Saved in:
Bibliographic Details
Main Authors: Wang, Chen, Peng, Tianyu, Yang, Wen, Bai, Yinan, Wang, Guangfu, Lin, Jun, Jia, Lanpeng, Wu, Lingxiang, Wang, Jinqiao, Zong, Chengqing, Zhang, Jiajun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05177
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918171909292032
author Wang, Chen
Peng, Tianyu
Yang, Wen
Bai, Yinan
Wang, Guangfu
Lin, Jun
Jia, Lanpeng
Wu, Lingxiang
Wang, Jinqiao
Zong, Chengqing
Zhang, Jiajun
author_facet Wang, Chen
Peng, Tianyu
Yang, Wen
Bai, Yinan
Wang, Guangfu
Lin, Jun
Jia, Lanpeng
Wu, Lingxiang
Wang, Jinqiao
Zong, Chengqing
Zhang, Jiajun
contents Empathetic interaction is a cornerstone of human-machine communication, due to the need for understanding speech enriched with paralinguistic cues and generating emotional and expressive responses. However, the most powerful empathetic LSLMs are increasingly closed off, leaving the crucial details about the architecture, data and development opaque to researchers. Given the critical need for transparent research into the LSLMs and empathetic behavior, we present OpenS2S, a fully open-source, transparent and end-to-end LSLM designed to enable empathetic speech interactions. Based on our empathetic speech-to-text model BLSP-Emo, OpenS2S further employs a streaming interleaved decoding architecture to achieve low-latency speech generation. To facilitate end-to-end training, OpenS2S incorporates an automated data construction pipeline that synthesizes diverse, high-quality empathetic speech dialogues at low cost. By leveraging large language models to generate empathetic content and controllable text-to-speech systems to introduce speaker and emotional variation, we construct a scalable training corpus with rich paralinguistic diversity and minimal human supervision. We release the fully open-source OpenS2S model, including the dataset, model weights, pre-training and fine-tuning codes, to empower the broader research community and accelerate innovation in empathetic speech systems. The project webpage can be accessed at https://casia-lm.github.io/OpenS2S
format Preprint
id arxiv_https___arxiv_org_abs_2507_05177
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model
Wang, Chen
Peng, Tianyu
Yang, Wen
Bai, Yinan
Wang, Guangfu
Lin, Jun
Jia, Lanpeng
Wu, Lingxiang
Wang, Jinqiao
Zong, Chengqing
Zhang, Jiajun
Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
Empathetic interaction is a cornerstone of human-machine communication, due to the need for understanding speech enriched with paralinguistic cues and generating emotional and expressive responses. However, the most powerful empathetic LSLMs are increasingly closed off, leaving the crucial details about the architecture, data and development opaque to researchers. Given the critical need for transparent research into the LSLMs and empathetic behavior, we present OpenS2S, a fully open-source, transparent and end-to-end LSLM designed to enable empathetic speech interactions. Based on our empathetic speech-to-text model BLSP-Emo, OpenS2S further employs a streaming interleaved decoding architecture to achieve low-latency speech generation. To facilitate end-to-end training, OpenS2S incorporates an automated data construction pipeline that synthesizes diverse, high-quality empathetic speech dialogues at low cost. By leveraging large language models to generate empathetic content and controllable text-to-speech systems to introduce speaker and emotional variation, we construct a scalable training corpus with rich paralinguistic diversity and minimal human supervision. We release the fully open-source OpenS2S model, including the dataset, model weights, pre-training and fine-tuning codes, to empower the broader research community and accelerate innovation in empathetic speech systems. The project webpage can be accessed at https://casia-lm.github.io/OpenS2S
title OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model
topic Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.05177