Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-to-Speech-Reference-Cited by-同舟云学术

Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-to-Speech

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Saeki Takaaki¹,Zen Heiga¹,Chen Zhehuai²,Morioka Nobuyuki¹,Wang Gary²,Zhang Yu²,Bapna Ankur²,Rosenberg Andrew²,Ramabhadran Bhuvana²

Affiliation:

1. Google,Japan

2. Google,USA

Publisher

IEEE

Link

Reference40 articles.

2. Common Voice: A massively-multilingual speech corpus;ardila,2019

3. A3T: Alignment-aware acoustic and text pretraining for speech synthesis and editing;bai;Proc ICML,2022

4. Maestro-U: leveraging joint speech–text representation learning for zero supervised speech ASR;chen,2022

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

2. Few-Shot Spoken Language Understanding Via Joint Speech-Text Models;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16

4. Joint Speech-Text Embeddings with Disentangled Speaker Features;2023 34th Irish Signals and Systems Conference (ISSC);2023-06-13