Adapting Foundation Speech Recognition Models to Impaired Speech: A Semantic Re-chaining Approach for Personalization of German Speech
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916812135858176 |
|---|---|
| author | Pokel, Niclas Moure, Pehuén Boehringer, Roman Gao, Yingqiang |
| author_facet | Pokel, Niclas Moure, Pehuén Boehringer, Roman Gao, Yingqiang |
| contents | Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advances, ASR models like Whisper struggle with non-normative speech due to limited training data and the difficulty of collecting and annotating non-normative speech samples. In this work, we propose a practical and lightweight pipeline to personalize ASR models, formalizing the selection of words and enriching a small, speech-impaired dataset with semantic coherence. Applied to data from a child with a structural speech impairment, our approach shows promising improvements in transcription quality, demonstrating the potential to reduce communication barriers for individuals with atypical speech patterns. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21622 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adapting Foundation Speech Recognition Models to Impaired Speech: A Semantic Re-chaining Approach for Personalization of German Speech Pokel, Niclas Moure, Pehuén Boehringer, Roman Gao, Yingqiang Computation and Language Artificial Intelligence Sound Audio and Speech Processing Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advances, ASR models like Whisper struggle with non-normative speech due to limited training data and the difficulty of collecting and annotating non-normative speech samples. In this work, we propose a practical and lightweight pipeline to personalize ASR models, formalizing the selection of words and enriching a small, speech-impaired dataset with semantic coherence. Applied to data from a child with a structural speech impairment, our approach shows promising improvements in transcription quality, demonstrating the potential to reduce communication barriers for individuals with atypical speech patterns. |
| title | Adapting Foundation Speech Recognition Models to Impaired Speech: A Semantic Re-chaining Approach for Personalization of German Speech |
| topic | Computation and Language Artificial Intelligence Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.21622 |