StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Shaolei, Fang, Qingkai, Guo, Shoutao, Ma, Zhengrui, Zhang, Min, Feng, Yang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911905336000512
author Zhang, Shaolei
Fang, Qingkai
Guo, Shoutao
Ma, Zhengrui
Zhang, Min
Feng, Yang
author_facet Zhang, Shaolei
Fang, Qingkai
Guo, Shoutao
Ma, Zhengrui
Zhang, Min
Feng, Yang
contents Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishing translation between speech, Simul-S2ST requires a policy to control the model to generate corresponding target speech at the opportune moment within speech inputs, thereby posing a double challenge of translation and policy. In this paper, we propose StreamSpeech, a direct Simul-S2ST model that jointly learns translation and simultaneous policy in a unified framework of multi-task learning. Adhering to a multi-task learning approach, StreamSpeech can perform offline and simultaneous speech recognition, speech translation and speech synthesis via an "All-in-One" seamless model. Experiments on CVSS benchmark demonstrate that StreamSpeech achieves state-of-the-art performance in both offline S2ST and Simul-S2ST tasks. Besides, StreamSpeech is able to present high-quality intermediate results (i.e., ASR or translation results) during simultaneous translation process, offering a more comprehensive real-time communication experience.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03049
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
Zhang, Shaolei
Fang, Qingkai
Guo, Shoutao
Ma, Zhengrui
Zhang, Min
Feng, Yang
Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishing translation between speech, Simul-S2ST requires a policy to control the model to generate corresponding target speech at the opportune moment within speech inputs, thereby posing a double challenge of translation and policy. In this paper, we propose StreamSpeech, a direct Simul-S2ST model that jointly learns translation and simultaneous policy in a unified framework of multi-task learning. Adhering to a multi-task learning approach, StreamSpeech can perform offline and simultaneous speech recognition, speech translation and speech synthesis via an "All-in-One" seamless model. Experiments on CVSS benchmark demonstrate that StreamSpeech achieves state-of-the-art performance in both offline S2ST and Simul-S2ST tasks. Besides, StreamSpeech is able to present high-quality intermediate results (i.e., ASR or translation results) during simultaneous translation process, offering a more comprehensive real-time communication experience.
title StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
topic Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2406.03049