BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912183406821376 |
|---|---|
| author | Nie, Yuting Zhao, Junhong Zhang, Wei-Qiang Bai, Jinfeng |
| author_facet | Nie, Yuting Zhao, Junhong Zhang, Wei-Qiang Bai, Jinfeng |
| contents | Language 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2203_00328 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | BERT-LID: Leveraging BERT to Improve Spoken Language Identification Nie, Yuting Zhao, Junhong Zhang, Wei-Qiang Bai, Jinfeng Computation and Language Sound Audio and Speech Processing Language 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. |
| title | BERT-LID: Leveraging BERT to Improve Spoken Language Identification |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2203.00328 |