English
Related papers

Related papers: Unsupervised pre-training for sequence to sequence…

200 papers

On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can benefit from training them jointly to take advantage of the…

Computation and Language · Computer Science 2021-07-15 Varun Nagaraja , Yangyang Shi , Ganesh Venkatesh , Ozlem Kalinli , Michael L. Seltzer , Vikas Chandra

Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with linguistic information. Both of them are beneficial for…

Sound · Computer Science 2022-11-28 Zhuoyuan Yao , Shuo Ren , Sanyuan Chen , Ziyang Ma , Pengcheng Guo , Lei Xie

Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks.…

Computation and Language · Computer Science 2024-04-01 Yash Jain , David Chan , Pranav Dheram , Aparna Khare , Olabanji Shonibare , Venkatesh Ravichandran , Shalini Ghosh

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models…

Audio and Speech Processing · Electrical Eng. & Systems 2018-02-16 Shubham Toshniwal , Tara N. Sainath , Ron J. Weiss , Bo Li , Pedro Moreno , Eugene Weinstein , Kanishka Rao

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-05 Tao Tu , Yuan-Jui Chen , Alexander H. Liu , Hung-yi Lee

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

Computation and Language · Computer Science 2019-02-21 Ozan Caglayan , Ramon Sanabria , Shruti Palaskar , Loïc Barrault , Florian Metze

Recent advancements in speech large language models (SpeechLLMs) have attracted considerable attention. Nonetheless, current methods exhibit suboptimal performance in adhering to speech instructions. Notably, the intelligence of models…

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…

Sound · Computer Science 2021-02-17 Yi Lin , Qin Li , Bo Yang , Zhen Yan , Huachun Tan , Zhengmao Chen

Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve…

Computation and Language · Computer Science 2022-10-25 Hao Yang , Jinming Zhao , Gholamreza Haffari , Ehsan Shareghi

Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the…

Computation and Language · Computer Science 2020-03-17 Chengyi Wang , Yu Wu , Yujiao Du , Jinyu Li , Shujie Liu , Liang Lu , Shuo Ren , Guoli Ye , Sheng Zhao , Ming Zhou

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…

Computation and Language · Computer Science 2021-09-02 Qian Chen , Wen Wang , Qinglin Zhang

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Machine Learning · Computer Science 2022-07-13 Metehan Cekic , Ruirui Li , Zeya Chen , Yuguang Yang , Andreas Stolcke , Upamanyu Madhow

This paper describes a method based on a sequence-to-sequence learning (Seq2Seq) with attention and context preservation mechanism for voice conversion (VC) tasks. Seq2Seq has been outstanding at numerous tasks involving sequence modeling…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-13 Kou Tanaka , Hirokazu Kameoka , Takuhiro Kaneko , Nobukatsu Hojo

Despite the recent significant advances witnessed in end-to-end (E2E) ASR system for code-switching, hunger for audio-text paired data limits the further improvement of the models' performance. In this paper, we propose a decoupled…

Sound · Computer Science 2020-10-29 Shuai Zhang , Jiangyan Yi , Zhengkun Tian , Ye Bai , Jianhua Tao , Zhengqi wen

Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Martin Kišš , Michal Hradiš

Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Zehan Li , Yan Yang , Xueqing Li , Jian Kang , Xiao-Lei Zhang , Jie Li

Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of…

Computation and Language · Computer Science 2022-06-16 Alexander H. Liu , Wei-Ning Hsu , Michael Auli , Alexei Baevski

End-to-end (E2E) spoken language understanding (SLU) can infer semantics directly from speech signal without cascading an automatic speech recognizer (ASR) with a natural language understanding (NLU) module. However, paired utterance…

Computation and Language · Computer Science 2021-02-15 Yao Qian , Ximo Bian , Yu Shi , Naoyuki Kanda , Leo Shen , Zhen Xiao , Michael Zeng

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

End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or decoder using source transcripts via speech recognition or text translation tasks, without which translation performance drops substantially.…

Computation and Language · Computer Science 2022-06-10 Biao Zhang , Barry Haddow , Rico Sennrich