Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912386838953984 |
|---|---|
| author | Xue, Hongfei Tang, Yufeng Zhang, Jun Geng, Xuelong Xie, Lei |
| author_facet | Xue, Hongfei Tang, Yufeng Zhang, Jun Geng, Xuelong Xie, Lei |
| contents | Although multilingual automatic speech recognition (ASR) systems have significantly advanced, enabling a single model to handle multiple languages, inherent linguistic differences and data imbalances challenge SOTA performance across all languages. While language identification (LID) models can route speech to the appropriate ASR model, they incur high costs from invoking SOTA commercial models and suffer from inaccuracies due to misclassification. To overcome these, we propose SIMA, a selective invocation for multilingual ASR that adapts to the difficulty level of the input speech. Built on a spoken large language model (SLLM), SIMA evaluates whether the input is simple enough for direct transcription or requires the invocation of a SOTA ASR model. Our approach reduces word error rates by 18.7% compared to the SLLM and halves invocation costs compared to LID-based methods. Tests on three datasets show that SIMA is a scalable, cost-effective solution for multilingual ASR applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_16168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Xue, Hongfei Tang, Yufeng Zhang, Jun Geng, Xuelong Xie, Lei Sound Audio and Speech Processing Although multilingual automatic speech recognition (ASR) systems have significantly advanced, enabling a single model to handle multiple languages, inherent linguistic differences and data imbalances challenge SOTA performance across all languages. While language identification (LID) models can route speech to the appropriate ASR model, they incur high costs from invoking SOTA commercial models and suffer from inaccuracies due to misclassification. To overcome these, we propose SIMA, a selective invocation for multilingual ASR that adapts to the difficulty level of the input speech. Built on a spoken large language model (SLLM), SIMA evaluates whether the input is simple enough for direct transcription or requires the invocation of a SOTA ASR model. Our approach reduces word error rates by 18.7% compared to the SLLM and halves invocation costs compared to LID-based methods. Tests on three datasets show that SIMA is a scalable, cost-effective solution for multilingual ASR applications. |
| title | Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.16168 |