Decoupling and Interacting Multi-Task Learning Network for Joint Speech and Accent Recognition

Accents pose significant challenges for speech recognition systems. Although joint automatic speech recognition (ASR) and accent recognition (AR) training has been proven effective in handling multi-accent scenarios, current multi-task ASR-AR approaches overlook the granularity differences between t...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE/ACM transactions on audio, speech, and language processing speech, and language processing, 2024, Vol.32, p.459-470
Hauptverfasser:	Shao, Qijie, Guo, Pengcheng, Yan, Jinghao, Hu, Pengfei, Xie, Lei
Format:	Artikel
Sprache:	eng
Schlagworte:	Accentuation Acoustics ASR-AR multi-task learning Automatic speech recognition Chinese languages Decoding Decoupling Encoders-Decoders Error analysis Error reduction Feature extraction Inference LASAS Learning Linguistics Multitasking Pronunciation Speech recognition Task analysis two-granularity modeling units Voice recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!