computationally feasible, we extend the Conformer using linear complexity attention and stacked 1-D dilated depthwise convolution layers. We trained the model on 3,396 hours of noisy speech data, and show that (i) the use of linear complexity attention avoids high computational complexity, and (ii) our model achieves higher scale-invariant signal-to-noise ratio than the improved time-dilated convolution network (TDCN++), an extended version of Conv-TasNet., Comment: 5 pages, 2 figure. accepted for WASPAA 2021

End-to-end (E2E) modeling is advantageous for automatic speech recognition (ASR) especially for Japanese since word-based tokenization of Japanese is not trivial, and E2E modeling is able to model character sequences directly. This paper focuses on the latest E2E modeling techniques, and investigates their performances on character-based Japanese ASR by conducting comparative experiments. The results are analyzed and discussed in order to understand the relative advantages of long short-term memory (LSTM), and Conformer models in combination with connectionist temporal classification, transducer, and attention-based loss functions. Furthermore, the paper investigates on effectivity of the recent training techniques such as data augmentation (SpecAugment), variational noise injection, and exponential moving average. The best configuration found in the paper achieved the state-of-the-art character error rates of 4.1%, 3.2%, and 3.5% for Corpus of Spontaneous Japanese (CSJ) eval1, eval2, and eval3 tasks, respectively. The system is also shown to be computationally efficient thanks to the efficiency of Conformer transducers., Comment: to be published in INTERSPEECH2021

Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models are composed of modular building blocks that are flexible and easily extensible, and experiment configurations are centralized and highly customizable. Distributed training and quantized inference are supported directly within the framework, and it contains existing implementations of a large number of utilities, helper functions, and the newest research ideas. Lingvo has been used in collaboration by dozens of researchers in more than 20 papers over the last two years. This document outlines the underlying design of Lingvo and serves as an introduction to the various pieces of the framework, while also offering examples of advanced features that showcase the capabilities of the framework.

Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text (or top N hypotheses) into a set of domains, intents, and arguments. These modules are typically optimized independently. In this paper, we formulate audio to semantic understanding as a sequence-to-sequence problem [1]. We propose and compare various encoder-decoder based approaches that optimize both modules jointly, in an end-to-end manner. Evaluations on a real-world task show that 1) having an intermediate text representation is crucial for the quality of the predicted semantics, especially the intent arguments and 2) jointly optimizing the full system improves overall accuracy of prediction. Compared to independently trained models, our best jointly trained model achieves similar domain and intent prediction F1 scores, but improves argument word error rate by 18% relative.

Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the training domain, performance significantly drops. This work explores the idea of building a single domain-invariant model for varied use-cases by combining large scale training data from multiple application domains. Our final system is trained using 162,000 hours of speech. Additionally, each utterance is artificially distorted during training to simulate effects like background noise, codec distortion, and sampling rates. Our results show that, even at such a scale, a model thus trained works almost as well as those fine-tuned to specific subsets: A single model can be robust to multiple application domains, and variations like codecs and noise. More importantly, such models generalize better to unseen conditions and allow for rapid adaptation -- we show that by using as little as 10 hours of data from a new domain, an adapted domain-invariant model can match performance of a domain-specific model trained from scratch using 70 times as much data. We also highlight some of the limitations of such models and areas that need addressing in future work.

In this paper, we describe how to efficiently implement an acoustic room simulator to generate large-scale simulated data for training deep neural networks. Even though Google Room Simulator in [1] was shown to be quite effective in reducing the Word Error Rates (WERs) for far-field applications by generating simulated far-field training sets, it requires a very large number of Fast Fourier Transforms (FFTs) of large size. Room Simulator in [1] used approximately 80 percent of Central Processing Unit (CPU) usage in our CPU + Graphics Processing Unit (GPU) training architecture [2]. In this work, we implement an efficient OverLap Addition (OLA) based filtering using the open-source FFTW3 library. Further, we investigate the effects of the Room Impulse Response (RIR) lengths. Experimentally, we conclude that we can cut the tail portions of RIRs whose power is less than 20 dB below the maximum power without sacrificing the speech recognition accuracy. However, we observe that cutting RIR tail more than this threshold harms the speech recognition accuracy for rerecorded test sets. Using these approaches, we were able to reduce CPU usage for the room simulator portion down to 9.69 percent in CPU/GPU training architecture. Profiling result shows that we obtain 22.4 times speed-up on a single machine and 37.3 times speed up on Google's distributed training infrastructure., Comment: Published at INTERSPEECH 2018. (https://www.isca-speech.org/archive/Interspeech_2018/abstracts/2566.html)

Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM), pronunciation (PM) and language (LM) models into a single neural network. In this work, we look at one such sequence-to-sequence model, namely listen, attend and spell (LAS), and explore the possibility of training a single model to serve different English dialects, which simplifies the process of training multi-dialect systems without the need for separate AM, PM and LMs for each dialect. We show that simply pooling the data from all dialects into one LAS model falls behind the performance of a model fine-tuned on each dialect. We then look at incorporating dialect-specific information into the model, both by modifying the training targets by inserting the dialect symbol at the end of the original grapheme sequence and also feeding a 1-hot representation of the dialect information into all layers of the model. Experimental results on seven English dialects show that our proposed system is effective in modeling dialect variations within a single LAS model, outperforming a LAS model trained individually on each of the seven dialects by 3.1 ~ 16.5% relative., Comment: submitted to ICASSP 2018

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural network. In previous work, we have shown that such architectures are comparable to state-of-theart ASR systems on dictation tasks, but it was not clear if such architectures would be practical for more challenging tasks such as voice search. In this work, we explore a variety of structural and optimization improvements to our LAS model which significantly improve performance. On the structural side, we show that word piece models can be used instead of graphemes. We also introduce a multi-head attention architecture, which offers improvements over the commonly-used single-head attention. On the optimization side, we explore synchronous training, scheduled sampling, label smoothing, and minimum word error rate optimization, which are all shown to improve accuracy. We present results with a unidirectional LSTM encoder for streaming recognition. On a 12, 500 hour voice search task, we find that the proposed changes improve the WER from 9.2% to 5.6%, while the best conventional system achieves 6.7%; on a dictation task our model achieves a WER of 4.1% compared to 5% for the conventional system., Comment: ICASSP camera-ready version