Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction
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_ | 1866918036474167296 |
|---|---|
| author | Qian, Mengjie Ma, Rao Bannò, Stefano Knill, Kate M. Gales, Mark J. F. |
| author_facet | Qian, Mengjie Ma, Rao Bannò, Stefano Knill, Kate M. Gales, Mark J. F. |
| contents | Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection (DD) and removal and one for GEC. With the rise of end-to-end (E2E) speech foundation models, we investigate their effectiveness in SGEC and feedback generation. This work introduces a pseudo-labelling process to address the challenge of limited labelled data, expanding the training data size from 77 hours to approximately 2500 hours, leading to improved performance. Additionally, we prompt an E2E Whisper-based SGEC model with fluent transcriptions, showing a slight improvement in SGEC performance, with more significant gains in feedback generation. Finally, we assess the impact of increasing model size, revealing that while pseudo-labelled data does not yield performance gain for a larger Whisper model, training with prompts proves beneficial. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21137 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction Qian, Mengjie Ma, Rao Bannò, Stefano Knill, Kate M. Gales, Mark J. F. Computation and Language Sound Audio and Speech Processing Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection (DD) and removal and one for GEC. With the rise of end-to-end (E2E) speech foundation models, we investigate their effectiveness in SGEC and feedback generation. This work introduces a pseudo-labelling process to address the challenge of limited labelled data, expanding the training data size from 77 hours to approximately 2500 hours, leading to improved performance. Additionally, we prompt an E2E Whisper-based SGEC model with fluent transcriptions, showing a slight improvement in SGEC performance, with more significant gains in feedback generation. Finally, we assess the impact of increasing model size, revealing that while pseudo-labelled data does not yield performance gain for a larger Whisper model, training with prompts proves beneficial. |
| title | Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.21137 |