arXiv subjects

Jinyu Li

Publications and source records attributed to Jinyu Li.

At least 163 records · Page 9Linked to original sources

arXiv2020

Listen, Look and Deliberate: Visual context-aware speech recognition using pre-trained text-video representations

In this study, we try to address the problem of leveraging visual signals to improve Automatic Speech Recognition (ASR), also known as visual context-aware ASR (VC-ASR). We explore novel VC-ASR approaches to leverage video and text representations extracted by a self-supervised pre-trained text-video embedding model. Firstly, we propose a multi-stream attention architecture to leverage signals from both audio and video modalities. This architecture consists of separate encoders for the two modalities and a single decoder that attends over them. We show that this architecture is better than fusing modalities at the signal level. Additionally, we also explore leveraging the visual information in a second pass model, which has also been referred to as a `deliberation model'. The deliberation model accepts audio representations and text hypotheses from the first pass ASR and combines them with a visual stream for an improved visual context-aware recognition. The proposed deliberation scheme can work on top of any well trained ASR and also enabled us to leverage the pre-trained text model to ground the hypotheses with the visual features. Our experiments on HOW2 dataset show that multi-stream and deliberation architectures are very effective at the VC-ASR task. We evaluate the proposed models for two scenarios; clean audio stream and distorted audio in which we mask out some specific words in the audio. The deliberation model outperforms the multi-stream model and achieves a relative WER improvement of 6% and 8.7% for the clean and masked data, respectively, compared to an audio-only model. The deliberation model also improves recovering the masked words by 59% relative.

eess.AS↗

arXiv2020

Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition

The external language models (LM) integration remains a challenging task for end-to-end (E2E) automatic speech recognition (ASR) which has no clear division between acoustic and language models. In this work, we propose an internal LM estimation (ILME) method to facilitate a more effective integration of the external LM with all pre-existing E2E models with no additional model training, including the most popular recurrent neural network transducer (RNN-T) and attention-based encoder-decoder (AED) models. Trained with audio-transcript pairs, an E2E model implicitly learns an internal LM that characterizes the training data in the source domain. With ILME, the internal LM scores of an E2E model are estimated and subtracted from the log-linear interpolation between the scores of the E2E model and the external LM. The internal LM scores are approximated as the output of an E2E model when eliminating its acoustic components. ILME can alleviate the domain mismatch between training and testing, or improve the multi-domain E2E ASR. Experimented with 30K-hour trained RNN-T and AED models, ILME achieves up to 15.5% and 6.8% relative word error rate reductions from Shallow Fusion on out-of-domain LibriSpeech and in-domain Microsoft production test sets, respectively.

eess.AS↗

arXiv2020

Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis

Multi-speaker speech recognition of unsegmented recordings has diverse applications such as meeting transcription and automatic subtitle generation. With technical advances in systems dealing with speech separation, speaker diarization, and automatic speech recognition (ASR) in the last decade, it has become possible to build pipelines that achieve reasonable error rates on this task. In this paper, we propose an end-to-end modular system for the LibriCSS meeting data, which combines independently trained separation, diarization, and recognition components, in that order. We study the effect of different state-of-the-art methods at each stage of the pipeline, and report results using task-specific metrics like SDR and DER, as well as downstream WER. Experiments indicate that the problem of overlapping speech for diarization and ASR can be effectively mitigated with the presence of a well-trained separation module. Our best system achieves a speaker-attributed WER of 12.7%, which is close to that of a non-overlapping ASR.

eess.AS↗

arXiv2020

Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020

This paper describes the Microsoft speaker diarization system for monaural multi-talker recordings in the wild, evaluated at the diarization track of the VoxCeleb Speaker Recognition Challenge(VoxSRC) 2020. We will first explain our system design to address issues in handling real multi-talker recordings. We then present the details of the components, which include Res2Net-based speaker embedding extractor, conformer-based continuous speech separation with leakage filtering, and a modified DOVER (short for Diarization Output Voting Error Reduction) method for system fusion. We evaluate the systems with the data set provided by VoxSRCchallenge 2020, which contains real-life multi-talker audio collected from YouTube. Our best system achieves 3.71% and 6.23% of the diarization error rate (DER) on development set and evaluation set, respectively, being ranked the 1st at the diarization track of the challenge.

eess.AS↗

arXiv2020

Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer

With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been successfully applied to speech separation recently. However, multi-channel speech separation sometimes does not necessarily need such a heavy structure for all time frames especially when the cross-talker challenge happens only occasionally. For example, in conversation scenarios, most regions contain only a single active speaker, where the separation task downgrades to a single speaker enhancement problem. It turns out that using a very deep network structure for dealing with signals with a low overlap ratio not only negatively affects the inference efficiency but also hurts the separation performance. To deal with this problem, we propose an early exit mechanism, which enables the Transformer model to handle different cases with adaptive depth. Experimental results indicate that not only does the early exit mechanism accelerate the inference, but it also improves the accuracy.

cs.SD↗

arXiv2020

Continuous Speech Separation with Conformer

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and conformer in lieu of recurrent neural networks in the separation system, as we believe capturing global information with the self-attention based method is crucial for the speech separation. Evaluating on the LibriCSS dataset, the conformer separation model achieves state of the art results, with a relative 23.5% word error rate (WER) reduction from bi-directional LSTM (BLSTM) in the utterance-wise evaluation and a 15.4% WER reduction in the continuous evaluation.

eess.AS↗

arXiv2020

Speaker Separation Using Speaker Inventories and Estimated Speech

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 speaker separation performance using the output of first-pass separation. We evaluate the models on both speaker separation and speech recognition metrics.

cs.SD↗

arXiv2020

An End-to-end Architecture of Online Multi-channel Speech Separation

Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas a remedy to this problem. Previously, we introduced a sys-tem, calledunmixing,fixed-beamformerandextraction(UFE),that was shown to be effective in addressing the speech over-lap problem in conversation transcription. With UFE, an inputmixed signal is processed by fixed beamformers, followed by aneural network post filtering. Although promising results wereobtained, the system contains multiple individually developedmodules, leading potentially sub-optimum performance. In thiswork, we introduce an end-to-end modeling version of UFE. Toenable gradient propagation all the way, an attentional selectionmodule is proposed, where an attentional weight is learnt foreach beamformer and spatial feature sampled over space. Ex-perimental results show that the proposed system achieves com-parable performance in an offline evaluation with the originalseparate processing-based pipeline, while producing remark-able improvements in an online evaluation.

eess.AS↗

arXiv2020

Transfer Learning Approaches for Streaming End-to-End Speech Recognition System

Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language. TL can be applied to end-to-end (E2E) ASR system such as recurrent neural network transducer (RNN-T) models, by initializing the encoder and/or prediction network of the target language with the pre-trained models from source language. In the hybrid ASR system, transfer learning is typically done by initializing the target language acoustic model (AM) with source language AM. Several transfer learning strategies exist in the case of the RNN-T framework, depending upon the choice of the initialization model for encoder and prediction networks. This paper presents a comparative study of four different TL methods for RNN-T framework. We show 17% relative word error rate reduction with different TL methods over randomly initialized RNN-T model. We also study the impact of TL with varying amount of training data ranging from 50 hours to 1000 hours and show the efficacy of TL for languages with small amount of training data.

eess.AS↗

arXiv2020

Exploring Transformers for Large-Scale Speech Recognition

While recurrent neural networks still largely define state-of-the-art speech recognition systems, the Transformer network has been proven to be a competitive alternative, especially in the offline condition. Most studies with Transformers have been constrained in a relatively small scale setting, and some forms of data argumentation approaches are usually applied to combat the data sparsity issue. In this paper, we aim at understanding the behaviors of Transformers in the large-scale speech recognition setting, where we have used around 65,000 hours of training data. We investigated various aspects on scaling up Transformers, including model initialization, warmup training as well as different Layer Normalization strategies. In the streaming condition, we compared the widely used attention mask based future context lookahead approach to the Transformer-XL network. From our experiments, we show that Transformers can achieve around 6% relative word error rate (WER) reduction compared to the BLSTM baseline in the offline fashion, while in the streaming fashion, Transformer-XL is comparable to LC-BLSTM with 800 millisecond latency constraint.

eess.AS↗

arXiv2020

On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition

Recently, there has been a strong push to transition from hybrid models to end-to-end (E2E) models for automatic speech recognition. Currently, there are three promising E2E methods: recurrent neural network transducer (RNN-T), RNN attention-based encoder-decoder (AED), and Transformer-AED. In this study, we conduct an empirical comparison of RNN-T, RNN-AED, and Transformer-AED models, in both non-streaming and streaming modes. We use 65 thousand hours of Microsoft anonymized training data to train these models. As E2E models are more data hungry, it is better to compare their effectiveness with large amount of training data. To the best of our knowledge, no such comprehensive study has been conducted yet. We show that although AED models are stronger than RNN-T in the non-streaming mode, RNN-T is very competitive in streaming mode if its encoder can be properly initialized. Among all three E2E models, transformer-AED achieved the best accuracy in both streaming and non-streaming mode. We show that both streaming RNN-T and transformer-AED models can obtain better accuracy than a highly-optimized hybrid model.

eess.AS↗

arXiv2020

Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability

Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition. In this paper, we describe our recent development of RNN-T models with reduced GPU memory consumption during training, better initialization strategy, and advanced encoder modeling with future lookahead. When trained with Microsoft's 65 thousand hours of anonymized training data, the developed RNN-T model surpasses a very well trained hybrid model with both better recognition accuracy and lower latency. We further study how to customize RNN-T models to a new domain, which is important for deploying E2E models to practical scenarios. By comparing several methods leveraging text-only data in the new domain, we found that updating RNN-T's prediction and joint networks using text-to-speech generated from domain-specific text is the most effective.

eess.AS↗

arXiv2020

Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are delayed compared to the actual acoustic boundaries since their unidirectional encoders lack future information. This leads to an inevitable latency during inference. To alleviate this issue and reduce latency, we propose several strategies during training by leveraging external hard alignments extracted from the hybrid model. We investigate to utilize the alignments in both the encoder and the decoder. On the encoder side, (1) multi-task learning and (2) pre-training with the framewise classification task are studied. On the decoder side, we (3) remove inappropriate alignment paths beyond an acceptable latency during the alignment marginalization, and (4) directly minimize the differentiable expected latency loss. Experiments on the Cortana voice search task demonstrate that our proposed methods can significantly reduce the latency, and even improve the recognition accuracy in certain cases on the decoder side. We also present some analysis to understand the behaviors of streaming S2S models.

cs.CL↗

arXiv2020

Continuous speech separation: dataset and analysis

This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior studies on speech separation use pre-segmented signals of artificially mixed speech utterances which are mostly \emph{fully} overlapped, and the algorithms are evaluated based on signal-to-distortion ratio or similar performance metrics. However, in natural conversations, a speech signal is continuous, containing both overlapped and overlap-free components. In addition, the signal-based metrics have very weak correlations with automatic speech recognition (ASR) accuracy. We think that not only does this make it hard to assess the practical relevance of the tested algorithms, it also hinders researchers from developing systems that can be readily applied to real scenarios. In this paper, we define continuous speech separation (CSS) as a task of generating a set of non-overlapped speech signals from a \textit{continuous} audio stream that contains multiple utterances that are \emph{partially} overlapped by a varying degree. A new real recorded dataset, called LibriCSS, is derived from LibriSpeech by concatenating the corpus utterances to simulate a conversation and capturing the audio replays with far-field microphones. A Kaldi-based ASR evaluation protocol is also established by using a well-trained multi-conditional acoustic model. By using this dataset, several aspects of a recently proposed speaker-independent CSS algorithm are investigated. The dataset and evaluation scripts are available to facilitate the research in this direction.

cs.SD↗

arXiv2020

Low Latency End-to-End Streaming Speech Recognition with a Scout Network

The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition accuracy when applying a fixed-length look-ahead window in each encoder layer. In this paper, we propose a novel low-latency streaming approach for Transformer models, which consists of a scout network and a recognition network. The scout network detects the whole word boundary without seeing any future frames, while the recognition network predicts the next subword by utilizing the information from all the frames before the predicted boundary. Our model achieves the best performance (2.7/6.4 WER) with only 639 ms latency on the test-clean and test-other data sets of Librispeech.

eess.AS↗

arXiv2020

Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition

Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However, RNN-T training is made difficult by the huge memory requirements, and complicated neural structure. A common solution to ease the RNN-T training is to employ connectionist temporal classification (CTC) model along with RNN language model (RNNLM) to initialize the RNN-T parameters. In this work, we conversely leverage external alignments to seed the RNN-T model. Two different pre-training solutions are explored, referred to as encoder pre-training, and whole-network pre-training respectively. Evaluated on Microsoft 65,000 hours anonymized production data with personally identifiable information removed, our proposed methods can obtain significant improvement. In particular, the encoder pre-training solution achieved a 10% and a 8% relative word error rate reduction when compared with random initialization and the widely used CTC+RNNLM initialization strategy, respectively. Our solutions also significantly reduce the RNN-T model latency from the baseline.

cs.CL↗

arXiv2020

L-Vector: Neural Label Embedding for Domain Adaptation

We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains. With NLE method, we distill the knowledge from a powerful source-domain DNN into a dictionary of label embeddings, or l-vectors, one for each senone class. Each l-vector is a representation of the senone-specific output distributions of the source-domain DNN and is learned to minimize the average L2, Kullback-Leibler (KL) or symmetric KL distance to the output vectors with the same label through simple averaging or standard back-propagation. During adaptation, the l-vectors serve as the soft targets to train the target-domain model with cross-entropy loss. Without parallel data constraint as in the teacher-student learning, NLE is specially suited for the situation where the paired target-domain data cannot be simulated from the source-domain data. We adapt a 6400 hours multi-conditional US English acoustic model to each of the 9 accented English (80 to 830 hours) and kids' speech (80 hours). NLE achieves up to 14.1% relative word error rate reduction over direct re-training with one-hot labels.

eess.AS↗

arXiv2020

High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion, we argue that such conventional hybrid models can still be significantly improved. In this paper, we detail our recent efforts to improve conventional hybrid LSTM acoustic models for high-accuracy and low-latency automatic speech recognition. To achieve high accuracy, we use a contextual layer trajectory LSTM (cltLSTM), which decouples the temporal modeling and target classification tasks, and incorporates future context frames to get more information for accurate acoustic modeling. We further improve the training strategy with sequence-level teacher-student learning. To obtain low latency, we design a two-head cltLSTM, in which one head has zero latency and the other head has a small latency, compared to an LSTM. When trained with Microsoft's 65 thousand hours of anonymized training data and evaluated with test sets with 1.8 million words, the proposed two-head cltLSTM model with the proposed training strategy yields a 28.2\% relative WER reduction over the conventional LSTM acoustic model, with a similar perceived latency.

eess.AS↗