English
Related papers

Related papers: RosettaSpeech: Zero-Shot Speech-to-Speech Translat…

200 papers

Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily…

Computation and Language · Computer Science 2022-05-18 Biao Zhang , Ankur Bapna , Melvin Johnson , Ali Dabirmoghaddam , Naveen Arivazhagan , Orhan Firat

Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Yi Ren , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , Tie-Yan Liu

This work presents a speech-to-text system "Pisets" for scientists and journalists which is based on a three-component architecture aimed at improving speech recognition accuracy while minimizing errors and hallucinations associated with…

Computation and Language · Computer Science 2026-01-27 Ivan Bondarenko , Daniil Grebenkin , Oleg Sedukhin , Mikhail Klementev , Roman Derunets , Lyudmila Budneva

Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have…

Computation and Language · Computer Science 2019-04-16 Matthias Sperber , Graham Neubig , Jan Niehues , Alex Waibel

Direct speech translation describes a scenario where only speech inputs and corresponding translations are available. Such data are notoriously limited. We present a technique that allows cascades of automatic speech recognition (ASR) and…

Computation and Language · Computer Science 2023-06-12 Tsz Kin Lam , Shigehiko Schamoni , Stefan Riezler

This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR…

Computation and Language · Computer Science 2019-05-24 Takaaki Hori , Ramon Astudillo , Tomoki Hayashi , Yu Zhang , Shinji Watanabe , Jonathan Le Roux

Joint speech-language training is challenging due to the large demand for training data and GPU consumption, as well as the modality gap between speech and language. We present ComSL, a speech-language model built atop a composite…

Computation and Language · Computer Science 2023-10-17 Chenyang Le , Yao Qian , Long Zhou , Shujie Liu , Yanmin Qian , Michael Zeng , Xuedong Huang

Zero-shot text-to-speech (TTS) aims to synthesize voices with unseen speech prompts, which significantly reduces the data and computation requirements for voice cloning by skipping the fine-tuning process. However, the prompting mechanisms…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-11 Ziyue Jiang , Jinglin Liu , Yi Ren , Jinzheng He , Zhenhui Ye , Shengpeng Ji , Qian Yang , Chen Zhang , Pengfei Wei , Chunfeng Wang , Xiang Yin , Zejun Ma , Zhou Zhao

Dialogue State Tracking (DST) is crucial for understanding user needs and executing appropriate system actions in task-oriented dialogues. Majority of existing DST methods are designed to work within predefined ontologies and assume the…

Computation and Language · Computer Science 2025-03-11 Abdulfattah Safa , Gözde Gül Şahin

Simultaneous speech translation (SST) aims to provide real-time translation of spoken language, even before the speaker finishes their sentence. Traditionally, SST has been addressed primarily by cascaded systems that decompose the task…

Computation and Language · Computer Science 2023-10-18 Peter Polák

In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style. Prior zero-shot TTS models only mimic the speaker's voice…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-05 Shengpeng Ji , Qian Chen , Wen Wang , Jialong Zuo , Minghui Fang , Ziyue Jiang , Hai Huang , Zehan Wang , Xize Cheng , Siqi Zheng , Zhou Zhao

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

Recently, the end-to-end approach has proven its efficacy in monaural multi-speaker speech recognition. However, high word error rates (WERs) still prevent these systems from being used in practical applications. On the other hand, the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-17 Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , Shinji Watanabe

Speech Recognition builds a bridge between the multimedia streaming (audio-only, visual-only or audio-visual) and the corresponding text transcription. However, when training the specific model of new domain, it often gets stuck in the lack…

Computation and Language · Computer Science 2023-06-13 Xize Cheng , Tao Jin , Linjun Li , Wang Lin , Xinyu Duan , Zhou Zhao

Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for…

Sound · Computer Science 2024-03-12 Chunhui Wang , Chang Zeng , Bowen Zhang , Ziyang Ma , Yefan Zhu , Zifeng Cai , Jian Zhao , Zhonglin Jiang , Yong Chen

Zero-shot voice conversion (VC) aims to transform source speech into arbitrary unseen target voice while keeping the linguistic content unchanged. Recent VC methods have made significant progress, but semantic losses in the decoupling…

Sound · Computer Science 2024-06-17 Linhan Ma , Xinfa Zhu , Yuanjun Lv , Zhichao Wang , Ziqian Wang , Wendi He , Hongbin Zhou , Lei Xie

Ensuring that Text-to-Speech (TTS) systems deliver human-perceived quality at scale is a central challenge for modern speech technologies. Human subjective evaluation protocols such as Mean Opinion Score (MOS) and Side-by-Side (SBS)…

Computation and Language · Computer Science 2026-04-13 Ilya Trofimenko , David Kocharyan , Aleksandr Zaitsev , Pavel Repnikov , Mark Levin , Nikita Shevtsov

Recent research on dialogue state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas. However, performance gains heavily depend on aggressive data augmentation and fine-tuning of ever larger…

Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…

Computation and Language · Computer Science 2019-11-22 Zihan Liu , Genta Indra Winata , Zhaojiang Lin , Peng Xu , Pascale Fung

Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the…

Computation and Language · Computer Science 2024-10-28 Peter Polák , Ondřej Bojar