The recent wave of audio foundation models (FMs) could provide new capabilities for conversational modeling. However, there have been limited efforts to evaluate these audio FMs comprehensively on their ability to have natural and interactive conversations. To engage in meaningful conversation with the end user, we would want the FMs to additionally perform a fluent succession of turns without too much overlapping speech or long stretches of silence. Inspired by this, we ask whether the recently proposed audio FMs can understand, predict, and perform turn-taking events? To answer this, we propose a novel evaluation protocol that can assess spoken dialog system's turn-taking capabilities using a supervised model as a judge that has been trained to predict turn-taking events in human-human conversations. Using this protocol, we present the first comprehensive user study that evaluates existing spoken dialogue systems on their ability to perform turn-taking events and reveal many interesting insights, such as they sometimes do not understand when to speak up, can interrupt too aggressively and rarely backchannel. We further evaluate multiple open-source and proprietary audio FMs accessible through APIs on carefully curated test benchmarks from Switchboard to measure their ability to understand and predict turn-taking events and identify significant room for improvement. We will open source our evaluation platform to promote the development of advanced conversational AI systems.

Wen Wu, Bo Li, Chao Zhang, Chung-Cheng Chiu, Qiujia Li, Junwen Bai, Tara Sainath, Phil Woodland. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

We present a joint Speech and Language Model (SLM), a multitask, multilingual, and dual-modal model that takes advantage of pretrained foundational speech and language models. SLM freezes the pretrained foundation models to maximally preserves their capabilities, and only trains a simple adapter with just 1% (156M) of the foundation models’ parameters. This adaptation not only leads SLM to achieve strong performance on conventional tasks such as automatic speech recognition (ASR) and automatic speech translation (AST), but also unlocks the novel capability of zero-shot instruction-following for more diverse tasks. Given a speech input and a text instruction, SLM is able to perform unseen generation tasks including contextual biasing ASR using real-time context, dialog generation, speech continuation, and question answering. Our approach demonstrates that the representational gap between pretrained speech and language models is narrower than one would expect, and can be bridged by a simple adaptation mechanism. As a result, SLM is not only efficient to train, but also inherits strong capabilities already present in foundation models of different modalities.

Research on speech-to-speech translation (S2ST) has progressed rapidly in recent years. Many end-to-end systems have been proposed and show advantages over conventional cascade systems, which are often composed of recognition, translation and synthesis sub-systems. However, most of end-to-end systems still rely on intermediate textual supervision during training, which makes it infeasible to work for languages without written forms. In this work, we propose a novel model, Textless Translatotron, which is based on Translatotron 2 [1], for training an end-to-end direct S2ST model without any textual supervision. Instead of jointly training with an auxiliary task predicting target phonemes as in Translatotron 2, the proposed model uses an auxiliary task predicting discrete speech representations which are obtained from learned or random speech quantizers. When a speech encoder pre-trained with unsupervised speech data is used for both models, the proposed model obtains translation quality nearly on-par with Translatotron 2 on the multilingual CVSS-C corpus [2] as well as the bilingual Fisher Spanish-English corpus [3]. On the latter, it outperforms the prior state-of-the-art textless model by +18.5 BLEU.

In this paper, we explore reducing computational latency of the 2-pass cascaded encoder model [1]. Specifically, we experiment with reducing the size of the causal 1st-pass and adding capacity to the non-causal 2nd-pass, such that the overall latency can be reduced without loss of quality. In addition, we explore using a confidence model for deciding to stop 2nd-pass recognition if we are confident in the 1st-pass hypothesis. Overall, we are able to reduce latency by a factor of 1.7X, compared to the baseline cascaded encoder from [1]. Secondly, with the added capacity in the non-causal 2nd-pass, we find that we can improve WER by up to 7% relative using wav2vec and minimum word-error-rate (MWER) training.

We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In particular the quantizer projects speech inputs with a randomly initialized matrix, and does a nearest-neighbor lookup in a randomly-initialized codebook. Neither the matrix nor the codebook are updated during self-supervised learning. Since the random-projection quantizer is not trained and is separated from the speech recognition model, the design makes the approach flexible and is compatible with universal speech recognition architecture. On LibriSpeech our approach achieves similar word-error-rates as previous work using self-supervised learning with non-streaming models, and provides lower word-error-rates than previous work with streaming models. On multilingual tasks the approach also provides significant improvement over wav2vec 2.0 and w2v-BERT.

Motivated by the success of masked language modeling (MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech representation learning. w2v-BERT is a framework that combines contrastive learning and MLM, where the former trains the model to discretize input continuous speech signals into a finite set of discriminative speech tokens, and the latter trains the model to learn contextualized speech representations via solving a masked prediction task consuming the discretized tokens. In contrast to existing MLM-based speech pre-training frameworks such as HuBERT, which relies on an iterative re-clustering and re-training process, or vq-wav2vec, which concatenates two separately trained modules, w2v-BERT can be optimized in an end-to-end fashion by solving the two self-supervised tasks (the contrastive task and MLM) simultaneously. Our experiments show that w2v-BERT achieves competitive results compared to current state-of-the-art pre-trained models on the LibriSpeech benchmarks when using the Libri-Light 60k corpus as the unsupervised data. In particular, when compared to published models such as conformer-based wav2vec 2.0 and HuBERT, our model shows 5% to 10% relative WER reduction on the test-clean and test-other subsets. When applied to the Google's Voice Search traffic dataset, w2v-BERT outperforms our internal conformer-based wav2vec 2.0 by more than 30% relatively.

This work introduces cross-attention conformer, an attention-based architecture for context modeling in speech enhancement. Given that the context information can often be sequential, and of different length as the audio that is to be enhanced, we make use of cross-attention to summarize and merge contextual information with input features. Building upon the recently proposed conformer model that uses self attention layers as building blocks, the proposed cross-attention conformer can be used to build deep contextual models. As a concrete example, we show how noise context, i.e., short noise-only audio segment preceding an utterance, can be used to build a speech enhancement feature frontend using cross-attention conformer layers for improving noise robustness of automatic speech recognition.

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with no future context, compared to their non-streaming counterparts. Consequently, streaming models usually perform worse than non-streaming models. We propose a novel and effective learning method by leveraging a non-streaming ASR model as a teacher to generate transcripts on an arbitrarily large data set, which is then used to distill knowledge into streaming ASR models. This way, we scale the training of streaming models to up to 3 million hours of YouTube audio. Experiments show that our approach can significantly reduce the word error rate (WER) of RNN-T models not only on LibriSpeech but also on YouTube data in four languages. For example, in French, we are able to reduce the WER by 16.4% relatively to a baseline streaming model by leveraging a non-streaming teacher model trained on the same amount of labeled data as the baseline.

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However, the model still tends to delay the predictions towards the end and thus has much higher partial latency compared to a conventional ASR model. To address this issue, we look at encouraging the E2E model to emit words early, through an algorithm called FastEmit [3]. Naturally, improving on latency results in a quality degradation. To address this, we explore replacing the LSTM layers in the encoder of our E2E model with Conformer layers [4], which has shown good improvements for ASR. Secondly, we also explore running a 2nd-pass beam search to improve quality. In order to ensure the 2nd-pass completes quickly, we explore non-causal Conformer layers that feed into the same 1st-pass RNN-T decoder, an algorithm called Cascaded Encoders [5]. Overall, the Conformer RNN-T with Cascaded Encoders offers a better quality and latency tradeoff for streaming ASR.

End-to-end (E2E) automatic speech recognition (ASR) models, by now, have shown competitive performance on several benchmarks. These models are structured to either operate in streaming or non-streaming mode. This work presents cascaded encoders for building a single E2E ASR model that can operate in both these modes simultaneously. The proposed model consists of streaming and non-streaming encoders. Input features are first processed by the streaming encoder; the non-streaming encoder operates exclusively on the output of the streaming encoder. A single decoder then learns to decode either using the output of the streaming or the non-streaming encoder. Results show that this model achieves similar word error rates (WER) as a standalone streaming model when operating in streaming mode, and obtains 10% – 27% relative improvement when operating in non-streaming mode. Our results also show that the proposed approach outperforms existing E2E two-pass models, especially on long-form speech.

Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In this paper, we develop a distillation method for RNN-Transducer (RNN-T) models, a popular end-to-end neural network architecture for streaming speech recognition. Our proposed distillation loss is simple and efficient, and uses only the "y" and "blank" posterior probabilities from the RNN-T output probability lattice. We study the effectiveness of the proposed approach in improving the accuracy of sparse RNN-T models obtained by gradually pruning a larger uncompressed model, which also serves as the teacher during distillation. With distillation of 60% and 90% sparse multi-domain RNN-T models, we obtain WER reductions of 4.3% and 12.1% respectively, on a noisy FarField eval set. We also present results of experiments on LibriSpeech, where the introduction of the distillation loss yields a 4.8% relative WER reduction on the test-other dataset for a small Conformer model.

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing approaches including Early and Late Penalties [1] and Constrained Alignments [2], [3] penalize emission delay by manipulating per-token or per-frame probability prediction in sequence transducer models [4]. While being successful in reducing delay, these approaches suffer from significant accuracy regression and also require additional word alignment information from an existing model. In this work, we propose a sequence-level emission regularization method, named FastEmit, that applies latency regularization directly on per-sequence probability in training transducer models, and does not require any alignment. We demonstrate that FastEmit is more suitable to the sequence-level optimization of transducer models [4] for streaming ASR by applying it on various end-to-end streaming ASR networks including RNN-Transducer [5], Transformer-Transducer [6], [7], ConvNet-Transducer [8] and Conformer-Transducer [9]. We achieve 150 ~ 300ms latency reduction with significantly better accuracy over previous techniques on a Voice Search test set. FastEmit also improves streaming ASR accuracy from 4.4%/8.9% to 3.1%/7.5% WER, meanwhile reduces 90th percentile latency from 210ms to only 30ms on LibriSpeech.

We combine recent advancements in end-to-end speech recognition to non-autoregressive automatic speech recognition. We push the limits of non-autoregressive state-of-the-art results for multiple datasets: LibriSpeech, Fisher+Switchboard and Wall Street Journal. Key to our recipe, we leverage CTC on giant Conformer neural network architectures with SpecAugment and wav2vec2 pre-training. We achieve 1.8%/3.6% WER on LibriSpeech test/test-other sets, 5.1%/9.8% WER on Switchboard, and 3.4% on the Wall Street Journal, all without a language model.

In recent years, all-neural end-to-end approaches have obtained state-of-the-art results on several challenging automatic speech recognition (ASR) tasks. However, most existing works focus on building ASR models where train and test data are drawn from the same domain. This results in poor generalization characteristics on mismatched-domains: e.g., end-to-end models trained on short segments perform poorly when evaluated on longer utterances. In this work, we analyze the generalization properties of streaming and non-streaming recurrent neural network transducer (RNN-T) based end-to-end models in order to identify model components that negatively affect generalization performance. We propose two solutions: combining multiple regularization techniques during training, and using dynamic overlapping inference. On a long-form YouTube test set, when the non-streaming RNN-T model is trained with shorter segments of data, the proposed combination improves word error rate (WER) from 22.3% to 14.8%; when the streaming RNN-T model trained on short Search queries, the proposed techniques improve WER on the YouTube set from 67.0% to 25.3%. Finally, when trained on Librispeech, we find that dynamic overlapping inference improves WER on YouTube from 99.8% to 33.0%.

In this paper, we propose to use pre-trained features from end-to-end ASR models to solve speech sentiment analysis as a down-stream task. We show that end-to-end ASR features, which integrate both acoustic and text information from speech, achieve promising results. We use RNN with self-attention as the sentiment classifier, which also provides an easy visualization through attention weights to help interpret model predictions. We use well benchmarked IEMOCAP dataset and a new large-scale speech sentiment dataset SWBD-sentiment for evaluation. Our approach improves the-state-of-the-art accuracy on IEMOCAP from 66.6% to 71.7%, and achieves an accuracy of 70.10% on SWBD-sentiment with more than 49,500 utterances.

Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhancing the performance of end-to-end networks on public datasets. In this paper, we demonstrate its effectiveness on tasks with large scale datasets by investigating its application to the Google Multidomain Dataset (Narayanan et al., 2018). We achieve improvement across all test domains by mixing raw training data augmented with SpecAugment and noise-perturbed training data when training the acoustic model. We also introduce a modification of SpecAugment that adapts the time mask size and/or multiplicity depending on the length of the utterance, which can potentially benefit large scale tasks. By using adaptive masking, we are able to further improve the performance of the Listen, Attend and Spell model on LibriSpeech to 2.2% WER on test-clean and 5.2% WER on test-other.

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent Neural Network Transducer (RNN-T) model and a second-pass Listen, Attend, Spell (LAS) rescorer that surpasses a conventional model in both quality and latency. On the quality side, we incorporate a large number of utterances across varied domains [1] to increase acoustic diversity and the vocabulary seen by the model. We also train with accented English speech to make the model more robust to different pronunciations. In addition, given the increased amount of training data, we explore a varied learning rate schedule. On the latency front, we explore using the end-of-sentence decision emitted by the RNN-T model to close the microphone, and also introduce various optimizations to improve the speed of LAS rescoring. Overall, we find that RNN-T+LAS offers a better WER and latency tradeoff compared to a conventional model. For example, for the same latency, RNN-T+LAS obtains a 8% relative improvement in WER, while being more than 400-times smaller in model size.

Recently, we introduced a two-pass on-device end-to-end (E2E) speech recognition model, which runs RNN-T in the first-pass and then rescores/redecodes the result using a noncausal Listen, Attend and Spell (LAS) decoder. This on-device model obtained similar performance to a state-of-the-art conventional model. However, like many E2E models, it suffers from being trained only on supervised audio-text pairs and thus performs poorly on rare words compared to a conventional model which incorporates a language model trained on a much larger text corpus. In this work, we introduce a joint acoustic and text decoder (JATD) into the LAS decoder, which makes it possible to incorporate a much larger text corpus into training. We find that the JATD model obtains in a 3-10% relative improvement in WER compared to a LAS decoder trained only on supervised audio-text pairs across a variety of proper noun test sets.

Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively.In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way.To this regard, we propose the convolution-augmented transformer for speech recognition, named Conformer.Conformer significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies.On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3%without using a language model and 1.9%/3.9%with an external language model on test/testother.We also observe competitive performance of 2.7%/6.3%with a small model of only 10M parameters.

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind RNN/transformer based models in performance.In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet.ContextNet features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules.In addition, we propose a simple scaling method that scales the widths of Con-textNet that achieves good trade-off between computation and accuracy.We demonstrate that on the widely used Librispeech benchmark, ContextNet achieves a word error rate (WER) of 2.1%/4.6%without external language model (LM), 1.9%/4.1% with LM and 2.9%/7.0%with only 10M parameters on the clean/noisy LibriSpeech test sets.This compares to the best previously published model of 2.0%/4.6%with LM and 3.9%/11.3%with 20M parameters.The superiority of the proposed ContextNet model is also verified on a much larger internal dataset.

Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-device speech recognition, where a 1st-pass model generates hypotheses in a streaming fashion, and a 2nd-pass model re-scores the hypotheses with full audio sequence context. The 2nd-pass model plays a key role in the quality improvement of the end-to-end model to surpass the conventional model. One main challenge of the two-pass model is the computation latency introduced by the 2nd-pass model. Specifically, the original design of the two-pass model uses LSTMs for the 2nd-pass model, which are subject to long latency as they are constrained by the recurrent nature and have to run inference sequentially. In this work we explore replacing the LSTM layers in the 2nd-pass rescorer with Transformer layers, which can process the entire hypothesis sequences in parallel and can therefore utilize the on-device computation resources more efficiently. Compared with an LSTM-based baseline, our proposed Transformer rescorer achieves more than 50% latency reduction with quality improvement.

Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly. Noisy student training is an iterative self-training method that leverages augmentation to improve network performance. In this work, we adapt and improve noisy student training for automatic speech recognition, employing (adaptive) SpecAugment as the augmentation method. We find effective methods to filter, balance and augment the data generated in between self-training iterations. By doing so, we are able to obtain word error rates (WERs) 4.2%/8.6% on the clean/noisy LibriSpeech test sets by only using the clean 100h subset of LibriSpeech as the supervised set and the rest (860h) as the unlabeled set. Furthermore, we are able to achieve WERs 1.7%/3.4% on the clean/noisy LibriSpeech test sets by using the unlab-60k subset of LibriLight as the unlabeled set for LibriSpeech 960h. We are thus able to improve upon the previous state-of-the-art clean/noisy test WERs achieved on LibriSpeech 100h (4.74%/12.20%) and LibriSpeech (1.9%/4.1%).

Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey, Chung-Cheng Chiu, Semih Yavuz, Ruoming Pang, Wei Li, Colin Raffel. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems [1], [2]. However, previous studies have focused primarily on short utterances that typically last for just a few seconds or, at most, a few tens of seconds. Whether such architectures are practical on long utterances that last from minutes to hours remains an open question. In this paper, we both investigate and improve the performance of end-to-end models on long-form transcription. We first present an empirical comparison of different end-to-end models on a real world long-form task and demonstrate that the RNN-T model is much more robust than attention-based systems in this regime. We next explore two improvements to attention-based systems that significantly improve its performance: restricting the attention to be monotonic, and applying a novel decoding algorithm that breaks long utterances into shorter overlapping segments. Combining these two improvements, we show that attention-based end-to-end models can be very competitive to RNN-T on long-form speech recognition.

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the ability of E2E models to generalize to unseen domains, where we find that models trained on short utterances fail to generalize to long-form speech. We propose two complementary solutions to address this: training on diverse acoustic data, and LSTM state manipulation to simulate long-form audio when training using short utterances. On a synthesized long-form test set, adding data diversity improves word error rate (WER) by 90% relative, while simulating long-form training improves it by 67% relative, though the combination doesn't improve over data diversity alone. On a real long-form call-center test set, adding data diversity improves WER by 40% relative. Simulating long-form training on top of data diversity improves performance by an additional 27% relative.

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of error compounding. However, the quality of end-to-end ST is often limited by a paucity of training data, since it is difficult to collect large parallel corpora of speech and translated transcript pairs. Previous studies have proposed the use of pre-trained components and multi-task learning in order to benefit from weakly supervised training data, such as speech-to-transcript or text-to-foreign-text pairs. In this paper, we demonstrate that using pre-trained MT or text-to-speech (TTS) synthesis models to convert weakly supervised data into speech-to-translation pairs for ST training can be more effective than multi-task learning. Furthermore, we demonstrate that a high quality end-to-end ST model can be trained using only weakly supervised datasets, and that synthetic data sourced from unlabeled monolingual text or speech can be used to improve performance. Finally, we discuss methods for avoiding overfitting to synthetic speech with a quantitative ablation study.

We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5'00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER.

The requirements for many applications of state-of-the-art speech recognition systems include not only low word error rate (WER) but also low latency. Specifically, for many use-cases, the system must be able to decode utterances in a streaming fashion and faster than real-time. Recently, a streaming recurrent neural network transducer (RNN-T) end-to-end (E2E) model has shown to be a good candidate for on-device speech recognition, with improved WER and latency metrics compared to conventional on-device models [1]. However, this model still lags behind a large state-of-the-art conventional model in quality [2]. On the other hand, a non-streaming E2E Listen, Attend and Spell (LAS) model has shown comparable quality to large conventional models [3]. This work aims to bring the quality of an E2E streaming model closer to that of a conventional system by incorporating a LAS network as a second-pass component, while still abiding by latency constraints. Our proposed two-pass model achieves a 17%-22% relative reduction in WER compared to RNN-T alone and increases latency by a small fraction over RNN-T.

Maximum-likelihood estimation (MLE) is one of the most widely used approaches for training structured prediction models for textgeneration based natural language processing applications.However, besides exposure bias, models trained with MLE suffer from wrong objective problem where they are trained to maximize the word-level correct next step prediction, but are evaluated with respect to sequence-level discrete metrics such as ROUGE and BLEU.Several variants of policy-gradient methods address some of these problems by optimizing for final discrete evaluation metrics and showing improvements over MLE training for downstream tasks like text summarization and machine translation.However, policy-gradient methods suffers from high sample variance, making the training process very difficult and unstable.In this paper, we present an alternative direction towards mitigating this problem by introducing a new objective (CALCS) based on a differentiable surrogate of longest common subsequence (LCS) measure that captures sequence-level structure similarity.Experimental results on abstractive summarization and machine translation validate the effectiveness of the proposed approach.

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-the-art 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.

There has recently been significant interest in hard attention models for tasks such as object recognition, visual captioning and speech recognition. Hard attention offers benefits over soft attention such as decreased computational cost, but training hard attention models can be difficult because of the discrete latent variables they introduce. Previous work used REINFORCE to approach these issues, however, it suffers from high-variance gradient estimates, resulting in slow convergence. In this paper, we tackle the problem of learning hard attention for a sequential task using variational inference methods, specifically the recently introduced Variational Inference for Monte Carlo Objectives (VIMCO) and Neural Variational Inference (NVIL). Furthermore, we propose a novel baseline that adapts VIMCO to this setting. We demonstrate our method on a phoneme recognition task in clean and noisy environments and show that our method outperforms REINFORCE, with the difference being greater for a more complicated task.

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system performance is usually measured in terms of word error rate (WER), not log-likelihood. Traditional ASR systems benefit from discriminative sequence training which optimizes criteria such as the state-level minimum Bayes risk (sMBR) which are more closely related to WER. In the present work, we explore techniques to train attention-based models to directly minimize expected word error rate. We consider two loss functions which approximate the expected number of word errors: either by sampling from the model, or by using N-best lists of decoded hypotheses, which we find to be more effective than the sampling-based method. In experimental evaluations, we find that the proposed training procedure improves performance by up to 8.2% relative to the baseline system. This allows us to train grapheme-based, uni-directional attention-based models which match the performance of a traditional, state-of-the-art, discriminative sequence-trained system on a mobile voice-search task.

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in performance compared to non-streaming models such as Listen, Attend and Spell (LAS). In this paper, we present various improvements to NT. Specifically, we look at increasing the window over which NT computes attention, mainly by looking backwards in time so the model still remains online. In addition, we explore initializing a NT model from a LAS-trained model so that it is guided with a better alignment. Finally, we explore including stronger language models such as using wordpiece models, and applying an external LM during the beam search. On a Voice Search task, we find with these improvements we can get NT to match the performance of LAS.

For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-to-end models which seek to combine acoustic, pronunciation, and language model components into a single neural network. Such systems, which typically predict graphemes or words, simplify the recognition process since they remove the need for a separate expert-curated pronunciation lexicon to map from phoneme-based units to words. However, there has been little previous work comparing phoneme-based versus grapheme-based sub-word units in the end-to-end modeling framework, to determine whether the gains from such approaches are primarily due to the new probabilistic model, or from the joint learning of the various components with grapheme-based units. In this work, we conduct detailed experiments which are aimed at quantifying the value of phoneme-based pronunciation lexica in the context of end-to-end models. We examine phoneme-based end-to-end models, which are contrasted against grapheme-based ones on a large vocabulary English Voice-search task, where we find that graphemes do indeed outperform phonemes. We also compare grapheme and phoneme-based approaches on a multi-dialect English task, which once again confirm the superiority of graphemes, greatly simplifying the system for recognizing multiple dialects.

In this paper we document our experiences with developing speech recognition for medical transcription -a system that automatically transcribes doctor-patient conversations.Towards this goal, we built a system along two different methodological lines -a Connectionist Temporal Classification (CTC) phoneme based model and a Listen Attend and Spell (LAS) grapheme based model.To train these models we used a corpus of anonymized conversations representing approximately 14,000 hours of speech.Because of noisy transcripts and alignments in the corpus, a significant amount of effort was invested in data cleaning issues.We describe a two-stage strategy we followed for segmenting the data.The data cleanup and development of a matched language model was essential to the success of the CTC based models.The LAS based models, however were found to be resilient to alignment and transcript noise and did not require the use of language models.CTC models were able to achieve a word error rate of 20.1%, and the LAS models were able to achieve 18.3%.Our analysis shows that both models perform well on important medical utterances and therefore can be practical for transcribing medical conversations.

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.

Sequence-to-sequence models with soft attention had significant success in machine translation, speech recognition, and question answering. Though capable and easy to use, they require that the entirety of the input sequence is available at the beginning of inference, an assumption that is not valid for instantaneous translation and speech recognition. To address this problem, we present a new method for solving sequence-to-sequence problems using hard online alignments instead of soft offline alignments. The online alignments model is able to start producing outputs without the need to first process the entire input sequence. A highly accurate online sequence-to-sequence model is useful because it can be used to build an accurate voice-based instantaneous translator. Our model uses hard binary stochastic decisions to select the timesteps at which outputs will be produced. The model is trained to produce these stochastic decisions using a standard policy gradient method. In our experiments, we show that this model achieves encouraging performance on TIMIT and Wall Street Journal (WSJ) speech recognition datasets.

Recent advances in scanning technology have enabled the widespread capture of 3D character models based on human subjects. However, in order to generate a recognizable 3D avatar, the movement and behavior of the human subject should be captured and replicated as well. We present a method of generating a 3D model from a scan, as well as a method to incorporate a subjects style of gesturing into a 3D character. We present a study which shows that 3D characters that used the gestural style as their original human subjects were more recognizable as the original subject than those that don't.

This paper presents a novel personal identification method by extracting unique object features from optical speckle patterns using the SIFT (Scale Invariant Feature Transform) algorithm. Accurate identification is achieved by developing an invariant speckle capturing device and recognition criteria. Experimental results show that optical speckle pattern of a given material is invariant after slight movement and the patterns captured from different areas of the same material are distinct. Therefore, this merit can be adopted for security applications by using the surface of specific object as the personal identification card and extracting speckle patterns from this surface to recognize the identity of certain subject.

High dimensionality of state representation is a major limitation for scale‐up in reinforcement learning (RL). This work derives the knowledge of complexity reduction from partial solutions and provides algorithms for automated dimension reduction in RL. We propose the cascading decomposition algorithm based on the spectral analysis on a normalized graph Laplacian to decompose a problem into several subproblems and then conduct parameter relevance analysis on each subproblem to perform dynamic state abstraction. The elimination of irrelevant parameters projects the original state space into the one with lower dimension in which some subtasks are projected onto the same shared subtasks. The framework could identify irrelevant parameters based on performed action sequences and thus relieve the problem of high dimensionality in learning process. We evaluate the framework with experiments and show that the dimension reduction approach could indeed make some infeasible problem to become learnable.

A video-based monitoring system must be capable of continuous operation under various weather and illumination conditions. Moreover, background subtraction is a very important part of surveillance applications for successful segmentation of objects from video sequences, and the accuracy, computational complexity, and memory requirements of the initial background extraction are crucial in any background subtraction method. This paper proposes an algorithm to extract initial color backgrounds from surveillance videos using a probability-based background extraction algorithm. With the proposed algorithm, the initial background can be extracted accurately and quickly, while using relatively little memory. The intrusive objects can then be segmented quickly and correctly by a robust object segmentation algorithm. The segmentation algorithm analyzes the threshold values of the background subtraction from the prior frame to obtain good quality while minimizing execution time and maximizing detection accuracy. The color background images can be extracted efficiently and quickly from color image sequences and updated in real time to overcome any variation in illumination conditions. Experimental results for various environmental sequences and a quantitative evaluation are provided to demonstrate the robustness, accuracy, effectiveness, and memory economy of the proposed algorithm.

This study uses two low-cost and compact CMOS cameras to construct an asynchronous binocular system and proposes an effective real-time front-vehicle detection algorithm with the binocular system. The proposed vehicle detection algorithm uses the edge information to detect the region of each front vehicle, and then computes the disparities of the front vehicles by an adaptive search method. According to the disparity values, the relative distances between the front and the host vehicles can be computed. The proposed algorithm of the manuscript conquers the asynchronous exposure problem and cost issue of a binocular system. Experimental results show that the proposed system can robustly and accurately detect obstacles or other vehicles in real time under different illumination and road conditions.

Adverse drug reaction (ADR) may cost a lot of unnecessary medical resources and leads to extra suffering on patients. To provide the prompt information about ADR and avoid the rate of occurrence of ADR is an important task yet to be done. The US Food and Drug Administration (FDA) provides a Adverse Event Reporting System (AERS) which contains a lot of clinical reports about ADRs. However, the biologists still do not know precisely which observed events are directly caused by drug-drug interactions. We use the probability analysis method to find the associations between a set of drugs and the symptoms for predicting the ADR and apply the decision tree to discovery the association rules between the drug-drug interactions and symptoms.

Text is commonly printed on a complex background. Segmenting text is an important part in document analysis. In the past some methods have been shown for the segmentation of texts with images. However, previous studies have not sufficiently addressed complex compound documents. This investigation presents an algorithm for the segmentation of text in various document images. The proposed segmentation algorithm applies a new multilayer segmentation method to separate the text from various compound document images, independent from the text and background overlapping or not. This method solves various problems associated with the complexity of background images. Experimental results obtained using various document images scanned from book covers, advertisements, brochures and magazines, reveal that the proposed algorithm can successfully segment Chinese and English text strings from various backgrounds, regardless of whether the texts are over a simple, slowly varying or rapidly varying background texture.