Pushing the performances of ASR models on English and Spanish accents

Autor:	Chitkara, Pooja, Riviere, Morgane, Copet, Jade, Zhang, Frank, Saraf, Yatharth
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Speech to text models tend to be trained and evaluated against a single target accent. This is especially true for English for which native speakers from the United States became the main benchmark. In this work, we are going to show how two simple methods: pre-trained embeddings and auxiliary classification losses can improve the performance of ASR systems. We are looking for upgrades as universal as possible and therefore we will explore their impact on several models architectures and several languages.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.12048 Zobrazit plný text záznamu View this record from Arxiv