English
Related papers

Related papers: Non-autoregressive Transformer-based End-to-end AS…

200 papers

Non-autoregressive transformer models have achieved extremely fast inference speed and comparable performance with autoregressive sequence-to-sequence models in neural machine translation. Most of the non-autoregressive transformers decode…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Zhengkun Tian , Jiangyan Yi , Jianhua Tao , Ye Bai , Shuai Zhang , Zhengqi Wen

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Computation and Language · Computer Science 2020-02-17 Genta Indra Winata , Samuel Cahyawijaya , Zhaojiang Lin , Zihan Liu , Pascale Fung

Automatic speech recognition (ASR) allows transcribing the communications between air traffic controllers (ATCOs) and aircraft pilots. The transcriptions are used later to extract ATC named entities, e.g., aircraft callsigns. One common…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-18 Juan Zuluaga-Gomez , Seyyed Saeed Sarfjoo , Amrutha Prasad , Iuliia Nigmatulina , Petr Motlicek , Karel Ondrej , Oliver Ohneiser , Hartmut Helmke

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Computation and Language · Computer Science 2020-02-06 Chi Sun , Xipeng Qiu , Yige Xu , Xuanjing Huang

Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-11 Grant P. Strimel , Yi Xie , Brian King , Martin Radfar , Ariya Rastrow , Athanasios Mouchtaris

Machine learning methods have recently achieved high-performance in biomedical text analysis. However, a major bottleneck in the widespread application of these methods is obtaining the required large amounts of annotated training data,…

Machine Learning · Computer Science 2019-12-06 Xing Meng , Craig H. Ganoe , Ryan T. Sieberg , Yvonne Y. Cheung , Saeed Hassanpour

Attention-based models have made tremendous progress on end-to-end automatic speech recognition(ASR) recently. However, the conventional transformer-based approaches usually generate the sequence results token by token from left to right,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Xi Chen , Songyang Zhang , Dandan Song , Peng Ouyang , Shouyi Yin

End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results, but they require large datasets and extensive computing resources. Transfer learning has been proposed to overcome these difficulties even…

Computation and Language · Computer Science 2021-09-03 Peter Polák , Ondřej Bojar

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

Computation and Language · Computer Science 2023-02-09 Hongqiu Wu , Ruixue Ding , Hai Zhao , Pengjun Xie , Fei Huang , Min Zhang

General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from…

Computation and Language · Computer Science 2020-04-30 Matthew Henderson , Iñigo Casanueva , Nikola Mrkšić , Pei-Hao Su , Tsung-Hsien Wen , Ivan Vulić

Recently, Transformer based models have shown competitive automatic speech recognition (ASR) performance. One key factor in the success of these models is the multi-head attention mechanism. However, for trained models, we have previously…

Computation and Language · Computer Science 2021-04-07 Shucong Zhang , Erfan Loweimi , Peter Bell , Steve Renals

Large scale self-supervised pre-training of Transformer language models has advanced the field of Natural Language Processing and shown promise in cross-application to the biological `languages' of proteins and DNA. Learning effective…

Machine Learning · Computer Science 2021-12-15 Meredith V. Trotter , Cuong Q. Nguyen , Stephen Young , Rob T. Woodruff , Kim M. Branson

In this paper, we take a step towards jointly modeling automatic speech recognition (STT) and speech synthesis (TTS) in a fully non-autoregressive way. We develop a novel multimodal framework capable of handling the speech and text…

The recent rise of generative artificial intelligence (AI), powered by Transformer networks, has achieved remarkable success in natural language processing, computer vision, and graphics. However, the application of Transformers in…

Graphics · Computer Science 2025-09-01 Qiang Zou , Lizhen Zhu

This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the conditional independence assumptions used in conventional CTC…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-21 Yosuke Higuchi , Brian Yan , Siddhant Arora , Tetsuji Ogawa , Tetsunori Kobayashi , Shinji Watanabe

Transferring the knowledge of large language models (LLMs) is a promising technique to incorporate linguistic knowledge into end-to-end automatic speech recognition (ASR) systems. However, existing works only transfer a single…

Computation and Language · Computer Science 2023-12-27 Takuma Udagawa , Masayuki Suzuki , Gakuto Kurata , Masayasu Muraoka , George Saon

Addressing the detrimental impact of non-stationary environmental noise on automatic speech recognition (ASR) has been a persistent and significant research focus. Despite advancements, this challenge continues to be a major concern.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-06 Noussaiba Djeffal , Djamel Addou , Hamza Kheddar , Sid Ahmed Selouani

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network.…

Computation and Language · Computer Science 2016-12-28 Zewang Zhang , Zheng Sun , Jiaqi Liu , Jingwen Chen , Zhao Huo , Xiao Zhang

Multilingual BERT (mBERT), a language model pre-trained on large multilingual corpora, has impressive zero-shot cross-lingual transfer capabilities and performs surprisingly well on zero-shot POS tagging and Named Entity Recognition (NER),…

Computation and Language · Computer Science 2022-05-18 Beiduo Chen , Wu Guo , Quan Liu , Kun Tao

We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization. Our architecture creates sparse computation pathways…

Computation and Language · Computer Science 2022-07-07 Yi Xie , Jonathan Macoskey , Martin Radfar , Feng-Ju Chang , Brian King , Ariya Rastrow , Athanasios Mouchtaris , Grant P. Strimel