Takaaki Hori

Rohit Prabhavalkar, Takaaki Hori, Tara N. Sainath et al.

In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning. In the wake of this transition, a number of all-neural ASR architectures were introduced. These so-called end-to-end (E2E) models provide highly integrated, completely neural ASR models, which rely strongly on general machine learning knowledge, learn more consistently from data, while depending less on ASR domain-specific experience. The success and enthusiastic adoption of deep learning accompanied by more generic model architectures lead to E2E models now becoming the prominent ASR approach. The goal of this survey is to provide a taxonomy of E2E ASR models and corresponding improvements, and to discuss their properties and their relation to the classical hidden Markov model (HMM) based ASR architecture. All relevant aspects of E2E ASR are covered in this work: modeling, training, decoding, and external language model integration, accompanied by discussions of performance and deployment opportunities, as well as an outlook into potential future developments.

Xuankai Chang, Niko Moritz, Takaaki Hori et al.

Graph-based temporal classification (GTC), a generalized form of the connectionist temporal classification loss, was recently proposed to improve automatic speech recognition (ASR) systems using graph-based supervision. For example, GTC was first used to encode an N-best list of pseudo-label sequences into a graph for semi-supervised learning. In this paper, we propose an extension of GTC to model the posteriors of both labels and label transitions by a neural network, which can be applied to a wider range of tasks. As an example application, we use the extended GTC (GTC-e) for the multi-speaker speech recognition task. The transcriptions and speaker information of multi-speaker speech are represented by a graph, where the speaker information is associated with the transitions and ASR outputs with the nodes. Using GTC-e, multi-speaker ASR modelling becomes very similar to single-speaker ASR modeling, in that tokens by multiple speakers are recognized as a single merged sequence in chronological order. For evaluation, we perform experiments on a simulated multi-speaker speech dataset derived from LibriSpeech, obtaining promising results with performance close to classical benchmarks for the task.

Pawel Swietojanski, Stefan Braun, Dogan Can et al.

This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios. We present a comprehensive set of experiments comparing fixed masking, where the same attention mask is applied at every frame, with chunked masking, where the attention mask for each frame is determined by chunk boundaries, in terms of recognition accuracy and latency. We then explore the use of variable masking, where the attention masks are sampled from a target distribution at training time, to build models that can work in different configurations. Finally, we investigate how a single configurable model can be used to perform both first pass streaming recognition and second pass acoustic rescoring. Experiments show that chunked masking achieves a better accuracy vs latency trade-off compared to fixed masking, both with and without FastEmit. We also show that variable masking improves the accuracy by up to 8% relative in the acoustic re-scoring scenario.

Pawel Swietojanski, Xinwei Li, Mingbin Xu et al.

We address the fundamental incompatibility of attention-based encoder-decoder (AED) models with long-form acoustic encodings. AED models trained on segmented utterances learn to encode absolute frame positions by exploiting limited acoustic context beyond segment boundaries, but fail to generalize when decoding long-form segments where these cues vanish. The model loses ability to order acoustic encodings due to permutation invariance of keys and values in cross-attention. We propose four modifications: (1) injecting explicit absolute positional encodings into cross-attention for each decoded segment, (2) long-form training with extended acoustic context to eliminate implicit absolute position encoding, (3) segment concatenation to cover diverse segmentations needed during training, and (4) semantic segmentation to align AED-decoded segments with training segments. We show these modifications close the accuracy gap between continuous and segmented acoustic encodings, enabling auto-regressive use of the attention decoder.

Shinji Watanabe, Florian Boyer, Xuankai Chang et al.

This paper describes the recent development of ESPnet (https://github.com/espnet/espnet), an end-to-end speech processing toolkit. This project was initiated in December 2017 to mainly deal with end-to-end speech recognition experiments based on sequence-to-sequence modeling. The project has grown rapidly and now covers a wide range of speech processing applications. Now ESPnet also includes text to speech (TTS), voice conversation (VC), speech translation (ST), and speech enhancement (SE) with support for beamforming, speech separation, denoising, and dereverberation. All applications are trained in an end-to-end manner, thanks to the generic sequence to sequence modeling properties, and they can be further integrated and jointly optimized. Also, ESPnet provides reproducible all-in-one recipes for these applications with state-of-the-art performance in various benchmarks by incorporating transformer, advanced data augmentation, and conformer. This project aims to provide up-to-date speech processing experience to the community so that researchers in academia and various industry scales can develop their technologies collaboratively.

Shigeki Karita, Nanxin Chen, Tomoki Hayashi et al.

Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence model called Transformer, which achieves state-of-the-art performance in neural machine translation and other natural language processing applications. We undertook intensive studies in which we experimentally compared and analyzed Transformer and conventional recurrent neural networks (RNN) in a total of 15 ASR, one multilingual ASR, one ST, and two TTS benchmarks. Our experiments revealed various training tips and significant performance benefits obtained with Transformer for each task including the surprising superiority of Transformer in 13/15 ASR benchmarks in comparison with RNN. We are preparing to release Kaldi-style reproducible recipes using open source and publicly available datasets for all the ASR, ST, and TTS tasks for the community to succeed our exciting outcomes.

Shinji Watanabe, Takaaki Hori, Shigeki Karita et al.

This paper introduces a new open source platform for end-to-end speech processing named ESPnet. ESPnet mainly focuses on end-to-end automatic speech recognition (ASR), and adopts widely-used dynamic neural network toolkits, Chainer and PyTorch, as a main deep learning engine. ESPnet also follows the Kaldi ASR toolkit style for data processing, feature extraction/format, and recipes to provide a complete setup for speech recognition and other speech processing experiments. This paper explains a major architecture of this software platform, several important functionalities, which differentiate ESPnet from other open source ASR toolkits, and experimental results with major ASR benchmarks.

Takaaki Hori, Martin Kocour, Adnan Haider et al.

This paper presents an efficient decoding approach for end-to-end automatic speech recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the most common approach to incorporate language models into E2E-ASR decoding, we face two practical problems with LLMs. (1) LLM inference is computationally costly. (2) There may be a vocabulary mismatch between the ASR model and the LLM. To resolve this mismatch, we need to retrain the ASR model and/or the LLM, which is at best time-consuming and in many cases not feasible. We propose "delayed fusion," which applies LLM scores to ASR hypotheses with a delay during decoding and enables easier use of pre-trained LLMs in ASR tasks. This method can reduce not only the number of hypotheses scored by the LLM but also the number of LLM inference calls. It also allows re-tokenizion of ASR hypotheses during decoding if ASR and LLM employ different tokenizations. We demonstrate that delayed fusion provides improved decoding speed and accuracy compared to shallow fusion and N-best rescoring using the LibriHeavy ASR corpus and three public LLMs, OpenLLaMA 3B & 7B and Mistral 7B.

Nikolaos Flemotomos, Roger Hsiao, Pawel Swietojanski et al.

Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription accuracy. However, the biasing mechanism is typically based on a cross-attention module between the audio and a catalogue of biasing entries, which means computational complexity can pose severe practical limitations on the size of the biasing catalogue and consequently on accuracy improvements. This work proposes an approximation to cross-attention scoring based on vector quantization and enables compute- and memory-efficient use of large biasing catalogues. We propose to use this technique jointly with a retrieval based contextual biasing approach. First, we use an efficient quantized retrieval module to shortlist biasing entries by grounding them on audio. Then we use retrieved entries for biasing. Since the proposed approach is agnostic to the biasing method, we investigate using full cross-attention, LLM prompting, and a combination of the two. We show that retrieval based shortlisting allows the system to efficiently leverage biasing catalogues of several thousands of entries, resulting in up to 71% relative error rate reduction in personal entity recognition. At the same time, the proposed approximation algorithm reduces compute time by 20% and memory usage by 85-95%, for lists of up to one million entries, when compared to standard dot-product cross-attention.

Niko Moritz, Takaaki Hori, Shinji Watanabe et al.

The recurrent neural network transducer (RNN-T) objective plays a major role in building today's best automatic speech recognition (ASR) systems for production. Similarly to the connectionist temporal classification (CTC) objective, the RNN-T loss uses specific rules that define how a set of alignments is generated to form a lattice for the full-sum training. However, it is yet largely unknown if these rules are optimal and do lead to the best possible ASR results. In this work, we present a new transducer objective function that generalizes the RNN-T loss to accept a graph representation of the labels, thus providing a flexible and efficient framework to manipulate training lattices, e.g., for studying different transition rules, implementing different transducer losses, or restricting alignments. We demonstrate that transducer-based ASR with CTC-like lattice achieves better results compared to standard RNN-T, while also ensuring a strictly monotonic alignment, which will allow better optimization of the decoding procedure. For example, the proposed CTC-like transducer achieves an improvement of 4.8% on the test-other condition of LibriSpeech relative to an equivalent RNN-T based system.

Ankit P. Shah, Shijie Geng, Peng Gao et al.

In previous work, we have proposed the Audio-Visual Scene-Aware Dialog (AVSD) task, collected an AVSD dataset, developed AVSD technologies, and hosted an AVSD challenge track at both the 7th and 8th Dialog System Technology Challenges (DSTC7, DSTC8). In these challenges, the best-performing systems relied heavily on human-generated descriptions of the video content, which were available in the datasets but would be unavailable in real-world applications. To promote further advancements for real-world applications, we proposed a third AVSD challenge, at DSTC10, with two modifications: 1) the human-created description is unavailable at inference time, and 2) systems must demonstrate temporal reasoning by finding evidence from the video to support each answer. This paper introduces the new task that includes temporal reasoning and our new extension of the AVSD dataset for DSTC10, for which we collected human-generated temporal reasoning data. We also introduce a baseline system built using an AV-transformer, which we released along with the new dataset. Finally, this paper introduces a new system that extends our baseline system with attentional multimodal fusion, joint student-teacher learning (JSTL), and model combination techniques, achieving state-of-the-art performances on the AVSD datasets for DSTC7, DSTC8, and DSTC10. We also propose two temporal reasoning methods for AVSD: one attention-based, and one based on a time-domain region proposal network.

Yosuke Higuchi, Niko Moritz, Jonathan Le Roux et al.

Pseudo-labeling (PL), a semi-supervised learning (SSL) method where a seed model performs self-training using pseudo-labels generated from untranscribed speech, has been shown to enhance the performance of end-to-end automatic speech recognition (ASR). Our prior work proposed momentum pseudo-labeling (MPL), which performs PL-based SSL via an interaction between online and offline models, inspired by the mean teacher framework. MPL achieves remarkable results on various semi-supervised settings, showing robustness to variations in the amount of data and domain mismatch severity. However, there is further room for improving the seed model used to initialize the MPL training, as it is in general critical for a PL-based method to start training from high-quality pseudo-labels. To this end, we propose to enhance MPL by (1) introducing the Conformer architecture to boost the overall recognition accuracy and (2) exploiting iterative pseudo-labeling with a language model to improve the seed model before applying MPL. The experimental results demonstrate that the proposed approaches effectively improve MPL performance, outperforming other PL-based methods. We also present in-depth investigations to make our improvements effective, e.g., with regard to batch normalization typically used in Conformer and LM quality.

Chiori Hori, Takaaki Hori, Jonathan Le Roux

Video captioning is an essential technology to understand scenes and describe events in natural language. To apply it to real-time monitoring, a system needs not only to describe events accurately but also to produce the captions as soon as possible. Low-latency captioning is needed to realize such functionality, but this research area for online video captioning has not been pursued yet. This paper proposes a novel approach to optimize each caption's output timing based on a trade-off between latency and caption quality. An audio-visual Trans-former is trained to generate ground-truth captions using only a small portion of all video frames, and to mimic outputs of a pre-trained Transformer to which all the frames are given. A CNN-based timing detector is also trained to detect a proper output timing, where the captions generated by the two Trans-formers become sufficiently close to each other. With the jointly trained Transformer and timing detector, a caption can be generated in the early stages of an event-triggered video clip, as soon as an event happens or when it can be forecasted. Experiments with the ActivityNet Captions dataset show that our approach achieves 94% of the caption quality of the upper bound given by the pre-trained Transformer using the entire video clips, using only 28% of frames from the beginning.

Niko Moritz, Takaaki Hori, Jonathan Le Roux

Attention-based end-to-end automatic speech recognition (ASR) systems have recently demonstrated state-of-the-art results for numerous tasks. However, the application of self-attention and attention-based encoder-decoder models remains challenging for streaming ASR, where each word must be recognized shortly after it was spoken. In this work, we present the dual causal/non-causal self-attention (DCN) architecture, which in contrast to restricted self-attention prevents the overall context to grow beyond the look-ahead of a single layer when used in a deep architecture. DCN is compared to chunk-based and restricted self-attention using streaming transformer and conformer architectures, showing improved ASR performance over restricted self-attention and competitive ASR results compared to chunk-based self-attention, while providing the advantage of frame-synchronous processing. Combined with triggered attention, the proposed streaming end-to-end ASR systems obtained state-of-the-art results on the LibriSpeech, HKUST, and Switchboard ASR tasks.

Yosuke Higuchi, Niko Moritz, Jonathan Le Roux et al.

Pseudo-labeling (PL) has been shown to be effective in semi-supervised automatic speech recognition (ASR), where a base model is self-trained with pseudo-labels generated from unlabeled data. While PL can be further improved by iteratively updating pseudo-labels as the model evolves, most of the previous approaches involve inefficient retraining of the model or intricate control of the label update. We present momentum pseudo-labeling (MPL), a simple yet effective strategy for semi-supervised ASR. MPL consists of a pair of online and offline models that interact and learn from each other, inspired by the mean teacher method. The online model is trained to predict pseudo-labels generated on the fly by the offline model. The offline model maintains a momentum-based moving average of the online model. MPL is performed in a single training process and the interaction between the two models effectively helps them reinforce each other to improve the ASR performance. We apply MPL to an end-to-end ASR model based on the connectionist temporal classification. The experimental results demonstrate that MPL effectively improves over the base model and is scalable to different semi-supervised scenarios with varying amounts of data or domain mismatch.

Takaaki Hori, Niko Moritz, Chiori Hori et al.

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual information (e.g., speaker or topic) over multiple utterances is known to be useful for ASR. In our prior work, we proposed a context-expanded Transformer that accepts multiple consecutive utterances at the same time and predicts an output sequence for the last utterance, achieving 5-15% relative error reduction from utterance-based baselines in lecture and conversational ASR benchmarks. Although the results have shown remarkable performance gain, there is still potential to further improve the model architecture and the decoding process. In this paper, we extend our prior work by (1) introducing the Conformer architecture to further improve the accuracy, (2) accelerating the decoding process with a novel activation recycling technique, and (3) enabling streaming decoding with triggered attention. We demonstrate that the extended Transformer provides state-of-the-art end-to-end ASR performance, obtaining a 17.3% character error rate for the HKUST dataset and 12.0%/6.3% word error rates for the Switchboard-300 Eval2000 CallHome/Switchboard test sets. The new decoding method reduces decoding time by more than 50% and further enables streaming ASR with limited accuracy degradation.

Niko Moritz, Takaaki Hori, Jonathan Le Roux

Self-attention has become an important and widely used neural network component that helped to establish new state-of-the-art results for various applications, such as machine translation and automatic speech recognition (ASR). However, the computational complexity of self-attention grows quadratically with the input sequence length. This can be particularly problematic for applications such as ASR, where an input sequence generated from an utterance can be relatively long. In this work, we propose a combination of restricted self-attention and a dilation mechanism, which we refer to as dilated self-attention. The restricted self-attention allows attention to neighboring frames of the query at a high resolution, and the dilation mechanism summarizes distant information to allow attending to it with a lower resolution. Different methods for summarizing distant frames are studied, such as subsampling, mean-pooling, and attention-based pooling. ASR results demonstrate substantial improvements compared to restricted self-attention alone, achieving similar results compared to full-sequence based self-attention with a fraction of the computational costs.

Sameer Khurana, Niko Moritz, Takaaki Hori et al.

The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based pseudo-label filtering approach can be effectively used for domain adaptation. We propose DUST, a dropout-based uncertainty-driven self-training technique which uses agreement between multiple predictions of an ASR system obtained for different dropout settings to measure the model's uncertainty about its prediction. DUST excludes pseudo-labeled data with high uncertainties from the training, which leads to substantially improved ASR results compared to ST without filtering, and accelerates the training time due to a reduced training data set. Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD as the target domains show that up to 80% of the performance of a system trained on ground-truth data can be recovered.

Niko Moritz, Takaaki Hori, Jonathan Le Roux

Semi-supervised learning has demonstrated promising results in automatic speech recognition (ASR) by self-training using a seed ASR model with pseudo-labels generated for unlabeled data. The effectiveness of this approach largely relies on the pseudo-label accuracy, for which typically only the 1-best ASR hypothesis is used. However, alternative ASR hypotheses of an N-best list can provide more accurate labels for an unlabeled speech utterance and also reflect uncertainties of the seed ASR model. In this paper, we propose a generalized form of the connectionist temporal classification (CTC) objective that accepts a graph representation of the training labels. The newly proposed graph-based temporal classification (GTC) objective is applied for self-training with WFST-based supervision, which is generated from an N-best list of pseudo-labels. In this setup, GTC is used to learn not only a temporal alignment, similarly to CTC, but also a label alignment to obtain the optimal pseudo-label sequence from the weighted graph. Results show that this approach can effectively exploit an N-best list of pseudo-labels with associated scores, considerably outperforming standard pseudo-labeling, with ASR results approaching an oracle experiment in which the best hypotheses of the N-best lists are selected manually.

Peng Gao, Chiori Hori, Shijie Geng et al.

In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of later layers. To maintain a directed acyclic graph structure, the encoder stack of a transformer is repeated along a new multi-pass dimension, keeping the parameters tied, and information is allowed to proceed unidirectionally both towards deeper layers within an encoder stack and towards any layer of subsequent stacks. We consider both soft (i.e., continuous) and hard (i.e., discrete) connections between parallel encoder stacks, relying on a neural architecture search to find the best connection pattern in the hard case. We perform an extensive ablation study of the proposed MPT architecture and compare it with other state-of-the-art transformer architectures. Surprisingly, Base Transformer equipped with MPT can surpass the performance of Large Transformer on the challenging machine translation En-De and En-Fr datasets. In the hard connection case, the optimal connection pattern found for En-De also leads to improved performance for En-Fr.

Leda Sarı, Niko Moritz, Takaaki Hori et al.

We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR). The proposed model contains a memory block that holds speaker i-vectors extracted from the training data and reads relevant i-vectors from the memory through an attention mechanism. The resulting memory vector (M-vector) is concatenated to the acoustic features or to the hidden layer activations of an E2E neural network model. The E2E ASR system is based on the joint connectionist temporal classification and attention-based encoder-decoder architecture. M-vector and i-vector results are compared for inserting them at different layers of the encoder neural network using the WSJ and TED-LIUM2 ASR benchmarks. We show that M-vectors, which do not require an auxiliary speaker embedding extraction system at test time, achieve similar word error rates (WERs) compared to i-vectors for single speaker utterances and significantly lower WERs for utterances in which there are speaker changes.

Niko Moritz, Takaaki Hori, Jonathan Le Roux

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context information, has been shown to achieve significantly lower word error rates (WERs) compared to recurrent neural network (RNN) based system architectures. Despite its success, the practical usage is limited to offline ASR tasks, since encoder-decoder architectures typically require an entire speech utterance as input. In this work, we propose a transformer based end-to-end ASR system for streaming ASR, where an output must be generated shortly after each spoken word. To achieve this, we apply time-restricted self-attention for the encoder and triggered attention for the encoder-decoder attention mechanism. Our proposed streaming transformer architecture achieves 2.8% and 7.2% WER for the "clean" and "other" test data of LibriSpeech, which to our knowledge is the best published streaming end-to-end ASR result for this task.

Ruizhi Li, Xiaofei Wang, Sri Harish Mallidi et al.

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing both architectures during multi-task training and joint decoding. In this work, we present a multi-stream framework based on joint CTC/Attention E2E ASR with parallel streams represented by separate encoders aiming to capture diverse information. On top of the regular attention networks, the Hierarchical Attention Network (HAN) is introduced to steer the decoder toward the most informative encoders. A separate CTC network is assigned to each stream to force monotonic alignments. Two representative framework have been proposed and discussed, which are Multi-Encoder Multi-Resolution (MEM-Res) framework and Multi-Encoder Multi-Array (MEM-Array) framework, respectively. In MEM-Res framework, two heterogeneous encoders with different architectures, temporal resolutions and separate CTC networks work in parallel to extract complimentary information from same acoustics. Experiments are conducted on Wall Street Journal (WSJ) and CHiME-4, resulting in relative Word Error Rate (WER) reduction of 18.0-32.1% and the best WER of 3.6% in the WSJ eval92 test set. The MEM-Array framework aims at improving the far-field ASR robustness using multiple microphone arrays which are activated by separate encoders. Compared with the best single-array results, the proposed framework has achieved relative WER reduction of 3.7% and 9.7% in AMI and DIRHA multi-array corpora, respectively, which also outperforms conventional fusion strategies.

Murali Karthick Baskar, Shinji Watanabe, Ramon Astudillo et al.

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such models. This work builds upon recent results showing notable improvements in semi-supervised training using cycle-consistency and related techniques. Such techniques derive training procedures and losses able to leverage unpaired speech and/or text data by combining ASR with Text-to-Speech (TTS) models. In particular, this work proposes a new semi-supervised loss combining an end-to-end differentiable ASR$\rightarrow$TTS loss with TTS$\rightarrow$ASR loss. The method is able to leverage both unpaired speech and text data to outperform recently proposed related techniques in terms of \%WER. We provide extensive results analyzing the impact of data quantity and speech and text modalities and show consistent gains across WSJ and Librispeech corpora. Our code is provided in ESPnet to reproduce the experiments.

Xiaofei Wang, Ruizhi Li, Sri Harish Mallid et al.

Automatic Speech Recognition (ASR) using multiple microphone arrays has achieved great success in the far-field robustness. Taking advantage of all the information that each array shares and contributes is crucial in this task. Motivated by the advances of joint Connectionist Temporal Classification (CTC)/attention mechanism in the End-to-End (E2E) ASR, a stream attention-based multi-array framework is proposed in this work. Microphone arrays, acting as information streams, are activated by separate encoders and decoded under the instruction of both CTC and attention networks. In terms of attention, a hierarchical structure is adopted. On top of the regular attention networks, stream attention is introduced to steer the decoder toward the most informative encoders. Experiments have been conducted on AMI and DIRHA multi-array corpora using the encoder-decoder architecture. Compared with the best single-array results, the proposed framework has achieved relative Word Error Rates (WERs) reduction of 3.7% and 9.7% in the two datasets, respectively, which is better than conventional strategies as well.

Ruizhi Li, Xiaofei Wang, Sri Harish Mallidi et al.

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing both architectures during multi-task training and joint decoding. In this work, we present a novel Multi-Encoder Multi-Resolution (MEMR) framework based on the joint CTC/Attention model. Two heterogeneous encoders with different architectures, temporal resolutions and separate CTC networks work in parallel to extract complimentary acoustic information. A hierarchical attention mechanism is then used to combine the encoder-level information. To demonstrate the effectiveness of the proposed model, experiments are conducted on Wall Street Journal (WSJ) and CHiME-4, resulting in relative Word Error Rate (WER) reduction of 18.0-32.1%. Moreover, the proposed MEMR model achieves 3.6% WER in the WSJ eval92 test set, which is the best WER reported for an end-to-end system on this benchmark.

Hiroshi Seki, Takaaki Hori, Shinji Watanabe

Attention-based encoder decoder network uses a left-to-right beam search algorithm in the inference step. The current beam search expands hypotheses and traverses the expanded hypotheses at the next time step. This traversal is implemented using a for-loop program in general, and it leads to speed down of the recognition process. In this paper, we propose a parallelism technique for beam search, which accelerates the search process by vectorizing multiple hypotheses to eliminate the for-loop program. We also propose a technique to batch multiple speech utterances for off-line recognition use, which reduces the for-loop program with regard to the traverse of multiple utterances. This extension is not trivial during beam search unlike during training due to several pruning and thresholding techniques for efficient decoding. In addition, our method can combine scores of external modules, RNNLM and CTC, in a batch as shallow fusion. We achieved 3.7 x speedup compared with the original beam search algorithm by vectoring hypotheses, and achieved 10.5 x speedup by further changing processing unit to GPU.

Martin Karafiát, Murali Karthick Baskar, Shinji Watanabe et al.

This paper investigates the applications of various multilingual approaches developed in conventional hidden Markov model (HMM) systems to sequence-to-sequence (seq2seq) automatic speech recognition (ASR). On a set composed of Babel data, we first show the effectiveness of multi-lingual training with stacked bottle-neck (SBN) features. Then we explore various architectures and training strategies of multi-lingual seq2seq models based on CTC-attention networks including combinations of output layer, CTC and/or attention component re-training. We also investigate the effectiveness of language-transfer learning in a very low resource scenario when the target language is not included in the original multi-lingual training data. Interestingly, we found multilingual features superior to multilingual models, and this finding suggests that we can efficiently combine the benefits of the HMM system with the seq2seq system through these multilingual feature techniques.

Murali Karthick Baskar, Lukáš Burget, Shinji Watanabe et al.

In this paper, we present promising accurate prefix boosting (PAPB), a discriminative training technique for attention based sequence-to-sequence (seq2seq) ASR. PAPB is devised to unify the training and testing scheme in an effective manner. The training procedure involves maximizing the score of each partial correct sequence obtained during beam search compared to other hypotheses. The training objective also includes minimization of token (character) error rate. PAPB shows its efficacy by achieving 10.8\% and 3.8\% WER with and without RNNLM respectively on Wall Street Journal dataset.

Nelson Yalta, Shinji Watanabe, Takaaki Hori et al.

Casual conversations involving multiple speakers and noises from surrounding devices are common in everyday environments, which degrades the performances of automatic speech recognition systems. These challenging characteristics of environments are the target of the CHiME-5 challenge. By employing a convolutional neural network (CNN)-based multichannel end-to-end speech recognition system, this study attempts to overcome the presents difficulties in everyday environments. The system comprises of an attention-based encoder-decoder neural network that directly generates a text as an output from a sound input. The multichannel CNN encoder, which uses residual connections and batch renormalization, is trained with augmented data, including white noise injection. The experimental results show that the word error rate is reduced by 8.5% and 0.6% absolute from a single channel end-to-end and the best baseline (LF-MMI TDNN) on the CHiME-5 corpus, respectively.

Jaejin Cho, Shinji Watanabe, Takaaki Hori et al.

In this paper, we explore several new schemes to train a seq2seq model to integrate a pre-trained LM. Our proposed fusion methods focus on the memory cell state and the hidden state in the seq2seq decoder long short-term memory (LSTM), and the memory cell state is updated by the LM unlike the prior studies. This means the memory retained by the main seq2seq would be adjusted by the external LM. These fusion methods have several variants depending on the architecture of this memory cell update and the use of memory cell and hidden states which directly affects the final label inference. We performed the experiments to show the effectiveness of the proposed methods in a mono-lingual ASR setup on the Librispeech corpus and in a transfer learning setup from a multilingual ASR (MLASR) base model to a low-resourced language. In Librispeech, our best model improved WER by 3.7%, 2.4% for test clean, test other relatively to the shallow fusion baseline, with multi-level decoding. In transfer learning from an MLASR base model to the IARPA Babel Swahili model, the best scheme improved the transferred model on eval set by 9.9%, 9.8% in CER, WER relatively to the 2-stage transfer baseline.

Takaaki Hori, Ramon Astudillo, Tomoki Hayashi et al.

This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR systems, it still requires a large amount of paired data, i.e., speech utterances and their transcriptions. Cycle-consistency losses have been recently proposed as a way to mitigate the problem of limited paired data. These approaches compose a reverse operation with a given transformation, e.g., text-to-speech (TTS) with ASR, to build a loss that only requires unsupervised data, speech in this example. Applying cycle consistency to ASR models is not trivial since fundamental information, such as speaker traits, are lost in the intermediate text bottleneck. To solve this problem, this work presents a loss that is based on the speech encoder state sequence instead of the raw speech signal. This is achieved by training a Text-To-Encoder model and defining a loss based on the encoder reconstruction error. Experimental results on the LibriSpeech corpus show that the proposed cycle-consistency training reduced the word error rate by 14.7% from an initial model trained with 100-hour paired data, using an additional 360 hours of audio data without transcriptions. We also investigate the use of text-only data mainly for language modeling to further improve the performance in the unpaired data training scenario.

Jaejin Cho, Murali Karthick Baskar, Ruizhi Li et al.

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new direction in speech research. The approach benefits by performing model training without using lexicon and alignments. However, this poses a new problem of requiring more data compared to conventional DNN-HMM systems. In this work, we attempt to use data from 10 BABEL languages to build a multi-lingual seq2seq model as a prior model, and then port them towards 4 other BABEL languages using transfer learning approach. We also explore different architectures for improving the prior multilingual seq2seq model. The paper also discusses the effect of integrating a recurrent neural network language model (RNNLM) with a seq2seq model during decoding. Experimental results show that the transfer learning approach from the multilingual model shows substantial gains over monolingual models across all 4 BABEL languages. Incorporating an RNNLM also brings significant improvements in terms of %WER, and achieves recognition performance comparable to the models trained with twice more training data.

Takaaki Hori, Jaejin Cho, Shinji Watanabe

This paper investigates the impact of word-based RNN language models (RNN-LMs) on the performance of end-to-end automatic speech recognition (ASR). In our prior work, we have proposed a multi-level LM, in which character-based and word-based RNN-LMs are combined in hybrid CTC/attention-based ASR. Although this multi-level approach achieves significant error reduction in the Wall Street Journal (WSJ) task, two different LMs need to be trained and used for decoding, which increase the computational cost and memory usage. In this paper, we further propose a novel word-based RNN-LM, which allows us to decode with only the word-based LM, where it provides look-ahead word probabilities to predict next characters instead of the character-based LM, leading competitive accuracy with less computation compared to the multi-level LM. We demonstrate the efficacy of the word-based RNN-LMs using a larger corpus, LibriSpeech, in addition to WSJ we used in the prior work. Furthermore, we show that the proposed model achieves 5.1 %WER for WSJ Eval'92 test set when the vocabulary size is increased, which is the best WER reported for end-to-end ASR systems on this benchmark.

Tomoki Hayashi, Shinji Watanabe, Yu Zhang et al.

In this paper we propose a novel data augmentation method for attention-based end-to-end automatic speech recognition (E2E-ASR), utilizing a large amount of text which is not paired with speech signals. Inspired by the back-translation technique proposed in the field of machine translation, we build a neural text-to-encoder model which predicts a sequence of hidden states extracted by a pre-trained E2E-ASR encoder from a sequence of characters. By using hidden states as a target instead of acoustic features, it is possible to achieve faster attention learning and reduce computational cost, thanks to sub-sampling in E2E-ASR encoder, also the use of the hidden states can avoid to model speaker dependencies unlike acoustic features. After training, the text-to-encoder model generates the hidden states from a large amount of unpaired text, then E2E-ASR decoder is retrained using the generated hidden states as additional training data. Experimental evaluation using LibriSpeech dataset demonstrates that our proposed method achieves improvement of ASR performance and reduces the number of unknown words without the need for paired data.

Chiori Hori, Huda Alamri, Jue Wang et al.

Dialog systems need to understand dynamic visual scenes in order to have conversations with users about the objects and events around them. Scene-aware dialog systems for real-world applications could be developed by integrating state-of-the-art technologies from multiple research areas, including: end-to-end dialog technologies, which generate system responses using models trained from dialog data; visual question answering (VQA) technologies, which answer questions about images using learned image features; and video description technologies, in which descriptions/captions are generated from videos using multimodal information. We introduce a new dataset of dialogs about videos of human behaviors. Each dialog is a typed conversation that consists of a sequence of 10 question-and-answer(QA) pairs between two Amazon Mechanical Turk (AMT) workers. In total, we collected dialogs on roughly 9,000 videos. Using this new dataset for Audio Visual Scene-aware dialog (AVSD), we trained an end-to-end conversation model that generates responses in a dialog about a video. Our experiments demonstrate that using multimodal features that were developed for multimodal attention-based video description enhances the quality of generated dialog about dynamic scenes (videos). Our dataset, model code and pretrained models will be publicly available for a new Video Scene-Aware Dialog challenge.

Hiroshi Seki, Takaaki Hori, Shinji Watanabe et al.

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments for effective learning. In this paper, we propose a new sequence-to-sequence framework to directly decode multiple label sequences from a single speech sequence by unifying source separation and speech recognition functions in an end-to-end manner. We further propose a new objective function to improve the contrast between the hidden vectors to avoid generating similar hypotheses. Experimental results show that the model is directly able to learn a mapping from a speech mixture to multiple label sequences, achieving 83.1 % relative improvement compared to a model trained without the proposed objective. Interestingly, the results are comparable to those produced by previous end-to-end works featuring explicit separation and recognition modules.

Chiori Hori, Takaaki Hori

End-to-end training of neural networks is a promising approach to automatic construction of dialog systems using a human-to-human dialog corpus. Recently, Vinyals et al. tested neural conversation models using OpenSubtitles. Lowe et al. released the Ubuntu Dialogue Corpus for researching unstructured multi-turn dialogue systems. Furthermore, the approach has been extended to accomplish task oriented dialogs to provide information properly with natural conversation. For example, Ghazvininejad et al. proposed a knowledge grounded neural conversation model [3], where the research is aiming at combining conversational dialogs with task-oriented knowledge using unstructured data such as Twitter data for conversation and Foursquare data for external knowledge.However, the task is still limited to a restaurant information service, and has not yet been tested with a wide variety of dialog tasks. In addition, it is still unclear how to create intelligent dialog systems that can respond like a human agent. In consideration of these problems, we proposed a challenge track to the 6th dialog system technology challenges (DSTC6) using human-to-human dialog data to mimic human dialog behaviors. The focus of the challenge track is to train end-to-end conversation models from human-to-human conversation and accomplish end-to-end dialog tasks in various situations assuming a customer service, in which a system plays a role of human agent and generates natural and informative sentences in response to user's questions or comments given dialog context.

Takaaki Hori, Shinji Watanabe, Yu Zhang et al.

We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR) model. We learn to listen and write characters with a joint Connectionist Temporal Classification (CTC) and attention-based encoder-decoder network. The encoder is a deep Convolutional Neural Network (CNN) based on the VGG network. The CTC network sits on top of the encoder and is jointly trained with the attention-based decoder. During the beam search process, we combine the CTC predictions, the attention-based decoder predictions and a separately trained LSTM language model. We achieve a 5-10\% error reduction compared to prior systems on spontaneous Japanese and Chinese speech, and our end-to-end model beats out traditional hybrid ASR systems.

Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori et al.

The field of speech recognition is in the midst of a paradigm shift: end-to-end neural networks are challenging the dominance of hidden Markov models as a core technology. Using an attention mechanism in a recurrent encoder-decoder architecture solves the dynamic time alignment problem, allowing joint end-to-end training of the acoustic and language modeling components. In this paper we extend the end-to-end framework to encompass microphone array signal processing for noise suppression and speech enhancement within the acoustic encoding network. This allows the beamforming components to be optimized jointly within the recognition architecture to improve the end-to-end speech recognition objective. Experiments on the noisy speech benchmarks (CHiME-4 and AMI) show that our multichannel end-to-end system outperformed the attention-based baseline with input from a conventional adaptive beamformer.

Chiori Hori, Takaaki Hori, Teng-Yok Lee et al.

Currently successful methods for video description are based on encoder-decoder sentence generation using recur-rent neural networks (RNNs). Recent work has shown the advantage of integrating temporal and/or spatial attention mechanisms into these models, in which the decoder net-work predicts each word in the description by selectively giving more weight to encoded features from specific time frames (temporal attention) or to features from specific spatial regions (spatial attention). In this paper, we propose to expand the attention model to selectively attend not just to specific times or spatial regions, but to specific modalities of input such as image features, motion features, and audio features. Our new modality-dependent attention mechanism, which we call multimodal attention, provides a natural way to fuse multimodal information for video description. We evaluate our method on the Youtube2Text dataset, achieving results that are competitive with current state of the art. More importantly, we demonstrate that our model incorporating multimodal attention as well as temporal attention significantly outperforms the model that uses temporal attention alone.

Suyoun Kim, Takaaki Hori, Shinji Watanabe

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping between variable-length input and output sequences in one step using a purely data-driven method. The attention model has often been shown to improve the performance over another end-to-end approach, the Connectionist Temporal Classification (CTC), mainly because it explicitly uses the history of the target character without any conditional independence assumptions. However, we observed that the performance of the attention has shown poor results in noisy condition and is hard to learn in the initial training stage with long input sequences. This is because the attention model is too flexible to predict proper alignments in such cases due to the lack of left-to-right constraints as used in CTC. This paper presents a novel method for end-to-end speech recognition to improve robustness and achieve fast convergence by using a joint CTC-attention model within the multi-task learning framework, thereby mitigating the alignment issue. An experiment on the WSJ and CHiME-4 tasks demonstrates its advantages over both the CTC and attention-based encoder-decoder baselines, showing 5.4-14.6% relative improvements in Character Error Rate (CER).