LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908606400561152 |
|---|---|
| author | Lee, Sangmin Chung, Woo-Jin Kang, Hong-Goo |
| author_facet | Lee, Sangmin Chung, Woo-Jin Kang, Hong-Goo |
| contents | Building a universal multilingual automatic speech recognition (ASR) model that performs equitably across languages has long been a challenge due to its inherent difficulties. To address this task we introduce a Language-Agnostic Multilingual ASR pipeline through orthography Unification and language-specific Transliteration (LAMA-UT). LAMA-UT operates without any language-specific modules while matching the performance of state-of-the-art models trained on a minimal amount of data. Our pipeline consists of two key steps. First, we utilize a universal transcription generator to unify orthographic features into Romanized form and capture common phonetic characteristics across diverse languages. Second, we utilize a universal converter to transform these universal transcriptions into language-specific ones. In experiments, we demonstrate the effectiveness of our proposed method leveraging universal transcriptions for massively multilingual ASR. Our pipeline achieves a relative error reduction rate of 45% when compared to Whisper and performs comparably to MMS, despite being trained on only 0.1% of Whisper's training data. Furthermore, our pipeline does not rely on any language-specific modules. However, it performs on par with zero-shot ASR approaches which utilize additional language-specific lexicons and language models. We expect this framework to serve as a cornerstone for flexible multilingual ASR systems that are generalizable even to unseen languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15299 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration Lee, Sangmin Chung, Woo-Jin Kang, Hong-Goo Computation and Language Sound Audio and Speech Processing Building a universal multilingual automatic speech recognition (ASR) model that performs equitably across languages has long been a challenge due to its inherent difficulties. To address this task we introduce a Language-Agnostic Multilingual ASR pipeline through orthography Unification and language-specific Transliteration (LAMA-UT). LAMA-UT operates without any language-specific modules while matching the performance of state-of-the-art models trained on a minimal amount of data. Our pipeline consists of two key steps. First, we utilize a universal transcription generator to unify orthographic features into Romanized form and capture common phonetic characteristics across diverse languages. Second, we utilize a universal converter to transform these universal transcriptions into language-specific ones. In experiments, we demonstrate the effectiveness of our proposed method leveraging universal transcriptions for massively multilingual ASR. Our pipeline achieves a relative error reduction rate of 45% when compared to Whisper and performs comparably to MMS, despite being trained on only 0.1% of Whisper's training data. Furthermore, our pipeline does not rely on any language-specific modules. However, it performs on par with zero-shot ASR approaches which utilize additional language-specific lexicons and language models. We expect this framework to serve as a cornerstone for flexible multilingual ASR systems that are generalizable even to unseen languages. |
| title | LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2412.15299 |