Improving Language Identification for Multilingual Speakers

Autor:	Titus, Andrew, Silovsky, Jan, Chen, Nanxin, Hsiao, Roger, Young, Mary, Ghoshal, Arnab
Rok vydání:	2020
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Machine Learning Computer Science - Sound Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Spoken language identification (LID) technologies have improved in recent years from discriminating largely distinct languages to discriminating highly similar languages or even dialects of the same language. One aspect that has been mostly neglected, however, is discrimination of languages for multilingual speakers, despite being a primary target audience of many systems that utilize LID technologies. As we show in this work, LID systems can have a high average accuracy for most combinations of languages while greatly underperforming for others when accented speech is present. We address this by using coarser-grained targets for the acoustic LID model and integrating its outputs with interaction context signals in a context-aware model to tailor the system to each user. This combined system achieves an average 97% accuracy across all language combinations while improving worst-case accuracy by over 60% relative to our baseline. Comment: 5 pages, 2 figures. Submitted to ICASSP 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2001.11019 Zobrazit plný text záznamu View this record from Arxiv