Audio-visual fine-tuning of audio-only ASR models

Audio-visual automatic speech recognition (AV-ASR) models are very effective at reducing word error rates on noisy speech, but require large amounts of transcribed AV training data. Recently, audio-visual self-supervised learning (SSL) approaches have been developed to reduce this dependence on tran...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-12
Hauptverfasser:	May, Avner, Serdyuk, Dmitriy, Ankit Parag Shah, Braga, Otavio, Siohan, Olivier
Format:	Artikel
Sprache:	eng
Schlagworte:	Audio data Audio visual equipment Automatic speech recognition Error reduction Machine learning Self-supervised learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!