Year: 2026
Type: preprint
Abstract: This report presents VibeVoice-ASR, a general-purpose speech understanding framework built upon VibeVoice, designed to address the persistent challenges of context fragmentation and multi-speaker complexity in long-form audio (e.g., meetings, podcasts) that remain despite recent advancements in short-form speech recognition. Unlike traditional pipelined approaches that rely on audio chunking, VibeVoice-ASRsupports single-pass processing for up to 60 minutes of audio. It unifies Automatic Speech Recognition, Speaker Diarization, and Timestamping into a single end-to-end generation task. In addition, VibeVoice-ASR supports over 50 languages, requires no explicit language setting, and natively handles code-switching within and across utterances. Furthermore, we introduce a prompt-based context injection mechanism that allows users to supply customized conetxt, significantly improving accuracy on domain-specific terminology and polyphonic character disambiguation.
Source: arXiv (Cornell University)
Authors: Peng, Zhiliang, Yu, Jianwei, Chang, Yaoyao, Wang, Zilong, Dong, Li, Hao, Yingbo, Tu, Yujie, Yang, Chenyu, Wang, Wenhui, Xu, Songchen, Sun, Yutao, Bao, Hangbo, Xu, Weijiang, Zhu, Yi, Wang, Zehua, Song, Ting, Xia, Yan, Chi, Zewen, Huang, Shaohan, Wang, Liang, Ding, Chuang, Wang, Shuai, Chen, Xie, Wei, Furu
Institution: Microsoft Research (United Kingdom)
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7125811016
Cites:
Cited by:
Related to: