Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"speech": models, code, and papers

SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation

Nov 03, 2020
Xutai Ma, Juan Pino, Philipp Koehn

Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together. We investigate how to adapt simultaneous text translation methods such as wait-k and monotonic multihead attention to end-to-end simultaneous speech translation by introducing a pre-decision module. A detailed analysis is provided on the latency-quality trade-offs of combining fixed and flexible pre-decision with fixed and flexible policies. We also design a novel computation-aware latency metric, adapted from Average Lagging.

  Access Paper or Ask Questions

Two-Pass End-to-End Speech Recognition

Aug 29, 2019
Tara N. Sainath, Ruoming Pang, David Rybach, Yanzhang He, Rohit Prabhavalkar, Wei Li, Mirkó Visontai, Qiao Liang, Trevor Strohman, Yonghui Wu, Ian McGraw, Chung-Cheng Chiu

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

  Access Paper or Ask Questions

The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation

Aug 09, 2021
Minghan Wang, Yuxia Wang, Chang Su, Jiaxin Guo, Yingtao Zhang, Yujia Liu, Min Zhang, Shimin Tao, Xingshan Zeng, Liangyou Li, Hao Yang, Ying Qin

This paper describes our work in participation of the IWSLT-2021 offline speech translation task. Our system was built in a cascade form, including a speaker diarization module, an Automatic Speech Recognition (ASR) module and a Machine Translation (MT) module. We directly use the LIUM SpkDiarization tool as the diarization module. The ASR module is trained with three ASR datasets from different sources, by multi-source training, using a modified Transformer encoder. The MT module is pretrained on the large-scale WMT news translation dataset and fine-tuned on the TED corpus. Our method achieves 24.6 BLEU score on the 2021 test set.

  Access Paper or Ask Questions

EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement

Feb 14, 2022
Kuan-Chen Wang, Kai-Chun Liu, Hsin-Min Wang, Yu Tsao

Multimodal learning has been proven to be an effective method to improve speech enhancement (SE) performance, especially in challenging situations such as low signal-to-noise ratios, speech noise, or unseen noise types. In previous studies, several types of auxiliary data have been used to construct multimodal SE systems, such as lip images, electropalatography, or electromagnetic midsagittal articulography. In this paper, we propose a novel EMGSE framework for multimodal SE, which integrates audio and facial electromyography (EMG) signals. Facial EMG is a biological signal containing articulatory movement information, which can be measured in a non-invasive way. Experimental results show that the proposed EMGSE system can achieve better performance than the audio-only SE system. The benefits of fusing EMG signals with acoustic signals for SE are notable under challenging circumstances. Furthermore, this study reveals that cheek EMG is sufficient for SE.

* 5 pages, 4 figures, and 3 tables 

  Access Paper or Ask Questions

UPC's Speech Translation System for IWSLT 2021

May 10, 2021
Gerard I. Gállego, Ioannis Tsiamas, Carlos Escolano, José A. R. Fonollosa, Marta R. Costa-jussà

This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Machine Translation group. The task consists of building a system capable of translating English audio recordings extracted from TED talks into German text. Submitted systems can be either cascade or end-to-end and use a custom or given segmentation. Our submission is an end-to-end speech translation system, which combines pre-trained models (Wav2Vec 2.0 and mBART) with coupling modules between the encoder and decoder, and uses an efficient fine-tuning technique, which trains only 20% of its total parameters. We show that adding an Adapter to the system and pre-training it, can increase the convergence speed and the final result, with which we achieve a BLEU score of 27.3 on the MuST-C test set. Our final model is an ensemble that obtains 28.22 BLEU score on the same set. Our submission also uses a custom segmentation algorithm that employs pre-trained Wav2Vec 2.0 for identifying periods of untranscribable text and can bring improvements of 2.5 to 3 BLEU score on the IWSLT 2019 test set, as compared to the result with the given segmentation.

* Submitted to IWSLT 2021 

  Access Paper or Ask Questions

Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation

Sep 06, 2020
Akhil Mathur, Fahim Kawsar, Nadia Berthouze, Nicholas D. Lane

This paper introduces a new dataset, Libri-Adapt, to support unsupervised domain adaptation research on speech recognition models. Built on top of the LibriSpeech corpus, Libri-Adapt contains English speech recorded on mobile and embedded-scale microphones, and spans 72 different domains that are representative of the challenging practical scenarios encountered by ASR models. More specifically, Libri-Adapt facilitates the study of domain shifts in ASR models caused by a) different acoustic environments, b) variations in speaker accents, c) heterogeneity in the hardware and platform software of the microphones, and d) a combination of the aforementioned three shifts. We also provide a number of baseline results quantifying the impact of these domain shifts on the Mozilla DeepSpeech2 ASR model.

* 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 7439-7443 
* 5 pages, Published at IEEE ICASSP 2020 

  Access Paper or Ask Questions

Automatic Estimation of Inteligibility Measure for Consonants in Speech

May 12, 2020
Ali Abavisani, Mark Hasegawa-Johnson

In this article, we provide a model to estimate a real-valued measure of the intelligibility of individual speech segments. We trained regression models based on Convolutional Neural Networks (CNN) for stop consonants \textipa{/p,t,k,b,d,g/} associated with vowel \textipa{/A/}, to estimate the corresponding Signal to Noise Ratio (SNR) at which the Consonant-Vowel (CV) sound becomes intelligible for Normal Hearing (NH) ears. The intelligibility measure for each sound is called SNR$_{90}$, and is defined to be the SNR level at which human participants are able to recognize the consonant at least 90\% correctly, on average, as determined in prior experiments with NH subjects. Performance of the CNN is compared to a baseline prediction based on automatic speech recognition (ASR), specifically, a constant offset subtracted from the SNR at which the ASR becomes capable of correctly labeling the consonant. Compared to baseline, our models were able to accurately estimate the SNR$_{90}$~intelligibility measure with less than 2 [dB$^2$] Mean Squared Error (MSE) on average, while the baseline ASR-defined measure computes SNR$_{90}$~with a variance of 5.2 to 26.6 [dB$^2$], depending on the consonant.

* 5 pages, 1 figure, 7 tables, submitted to Inter Speech 2020 Conference 

  Access Paper or Ask Questions

speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment

Apr 03, 2021
Junbo Zhang, Zhiwen Zhang, Yongqing Wang, Zhiyong Yan, Qiong Song, Yukai Huang, Ke Li, Daniel Povey, Yujun Wang

This paper introduces a new open-source speech corpus named "speechocean762" designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children. Five experts annotated each of the utterances at sentence-level, word-level and phoneme-level. A baseline system is released in open source to illustrate the phoneme-level pronunciation assessment workflow on this corpus. This corpus is allowed to be used freely for commercial and non-commercial purposes. It is available for free download from OpenSLR, and the corresponding baseline system is published in the Kaldi speech recognition toolkit.

  Access Paper or Ask Questions

Leveraging End-to-End Speech Recognition with Neural Architecture Search

Dec 11, 2019
Ahmed Baruwa, Mojeed Abisiga, Ibrahim Gbadegesin, Afeez Fakunle

Deep neural networks (DNNs) have been demonstrated to outperform many traditional machine learning algorithms in Automatic Speech Recognition (ASR). In this paper, we show that a large improvement in the accuracy of deep speech models can be achieved with effective Neural Architecture Optimization at a very low computational cost. Phone recognition tests with the popular LibriSpeech and TIMIT benchmarks proved this fact by displaying the ability to discover and train novel candidate models within a few hours (less than a day) many times faster than the attention-based seq2seq models. Our method achieves test error of 7% Word Error Rate (WER) on the LibriSpeech corpus and 13% Phone Error Rate (PER) on the TIMIT corpus, on par with state-of-the-art results.

* IJSER, vol 10, Issue 11, 2019, pp 1113-1119 

  Access Paper or Ask Questions

Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition

Feb 27, 2017
Zhiyuan Tang, Ying Shi, Dong Wang, Yang Feng, Shiyue Zhang

Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU). However, the dynamic properties behind the remarkable performance remain unclear in many applications, e.g., automatic speech recognition (ASR). This paper employs visualization techniques to study the behavior of LSTM and GRU when performing speech recognition tasks. Our experiments show some interesting patterns in the gated memory, and some of them have inspired simple yet effective modifications on the network structure. We report two of such modifications: (1) lazy cell update in LSTM, and (2) shortcut connections for residual learning. Both modifications lead to more comprehensible and powerful networks.

* ICASSP 2017 

  Access Paper or Ask Questions