English
Related papers

Related papers: Fully Learnable Front-End for Multi-Channel Acoust…

200 papers

Although great progresses have been made in automatic speech recognition (ASR), significant performance degradation is still observed when recognizing multi-talker mixed speech. In this paper, we propose and evaluate several architectures…

Sound · Computer Science 2018-12-06 Yanmin Qian , Xuankai Chang , Dong Yu

While existing end-to-end beamformers achieve impressive performance in various front-end speech processing tasks, they usually encapsulate the whole process into a black box and thus lack adequate interpretability. As an attempt to fill…

Sound · Computer Science 2022-03-17 Andong Li , Guochen Yu , Chengshi Zheng , Xiaodong Li

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of…

Sound · Computer Science 2022-02-18 Kun Wei , Yike Zhang , Sining Sun , Lei Xie , Long Ma

In multi-channel speech enhancement and robust automatic speech recognition (ASR), beamforming can typically improve the signal-to-noise ratio (SNR) of the target speaker and produce reliable enhancement with little distortion to target…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-22 Zhong-Qiu Wang , Ruizhe Pang

Recent work has shown that it is possible to train an $\textit{unsupervised}$ automatic speech recognition (ASR) system using only unpaired audio and text. Existing unsupervised ASR methods assume that no labeled data can be used for…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-19 Tatiana Likhomanenko , Loren Lugosch , Ronan Collobert

To address the performance gap of English ASR models on L2 English speakers, we evaluate fine-tuning of pretrained wav2vec 2.0 models (Baevski et al., 2020; Xu et al., 2021) on L2-ARCTIC, a non-native English speech corpus (Zhao et al.,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-18 Toshiko Shibano , Xinyi Zhang , Mia Taige Li , Haejin Cho , Peter Sullivan , Muhammad Abdul-Mageed

Sequence-to-sequence (S2S) modeling is becoming a popular paradigm for automatic speech recognition (ASR) because of its ability to jointly optimize all the conventional ASR components in an end-to-end (E2E) fashion. This report…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-30 Aswin Shanmugam Subramanian , Xiaofei Wang , Shinji Watanabe , Toru Taniguchi , Dung Tran , Yuya Fujita

This paper presents a study on the use of federated learning to train an ASR model based on a wav2vec 2.0 model pre-trained by self supervision. Carried out on the well-known TED-LIUM 3 dataset, our experiments show that such a model can…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-22 Tuan Nguyen , Salima Mdhaffar , Natalia Tomashenko , Jean-François Bonastre , Yannick Estève

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-14 Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , Shinji Watanabe

Automatic speech recognition in multi-channel reverberant conditions is a challenging task. The conventional way of suppressing the reverberation artifacts involves a beamforming based enhancement of the multi-channel speech signal, which…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-28 Anurenjan Purushothaman , Anirudh Sreeram , Sriram Ganapathy

In this work, we explore a multimodal semi-supervised learning approach for punctuation prediction by learning representations from large amounts of unlabelled audio and text data. Conventional approaches in speech processing typically use…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-04 Monica Sunkara , Srikanth Ronanki , Dhanush Bekal , Sravan Bodapati , Katrin Kirchhoff

In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…

Computation and Language · Computer Science 2018-06-19 Pengcheng Guo , Haihua Xu , Lei Xie , Eng Siong Chng

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Computation and Language · Computer Science 2022-02-14 Chak-Fai Li , Francis Keith , William Hartmann , Matthew Snover

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-06 Matthew Wiesner , Adithya Renduchintala , Shinji Watanabe , Chunxi Liu , Najim Dehak , Sanjeev Khudanpur

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…

Computation and Language · Computer Science 2021-04-20 Takaaki Hori , Niko Moritz , Chiori Hori , Jonathan Le Roux

In this paper, we study several microphone channel selection and weighting methods for robust automatic speech recognition (ASR) in noisy conditions. For channel selection, we investigate two methods based on the maximum likelihood (ML)…

Sound · Computer Science 2016-10-04 Zhaofeng Zhang , Xiong Xiao , Longbiao Wang , EngSiong Chng , Haizhou Li

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Artificial Intelligence · Computer Science 2021-03-19 Md Akmal Haidar , Chao Xing , Mehdi Rezagholizadeh

Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design decision assumes the primary input data source does not change…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-30 Gokce Keskin , Minhua Wu , Brian King , Harish Mallidi , Yang Gao , Jasha Droppo , Ariya Rastrow , Roland Maas

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-13 Anjuli Kannan , Arindrima Datta , Tara N. Sainath , Eugene Weinstein , Bhuvana Ramabhadran , Yonghui Wu , Ankur Bapna , Zhifeng Chen , Seungji Lee

Nowadays, research in speech technologies has gotten a lot out thanks to recently created public domain corpora that contain thousands of recording hours. These large amounts of data are very helpful for training the new complex models…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-12 Guillermo Cámbara , Alex Peiró-Lilja , Mireia Farrús , Jordi Luque