English
Related papers

Related papers: A practical two-stage training strategy for multi-…

200 papers

The recognition of personalized content, such as contact names, remains a challenging problem for end-to-end speech recognition systems. In this work, we demonstrate how first and second-pass rescoring strategies can be leveraged together…

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…

Computation and Language · Computer Science 2018-01-04 Kanishka Rao , Haşim Sak , Rohit Prabhavalkar

In this work, we study the problem of cross-subject motor imagery (MI) decoding from electroencephalography (EEG) data. Multi-subject EEG datasets present several kinds of domain shifts due to various inter-individual differences (e.g.…

Signal Processing · Electrical Eng. & Systems 2024-02-22 Georgios Zoumpourlis , Ioannis Patras

We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis. We also examine choice of neural vocoder for waveform synthesis, as well as…

Sound · Computer Science 2020-11-11 Erica Cooper , Xin Wang , Yi Zhao , Yusuke Yasuda , Junichi Yamagishi

A speaker extraction algorithm seeks to extract the target speaker's speech from a multi-talker speech mixture. The prior studies focus mostly on speaker extraction from a highly overlapped multi-talker speech mixture. However, the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-01 Zexu Pan , Meng Ge , Haizhou Li

Controllable speech synthesis aims to control the style of generated speech using reference input, which can be of various modalities. Existing face-based methods struggle with robustness and generalization due to data quality constraints,…

Sound · Computer Science 2025-06-27 Rui Niu , Weihao Wu , Jie Chen , Long Ma , Zhiyong Wu

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-17 Li Fu , Xiaoxiao Li , Libo Zi , Zhengchen Zhang , Youzheng Wu , Xiaodong He , Bowen Zhou

This paper presents a new approach for end-to-end audio-visual multi-talker speech recognition. The approach, referred to here as the visual context attention model (VCAM), is important because it uses the available video information to…

Sound · Computer Science 2022-04-05 Richard Rose , Olivier Siohan

To accomplish the punctuation restoration task, most existing approaches focused on leveraging extra information (e.g., part-of-speech tags) or addressing the class imbalance problem. Recent works have widely applied the transformer-based…

Computation and Language · Computer Science 2022-04-12 Yangjun Wu , Kebin Fang , Yao Zhao

Multimodal dimensional emotion recognition has drawn a great attention from the affective computing community and numerous schemes have been extensively investigated, making a significant progress in this area. However, several questions…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Dung Nguyen , Duc Thanh Nguyen , Rui Zeng , Thanh Thi Nguyen , Son N. Tran , Thin Nguyen , Sridha Sridharan , Clinton Fookes

End-to-end diarization presents an attractive alternative to standard cascaded diarization systems because a single system can handle all aspects of the task at once. Many flavors of end-to-end models have been proposed but all of them…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-27 Federico Landini , Mireia Diez , Alicia Lozano-Diez , Lukáš Burget

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

End-to-end Speech-to-text Translation (E2E-ST), which directly translates source language speech to target language text, is widely useful in practice, but traditional cascaded approaches (ASR+MT) often suffer from error propagation in the…

Computation and Language · Computer Science 2021-02-10 Junkun Chen , Mingbo Ma , Renjie Zheng , Liang Huang

Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-26 Anirudh Raju , Aparna Khare , Di He , Ilya Sklyar , Long Chen , Sam Alptekin , Viet Anh Trinh , Zhe Zhang , Colin Vaz , Venkatesh Ravichandran , Roland Maas , Ariya Rastrow

The majority of existing speech bandwidth extension (BWE) methods operate under the constraint of fixed source and target sampling rates, which limits their flexibility in practical applications. In this paper, we propose a multi-stage…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-05 Ye-Xin Lu , Yang Ai , Zheng-Yan Sheng , Zhen-Hua Ling

Unsupervised video object segmentation (UVOS) aims at detecting the primary objects in a given video sequence without any human interposing. Most existing methods rely on two-stream architectures that separately encode the appearance and…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Lingyi Hong , Wei Zhang , Shuyong Gao , Hong Lu , WenQiang Zhang

The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-06 Zhengkun Tian , Jiangyan Yi , Ye Bai , Jianhua Tao , Shuai Zhang , Zhengqi Wen

Attention encoder-decoder model architecture is the backbone of several recent top performing foundation speech models: Whisper, Seamless, OWSM, and Canary-1B. However, the reported data and compute requirements for their training are…

Meetings are a common activity in professional contexts, and it remains challenging to endow vocal assistants with advanced functionalities to facilitate meeting management. In this context, a task like active speaker detection can provide…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Lionel Pibre , Francisco Madrigal , Cyrille Equoy , Frédéric Lerasle , Thomas Pellegrini , Julien Pinquier , Isabelle Ferrané

Automatic speech emotion recognition (SER) by a computer is a critical component for more natural human-machine interaction. As in human-human interaction, the capability to perceive emotion correctly is essential to take further steps in a…

Sound · Computer Science 2022-10-27 Bagus Tris Atmaja , Masato Akagi