VIBEVOICE-ASR Technical Report
By: Zhiliang Peng , Jianwei Yu , Yaoyao Chang and more
Potential Business Impact:
Listens to hours of talking, understands everyone.
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.
Similar Papers
VibeVoice Technical Report
Computation and Language
Creates long, natural-sounding conversations with many voices.
SW-ASR: A Context-Aware Hybrid ASR Pipeline for Robust Single Word Speech Recognition
Sound
Helps computers understand spoken words in noisy places.
JoyVoice: Long-Context Conditioning for Anthropomorphic Multi-Speaker Conversational Synthesis
Sound
Makes one computer voice talk like eight people.