Direct speech-to-speech translation (S2ST), in which all components can be optimized jointly, is advantageous over cascaded approaches to achieve fast inference with a simplified pipeline. We present a novel two-pass direct S2ST architecture, UnitY, which first generates textual representations and predicts discrete acoustic units subsequently. We enhance the model performance by subword prediction in the first-pass decoder, advanced two-pass decoder architecture design and search strategy, and better training regularization. To leverage large amounts of unlabeled text data, we pre-train the first-pass text decoder based on the self-supervised denoising auto-encoding task. Experimental evaluations on benchmark datasets at various data scales demonstrate that UnitY outperforms a single-pass speech-to-unit translation model by 2.5-4.2 ASR-BLEU with 2.83x decoding speed-up. We show that the proposed methods boost the performance even when predicting spectrogram in the second pass. However, predicting discrete units achieves 2.51x decoding speed-up compared to that case.
End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a two-pass model has been proposed to rescore streamed hypotheses using the non-streaming Listen, Attend and Spell (LAS) model while maintaining a reasonable latency. The model attends to acoustics to rescore hypotheses, as opposed to a class of neural correction models that use only first-pass text hypotheses. In this work, we propose to attend to both acoustics and first-pass hypotheses using a deliberation network. …
Hybrid and end-to-end (E2E) systems have their individual advantages, with different error patterns in the speech recognition results. By jointly modeling audio and text, the E2E model performs better in matched scenarios and scales well with a large amount of paired audio-text training data. The modularized hybrid model is easier for customization, and better to make use of a massive amount of unpaired text data. This paper proposes a two-pass hybrid and E2E cascading (HEC) framework to combine the hybrid and E2E model in order to take advantage of both sides, with hybrid in the first pass an…
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 mod…
It is estimated that around 70 million people worldwide are affected by a speech disorder called stuttering. With recent advances in Automatic Speech Recognition (ASR), voice assistants are increasingly useful in our everyday lives. Many technologies in education, retail, telecommunication and healthcare can now be operated through voice. Unfortunately, these benefits are not accessible for People Who Stutter (PWS). We propose a simple but effective method called 'Detect and Pass' to make modern ASR systems accessible for People Who Stutter in a limited data setting. The algorithm uses a conte…
Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-pass streaming ASR model to improve recognition accuracy while keeping latency low. One of the latest 2nd-pass rescoring model, Transformer Rescorer, takes the n-best initial outputs and audio embeddings from the 1st-pass model, and then choose the best output by re-scoring the n-best initial outputs. However, training this Transformer Rescorer requires expensive paired audio-text training data because the model us…
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 origi…
In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the encoder are modified. We propose a dynamic chunk-based attention strategy to allow arbitrary right context length. At inference time, the CTC decoder generates n-best hypotheses in a streaming way. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final resu…
Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction
Nara Institute of Science and Technology (NAIST)（奈良科学技术研究所（NAIST））；National Institute of Information and Communications Technology (NICT)（信息通信研究机构（NICT））；NVIDIA Research（英伟达研究院）；Kyoto University（京都大学）
Mobvoi Inc.（出门问问公司）；WeNet Open Source Community（WeNet开源社区）
The unified streaming and non-streaming two-pass (U2) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy, real-time factor (RTF), and latency. In this paper, we present U2++, an enhanced version of U2 to further improve the accuracy. The core idea of U2++ is to use the forward and the backward information of the labeling sequences at the same time at training to learn richer information, and combine the forward and backward prediction at decoding to give more accurate recognition results. We also proposed a new data augmentation metho…
LSTM language models (LSTM-LMs) have been proven to be powerful and yielded significant performance improvements over count based n-gram LMs in modern speech recognition systems. Due to its infinite history states and computational load, most previous studies focus on applying LSTM-LMs in the second-pass for rescoring purpose. Recent work shows that it is feasible and computationally affordable to adopt the LSTM-LMs in the first-pass decoding within a dynamic (or tree based) decoder framework. In this work, the LSTM-LM is composed with a WFST decoder on-the-fly for the first-pass decoding. Fur…
Interactive speech recognition systems must generate words quickly while also producing accurate results. Two-pass models excel at these requirements by employing a first-pass decoder that quickly emits words, and a second-pass decoder that requires more context but is more accurate. Previous work has established that a deliberation network can be an effective second-pass model. The model attends to two kinds of inputs at once: encoded audio frames and the hypothesis text from the first-pass model. In this work, we explore using transformer layers instead of long-short term memory (LSTM) layer…
We present a method to perform first-pass large vocabulary continuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace in HMM-based speech recognition systems, but building such systems is a complex, domain-specific task. Recent work demonstrated the feasibility of discarding the HMM sequence modeling framework by directly predicting transcript text from audio. This paper extends this approach in two ways. First, we demonstrate that a straightforward recurrent neural network architecture can achieve a high level of accur…
This paper describes the winning approach in the Shared Task 3 at SwissText 2021 on Swiss German Speech to Standard German Text, a public competition on dialect recognition and translation. Swiss German refers to the multitude of Alemannic dialects spoken in the German-speaking parts of Switzerland. Swiss German differs significantly from standard German in pronunciation, word inventory and grammar. It is mostly incomprehensible to native German speakers. Moreover, it lacks a standardized written script. To solve the challenging task, we propose a hybrid automatic speech recognition system wit…
We propose speaker separation using speaker inventories and estimated speech (SSUSIES), a framework leveraging speaker profiles and estimated speech for speaker separation. SSUSIES contains two methods, speaker separation using speaker inventories (SSUSI) and speaker separation using estimated speech (SSUES). SSUSI performs speaker separation with the help of speaker inventory. By combining the advantages of permutation invariant training (PIT) and speech extraction, SSUSI significantly outperforms conventional approaches. SSUES is a widely applicable technique that can substantially improve s…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational requirements, due to the large number of possible segments to consider. Multi-pass cascades of segmental models introduce features of increasing complexity in different passes, where in each pass a segmental model rescores lattices produced by a previous (simpler) segmental model. In this paper, we explore several ways of making segmental cascades efficient and practical: reducing the feature set in the first pass, frame su…
This paper presents, in the context of multi-channel ASR, a method to adapt a mask based, statistically optimal beamforming approach to a speaker of interest. The beamforming vector of the statistically optimal beamformer is computed by utilizing speech and noise masks, which are estimated by a neural network. The proposed adaptation approach is based on the integration of the beamformer, which includes the mask estimation network, and the acoustic model of the ASR system. This allows for the propagation of the training error, from the acoustic modeling cost function, all the way through the b…
As voice assistants become more ubiquitous, they are increasingly expected to support and perform well on a wide variety of use-cases across different domains. We present a domain-aware rescoring framework suitable for achieving domain-adaptation during second-pass rescoring in production settings. In our framework, we fine-tune a domain-general neural language model on several domains, and use an LSTM-based domain classification model to select the appropriate domain-adapted model to use for second-pass rescoring. This domain-aware rescoring improves the word error rate by up to 2.4% and slot…
Northwestern Polytechnical University（西北工业大学）；Mobvoi Inc.（出门问问公司）；WeNet Open Source Community（WeNet开源社区）
In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. The main motivation of WeNet is to close the gap between the research and the production of E2E speechrecognition models. WeNet provides an efficient way to ship ASR applications in several real-world scenarios, which is the main difference and advantage to other open source E2E speech recognition toolkits. In our toolkit, a new two-pass…
Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of the cascaded-encoder-based recurrent neural network transducer (RNN-T) model by integrating a per-frame language identifier (LID) predictor. RNN-T with cascaded encoders can achieve streaming ASR with low latency using first-pass decoding with no right-context, and achieve lower word error rates (WERs) using second-pass decoding with longer right-context. B…
End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to adapt when mismatch exists between training and test data. In this work, we focus on contextual speech recognition, which is particularly challenging for E2E models because it introduces significant mismatch between training and test data. To improve the performance in the presence of complex contextual information, we propose to use class-based language mod…
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
University of Chinese Academy of Sciences（中国科学院大学）；School of Future Science and Engineering, Soochow University（苏州大学未来科学与工程学院）；Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室）
We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support humanitarian relief programmes in rural Africa. Using just 1.57 hours of annotated speech data as a seed corpus, we increase the pool of training data by applying semi-supervised training to 17.55 hours of untranscribed speech. We make use of factorised time-delay neural networks (TDNN-F) for acoustic modelling, since these have recently been shown to be effect…
We present a direct simultaneous speech-to-speech translation (Simul-S2ST) model, Furthermore, the generation of translation is independent from intermediate text representations. Our approach leverages recent progress on direct speech-to-speech translation with discrete units, in which a sequence of discrete representations, instead of continuous spectrogram features, learned in an unsupervised manner, are predicted from the model and passed directly to a vocoder for speech synthesis on-the-fly. We also introduce the variational monotonic multihead attention (V-MMA), to handle the challenge o…
End-to-end (E2E) models are becoming increasingly popular for spoken language understanding (SLU) systems and are beginning to achieve competitive performance to pipeline-based approaches. However, recent work has shown that these models struggle to generalize to new phrasings for the same intent indicating that models cannot understand the semantic content of the given utterance. In this work, we incorporated language models pre-trained on unlabeled text data inside E2E-SLU frameworks to build strong semantic representations. Incorporating both semantic and acoustic information can increase t…
Recently, attention-based encoder-decoder (AED) end-to-end (E2E) models have drawn more and more attention in the field of automatic speech recognition (ASR). AED models, however, still have drawbacks when deploying in commercial applications. Autoregressive beam search decoding makes it inefficient for high-concurrency applications. It is also inconvenient to integrate external word-level language models. The most important thing is that AED models are difficult for streaming recognition due to global attention mechanism. In this paper, we propose a novel framework, namely WNARS, using hybrid…
The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits of the non-streaming model in streaming applications like voice search, it is commonly used in second pass re-scoring mode. The candidate hypothesis generated using steaming models is re-scored using a non-streaming model. In this work, we evaluate the non-streaming attention-based end-to-end ASR models on the Flipkart voice search task in both standalone an…
Multilingual end-to-end automatic speech recognition models are attractive due to its simplicity in training and deployment. Recent work on large-scale training of such models has shown promising results compared to monolingual models. However, the work often focuses on multilingual models themselves in a single-pass setup. In this work, we investigate second-pass deliberation for multilingual speech recognition. Our proposed deliberation is multilingual, i.e., the text encoder encodes hypothesis text from multiple languages, and the decoder attends to multilingual text and audio. We investiga…
We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words or document-level features, we focus our study on the ability of LSTM and Transformer language models to implicitly learn to carry over context across sentence boundaries. We introduce a new architecture that incorporates an attention mechanism into LSTM to combine the benefits of recurrent and attention architectures. We conduct language modeling and speech recognition experiments on the publicly available LibriSpe…
VIT-AP University（VIT-AP大学）；Aalborg University（奥尔堡大学）；Massachusetts Institute of Technology（麻省理工学院）
There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker verification (TD-SV). However, a moderate success has been achieved. A recent study [1] presented a time contrastive learning (TCL) concept to explore the non-stationarity of brain signals for classification of brain states. Speech signals have similar non-stationarity property, and TCL further has the advantage of having no need for labeled data. We therefore present…
The recognition of personalized content, such as contact names, remains a challenging problem for end-to-end speech recognition systems. In this work, we demonstrate how first and second-pass rescoring strategies can be leveraged together to improve the recognition of such words. Following previous work, we use a shallow fusion approach to bias towards recognition of personalized content in the first-pass decoding. We show that such an approach can improve personalized content recognition by up to 16% with minimum degradation on the general use case. We describe a fast and scalable algorithm t…
We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language understanding (NLU) component generates the semantic parse by conditioning on both ASR's text and audio embeddings. By formulating E2E SLU as a generalized decoder, our system is able to support complex compositional semantic structures. Furthermore, the sharing of parameters between ASR and NLU makes the system especially suitable for resource-constrained (on-devi…
This paper presented our work on applying Recurrent Deep Stacking Networks (RDSNs) to Robust Automatic Speech Recognition (ASR) tasks. In the paper, we also proposed a more efficient yet comparable substitute to RDSN, Bi- Pass Stacking Network (BPSN). The main idea of these two models is to add phoneme-level information into acoustic models, transforming an acoustic model to the combination of an acoustic model and a phoneme-level N-gram model. Experiments showed that RDSN and BPsn can substantially improve the performances over conventional DNNs.
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applications. To address this issue, we propose a non-autoregressive end-to-end speech recognition system called LASO (listen attentively, and spell once). Because of the non-autoregressive property, LASO predicts a textual token in the sequence without the dependence on other tokens. Without beam-search, the one-pass propagation much reduces inference time cost of LASO. And because th…
Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model. To further improve ASR performance and facilitate various production requirements, in this paper, we present WeNet 2.0 with four important updates. (1) We propose U2++, a unified two-pass framework with bidirectional attention decoders, which includes the future contextual information by a right-to-left attention decoder to improve the representative …
Taiyuan University of Science and Technology（太原科技大学）；University of Surrey（萨里大学）
In a recent study of auditory evoked potential (AEP) based brain-computer interface (BCI), it was shown that, with an encoder-decoder framework, it is possible to translate human neural activity to speech (T-CAS). However, current encoder-decoder-based methods achieve T-CAS often with a two-step method where the information is passed between the encoder and decoder with a shared dimension reduction vector, which may result in a loss of information. A potential approach to this problem is to design an end-to-end method by using a dual generative adversarial network (DualGAN) without dimension r…
Toyota Technological Institute at Chicago（芝加哥丰田理工学院）；Google Inc.（谷歌公司）
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…
Direct speech-to-speech translation (S2ST) with discrete units leverages recent progress in speech representation learning. Specifically, a sequence of discrete representations derived in a self-supervised manner are predicted from the model and passed to a vocoder for speech reconstruction, while still facing the following challenges: 1) Acoustic multimodality: the discrete units derived from speech with same content could be indeterministic due to the acoustic property (e.g., rhythm, pitch, and energy), which causes deterioration of translation accuracy; 2) high latency: current S2ST systems…
End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the performance on rare content words often lags behind hybrid ASR systems. To address this problem, second-pass rescoring is often applied leveraging upon language modeling. In this paper, we propose a second-pass system with multi-task learning, utilizing semantic targets (such as intent and slot prediction) to improve speech recognition performance. We show that our r…
Carnegie Mellon University（卡内基梅隆大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Edinburgh（爱丁堡大学）；Indian Institute of Technology Bombay（印度理工学院孟买分校）
In this work, we seek to build effective code-switched (CS) automatic speech recognition systems (ASR) under the zero-shot setting where no transcribed CS speech data is available for training. Previously proposed frameworks which conditionally factorize the bilingual task into its constituent monolingual parts are a promising starting point for leveraging monolingual data efficiently. However, these methods require the monolingual modules to perform language segmentation. That is, each monolingual module has to simultaneously detect CS points and transcribe speech segments of one language whi…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；University of British Columbia（不列颠哥伦比亚大学）；Indiana University Bloomington（印第安纳大学伯明顿分校）；Newcastle University（纽卡斯尔大学）；Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）
Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic representations for spoken utterances. Through converting speech signals into hidden units generated from acoustic unit discovery, we propose WavEmbed, a multimodal sequential autoencoder that predicts hidden units from a dense representation of speech. Secondly, we also propose S-HuBERT to induce meaning through knowledge distillation, in which a sentence embeddi…
A new language model for speech recognition is presented. The model develops hidden hierarchical syntactic-like structure incrementally and uses it to extract meaningful information from the word history, thus complementing the locality of currently used trigram models. The structured language model (SLM) and its performance in a two-pass speech recognizer --- lattice decoding --- are presented. Experiments on the WSJ corpus show an improvement in both perplexity (PPL) and word error rate (WER) over conventional trigram models.
Second-pass rescoring is an important component in automatic speech recognition (ASR) systems that is used to improve the outputs from a first-pass decoder by implementing a lattice rescoring or $n$-best re-ranking. While pretraining with a masked language model (MLM) objective has received great success in various natural language understanding (NLU) tasks, it has not gained traction as a rescoring model for ASR. Specifically, training a bidirectional model like BERT on a discriminative objective such as minimum WER (MWER) has not been explored. Here we show how to train a BERT-based rescorin…
A Pascal challenge entitled monaural multi-talker speech recognition was developed, targeting the problem of robust automatic speech recognition against speech like noises which significantly degrades the performance of automatic speech recognition systems. In this challenge, two competing speakers say a simple command simultaneously and the objective is to recognize speech of the target speaker. Surprisingly during the challenge, a team from IBM research, could achieve a performance better than human listeners on this task. The proposed method of the IBM team, consist of an intermediate speec…
Most current very low bit rate (VLBR) speech coding systems use hidden Markov model (HMM) based speech recognition/synthesis techniques. This allows transmission of information (such as phonemes) segment by segment that decreases the bit rate. However, the encoder based on a phoneme speech recognition may create bursts of segmental errors. Segmental errors are further propagated to optional suprasegmental (such as syllable) information coding. Together with the errors of voicing detection in pitch parametrization, HMM-based speech coding creates speech discontinuities and unnatural speech soun…
Microsoft Speech and Language Group（微软语音与语言组）；Microsoft Research Asia（微软亚洲研究院）
Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is a key issue to prevent their applications. In this work, we explored the potential of Transformer Transducer (T-T) models for the fist pass decoding with low latency and fast speed on a large-scale dataset. We combine the idea of Transformer-XL and chunk-wise streaming processing to design a streamable Transformer Transducer model. We demonstrate that T-T outperforms the hybrid…
A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers from error propagation between ASR and MT models. Direct speech translation is an alternative method to avoid error propagation; however, its performance is often behind the cascade system. To use an intermediate representation and preserve the end-to-end trainability, previous studies have proposed using two-stage models by passing the hidden vectors of the…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；SpeechTex Ltd.（SpeechTex有限公司）；THINKTech Research Center（THINKTech研究中心）
Advanced neural network models have penetrated Automatic Speech Recognition (ASR) in recent years, however, in language modeling many systems still rely on traditional Back-off N-gram Language Models (BNLM) partly or entirely. The reason for this are the high cost and complexity of training and using neural language models, mostly possible by adding a second decoding pass (rescoring). In our recent work we have significantly improved the online performance of a conversational speech transcription system by transferring knowledge from a Recurrent Neural Network Language Model (RNNLM) to the sin…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Carnegie Mellon University（卡内基梅隆大学）
Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have shown the feasibility of collapsing the cascade into a single, direct model that can be trained in an end-to-end fashion on a corpus of translated speech. However, experiments are inconclusive on whether the cascade or the direct model is stronger, and have only been conducted under the unrealistic assumption that both are trained on equal amounts of data, i…
