Leveraging Language Information for Target Language Extraction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911247483535360 |
|---|---|
| author | Yıldırım, Mehmet Sinan Tao, Ruijie Wang, Wupeng Ao, Junyi Li, Haizhou |
| author_facet | Yıldırım, Mehmet Sinan Tao, Ruijie Wang, Wupeng Ao, Junyi Li, Haizhou |
| contents | Target Language Extraction aims to extract speech in a specific language from a mixture waveform that contains multiple speakers speaking different languages. The human auditory system is adept at performing this task with the knowledge of the particular language. However, the performance of the conventional extraction systems is limited by the lack of this prior knowledge. Speech pre-trained models, which capture rich linguistic and phonetic representations from large-scale in-the-wild corpora, can provide this missing language knowledge to these systems. In this work, we propose a novel end-to-end framework to leverage language knowledge from speech pre-trained models. This knowledge is used to guide the extraction model to better capture the target language characteristics, thereby improving extraction quality. To demonstrate the effectiveness of our proposed approach, we construct the first publicly available multilingual dataset for Target Language Extraction. Experimental results show that our method achieves improvements of 1.22 dB and 1.12 dB in SI-SNR for English and German extraction, respectively, from mixtures containing both languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01652 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Language Information for Target Language Extraction Yıldırım, Mehmet Sinan Tao, Ruijie Wang, Wupeng Ao, Junyi Li, Haizhou Audio and Speech Processing Sound Target Language Extraction aims to extract speech in a specific language from a mixture waveform that contains multiple speakers speaking different languages. The human auditory system is adept at performing this task with the knowledge of the particular language. However, the performance of the conventional extraction systems is limited by the lack of this prior knowledge. Speech pre-trained models, which capture rich linguistic and phonetic representations from large-scale in-the-wild corpora, can provide this missing language knowledge to these systems. In this work, we propose a novel end-to-end framework to leverage language knowledge from speech pre-trained models. This knowledge is used to guide the extraction model to better capture the target language characteristics, thereby improving extraction quality. To demonstrate the effectiveness of our proposed approach, we construct the first publicly available multilingual dataset for Target Language Extraction. Experimental results show that our method achieves improvements of 1.22 dB and 1.12 dB in SI-SNR for English and German extraction, respectively, from mixtures containing both languages. |
| title | Leveraging Language Information for Target Language Extraction |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2511.01652 |