Multi-Task Learning for Front-End Text Processing in TTS
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909158852263936 |
|---|---|
| author | Kang, Wonjune Wang, Yun Zhang, Shun Hinsvark, Arthur He, Qing |
| author_facet | Kang, Wonjune Wang, Yun Zhang, Shun Hinsvark, Arthur He, Qing |
| contents | We propose a multi-task learning (MTL) model for jointly performing three tasks that are commonly solved in a text-to-speech (TTS) front-end: text normalization (TN), part-of-speech (POS) tagging, and homograph disambiguation (HD). Our framework utilizes a tree-like structure with a trunk that learns shared representations, followed by separate task-specific heads. We further incorporate a pre-trained language model to utilize its built-in lexical and contextual knowledge, and study how to best use its embeddings so as to most effectively benefit our multi-task model. Through task-wise ablations, we show that our full model trained on all three tasks achieves the strongest overall performance compared to models trained on individual or sub-combinations of tasks, confirming the advantages of our MTL framework. Finally, we introduce a new HD dataset containing a balanced number of sentences in diverse contexts for a variety of homographs and their pronunciations. We demonstrate that incorporating this dataset into training significantly improves HD performance over only using a commonly used, but imbalanced, pre-existing dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_06321 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Task Learning for Front-End Text Processing in TTS Kang, Wonjune Wang, Yun Zhang, Shun Hinsvark, Arthur He, Qing Computation and Language We propose a multi-task learning (MTL) model for jointly performing three tasks that are commonly solved in a text-to-speech (TTS) front-end: text normalization (TN), part-of-speech (POS) tagging, and homograph disambiguation (HD). Our framework utilizes a tree-like structure with a trunk that learns shared representations, followed by separate task-specific heads. We further incorporate a pre-trained language model to utilize its built-in lexical and contextual knowledge, and study how to best use its embeddings so as to most effectively benefit our multi-task model. Through task-wise ablations, we show that our full model trained on all three tasks achieves the strongest overall performance compared to models trained on individual or sub-combinations of tasks, confirming the advantages of our MTL framework. Finally, we introduce a new HD dataset containing a balanced number of sentences in diverse contexts for a variety of homographs and their pronunciations. We demonstrate that incorporating this dataset into training significantly improves HD performance over only using a commonly used, but imbalanced, pre-existing dataset. |
| title | Multi-Task Learning for Front-End Text Processing in TTS |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.06321 |