File(s) stored somewhere else
Please note: Linked content is NOT stored on Open Access Te Herenga Waka-Victoria University of Wellington and we can't guarantee its availability, quality, security or accept any liability.
BERT-LID: Leveraging BERT to Improve Spoken Language Identification
conference contribution
posted on 2023-02-12, 20:32 authored by Yuting Nie, Junhong ZhaoJunhong Zhao, Wei-Qiang Zhang, Jinfeng BaiLanguage identification is the task of automatically determining the identity of a language conveyed by a spoken segment. It has a profound impact on the multilingual interoperability of an intelligent speech system. Despite language identification attaining high accuracy on medium or long utterances(>3s), the performance on short utterances (<=1s) is still far from satisfactory. We propose a BERT-based language identification system (BERT-LID) to improve language identification performance, especially on short-duration speech segments. We extend the original BERT model by taking the phonetic posteriorgrams (PPG) derived from the front-end phone recognizer as input. Then we deployed the optimal deep classifier followed by it for language identification. Our BERT-LID model can improve the baseline accuracy by about 6.5% on long-segment identification and 19.9% on short-segment identification, demonstrating our BERT-LID's effectiveness to language identification
