Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages

Kaydedildi:

Detaylı Bibliyografya
Yayımlandı:	arXiv.org (May 30, 2023), p. n/a
Yazar:	Do, Phat
Diğer Yazarlar:	Coler, Matt, Dijkstra, Jelske, Klabbers, Esther
Baskı/Yayın Bilgisi:	Cornell University Library, arXiv.org
Konular:	Prediction models Speech recognition
Online Erişim:	Citation/Abstract Full text outside of ProQuest
Etiketler:	Etiketle Etiket eklenmemiş, İlk siz ekleyin!

Diğer Bilgiler
Özet:	We train a MOS prediction model based on wav2vec 2.0 using the open-access data sets BVCC and SOMOS. Our test with neural TTS data in the low-resource language (LRL) West Frisian shows that pre-training on BVCC before fine-tuning on SOMOS leads to the best accuracy for both fine-tuned and zero-shot prediction. Further fine-tuning experiments show that using more than 30 percent of the total data does not lead to significant improvements. In addition, fine-tuning with data from a single listener shows promising system-level accuracy, supporting the viability of one-participant pilot tests. These findings can all assist the resource-conscious development of TTS for LRLs by progressing towards better zero-shot MOS prediction and informing the design of listening tests, especially in early-stage evaluation.
ISSN:	2331-8422
Kaynak:	Engineering Database