Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.13875 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908455613235200 |
|---|---|
| author | Mena, Carlos Serra, Pol Romero, Jacobo Messaoudi, Abir Giraldo, Jose Armentano-Oller, Carme Zevallos, Rodolfo Meza, Ivan Hernando, Javier |
| author_facet | Mena, Carlos Serra, Pol Romero, Jacobo Messaoudi, Abir Giraldo, Jose Armentano-Oller, Carme Zevallos, Rodolfo Meza, Ivan Hernando, Javier |
| contents | Code-switching (CS), the alternating use of two or more languages, challenges automatic speech recognition (ASR) due to scarce training data and linguistic similarities. The lack of dedicated CS datasets limits ASR performance, as most models rely on monolingual or mixed-language corpora that fail to reflect real-world CS patterns. This issue is critical in multilingual societies where CS occurs in informal and formal settings. A key example is Catalan-Spanish CS, widely used in media and parliamentary speeches. In this work, we improve ASR for Catalan-Spanish CS by exploring three strategies: (1) generating synthetic CS data, (2) concatenating monolingual audio, and (3) leveraging real CS data with language tokens. We extract CS data from Catalan speech corpora and fine-tune OpenAI's Whisper models, making them available on Hugging Face. Results show that combining a modest amount of synthetic CS data with the dominant language token yields the best transcription performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13875 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing ASR for Catalan-Spanish Code-Switching: A Comparative Analysis of Methodologies Mena, Carlos Serra, Pol Romero, Jacobo Messaoudi, Abir Giraldo, Jose Armentano-Oller, Carme Zevallos, Rodolfo Meza, Ivan Hernando, Javier Computation and Language Audio and Speech Processing Code-switching (CS), the alternating use of two or more languages, challenges automatic speech recognition (ASR) due to scarce training data and linguistic similarities. The lack of dedicated CS datasets limits ASR performance, as most models rely on monolingual or mixed-language corpora that fail to reflect real-world CS patterns. This issue is critical in multilingual societies where CS occurs in informal and formal settings. A key example is Catalan-Spanish CS, widely used in media and parliamentary speeches. In this work, we improve ASR for Catalan-Spanish CS by exploring three strategies: (1) generating synthetic CS data, (2) concatenating monolingual audio, and (3) leveraging real CS data with language tokens. We extract CS data from Catalan speech corpora and fine-tune OpenAI's Whisper models, making them available on Hugging Face. Results show that combining a modest amount of synthetic CS data with the dominant language token yields the best transcription performance. |
| title | Optimizing ASR for Catalan-Spanish Code-Switching: A Comparative Analysis of Methodologies |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.13875 |