Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhu, Qiushi, Zhang, Jie, Gu, Yu, Hu, Yuchen, Dai, Lirong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916083481444352
author Zhu, Qiushi
Zhang, Jie
Gu, Yu
Hu, Yuchen
Dai, Lirong
author_facet Zhu, Qiushi
Zhang, Jie
Gu, Yu
Hu, Yuchen
Dai, Lirong
contents Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the scarcity of labeled multichannel data and complex ambient noises. The efficacy of self-supervised learning for far-field multichannel and multi-modal speech processing has not been well explored. Considering that visual information helps to improve speech recognition performance in noisy scenes, in this work we propose a multichannel multi-modal speech self-supervised learning framework AV-wav2vec2, which utilizes video and multichannel audio data as inputs. First, we propose a multi-path structure to process multichannel audio streams and a visual stream in parallel, with intra- and inter-channel contrastive losses as training targets to fully exploit the spatiotemporal information in multichannel speech data. Second, based on contrastive learning, we use additional single-channel audio data, which is trained jointly to improve the performance of speech representation. Finally, we use a Chinese multichannel multi-modal dataset in real scenarios to validate the effectiveness of the proposed method on audio-visual speech recognition (AVSR), automatic speech recognition (ASR), visual speech recognition (VSR) and audio-visual speaker diarization (AVSD) tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03468
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
Zhu, Qiushi
Zhang, Jie
Gu, Yu
Hu, Yuchen
Dai, Lirong
Audio and Speech Processing
Sound
Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the scarcity of labeled multichannel data and complex ambient noises. The efficacy of self-supervised learning for far-field multichannel and multi-modal speech processing has not been well explored. Considering that visual information helps to improve speech recognition performance in noisy scenes, in this work we propose a multichannel multi-modal speech self-supervised learning framework AV-wav2vec2, which utilizes video and multichannel audio data as inputs. First, we propose a multi-path structure to process multichannel audio streams and a visual stream in parallel, with intra- and inter-channel contrastive losses as training targets to fully exploit the spatiotemporal information in multichannel speech data. Second, based on contrastive learning, we use additional single-channel audio data, which is trained jointly to improve the performance of speech representation. Finally, we use a Chinese multichannel multi-modal dataset in real scenarios to validate the effectiveness of the proposed method on audio-visual speech recognition (AVSR), automatic speech recognition (ASR), visual speech recognition (VSR) and audio-visual speaker diarization (AVSD) tasks.
title Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2401.03468