Cued Speech Generation Leveraging a Pre-trained Audiovisual Text-to-Speech Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915095577100288 |
|---|---|
| author | Sankar, Sanjana Lenglet, Martin Bailly, Gerard Beautemps, Denis Hueber, Thomas |
| author_facet | Sankar, Sanjana Lenglet, Martin Bailly, Gerard Beautemps, Denis Hueber, Thomas |
| contents | This paper presents a novel approach for the automatic generation of Cued Speech (ACSG), a visual communication system used by people with hearing impairment to better elicit the spoken language. We explore transfer learning strategies by leveraging a pre-trained audiovisual autoregressive text-to-speech model (AVTacotron2). This model is reprogrammed to infer Cued Speech (CS) hand and lip movements from text input. Experiments are conducted on two publicly available datasets, including one recorded specifically for this study. Performance is assessed using an automatic CS recognition system. With a decoding accuracy at the phonetic level reaching approximately 77%, the results demonstrate the effectiveness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04799 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cued Speech Generation Leveraging a Pre-trained Audiovisual Text-to-Speech Model Sankar, Sanjana Lenglet, Martin Bailly, Gerard Beautemps, Denis Hueber, Thomas Computation and Language This paper presents a novel approach for the automatic generation of Cued Speech (ACSG), a visual communication system used by people with hearing impairment to better elicit the spoken language. We explore transfer learning strategies by leveraging a pre-trained audiovisual autoregressive text-to-speech model (AVTacotron2). This model is reprogrammed to infer Cued Speech (CS) hand and lip movements from text input. Experiments are conducted on two publicly available datasets, including one recorded specifically for this study. Performance is assessed using an automatic CS recognition system. With a decoding accuracy at the phonetic level reaching approximately 77%, the results demonstrate the effectiveness of our approach. |
| title | Cued Speech Generation Leveraging a Pre-trained Audiovisual Text-to-Speech Model |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.04799 |