Convoifilter: A case study of doing cocktail party speech recognition

arXiv:2308.11380v3 Announce Type: replace-cross
Abstract: This paper presents an end-to-end model designed to improve automatic speech recognition (ASR) for a particular speaker in a crowded, noisy environment. The model utilizes a single-channel speech enhancement module that isolates the speaker's voice from background noise (ConVoiFilter) and an ASR module. The model can decrease ASR's word error rate (WER) from 80% to 26.4% through this approach. Typically, these two components are adjusted independently due to variations in data requirements. However, speech enhancement …

abstract arxiv asr automatic speech recognition case case study cs.cl cs.sd eess.as environment noise paper recognition speaker speech speech recognition study type voice