Universal-2-TF: Robust All-Neural Text Formatting for ASR
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_ | 1866916561273487360 |
|---|---|
| author | Khare, Yash Peyash, Taufiquzzaman Vanzo, Andrea Yoshioka, Takuya |
| author_facet | Khare, Yash Peyash, Taufiquzzaman Vanzo, Andrea Yoshioka, Takuya |
| contents | This paper introduces an all-neural text formatting (TF) model designed for commercial automatic speech recognition (ASR) systems, encompassing punctuation restoration (PR), truecasing, and inverse text normalization (ITN). Unlike traditional rule-based or hybrid approaches, this method leverages a two-stage neural architecture comprising a multi-objective token classifier and a sequence-to-sequence (seq2seq) model. This design minimizes computational costs and reduces hallucinations while ensuring flexibility and robustness across diverse linguistic entities and text domains. Developed as part of the Universal-2 ASR system, the proposed method demonstrates superior performance in TF accuracy, computational efficiency, and perceptual quality, as validated through comprehensive evaluations using both objective and subjective methods. This work underscores the importance of holistic TF models in enhancing ASR usability in practical settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05948 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Universal-2-TF: Robust All-Neural Text Formatting for ASR Khare, Yash Peyash, Taufiquzzaman Vanzo, Andrea Yoshioka, Takuya Computation and Language I.2.7 This paper introduces an all-neural text formatting (TF) model designed for commercial automatic speech recognition (ASR) systems, encompassing punctuation restoration (PR), truecasing, and inverse text normalization (ITN). Unlike traditional rule-based or hybrid approaches, this method leverages a two-stage neural architecture comprising a multi-objective token classifier and a sequence-to-sequence (seq2seq) model. This design minimizes computational costs and reduces hallucinations while ensuring flexibility and robustness across diverse linguistic entities and text domains. Developed as part of the Universal-2 ASR system, the proposed method demonstrates superior performance in TF accuracy, computational efficiency, and perceptual quality, as validated through comprehensive evaluations using both objective and subjective methods. This work underscores the importance of holistic TF models in enhancing ASR usability in practical settings. |
| title | Universal-2-TF: Robust All-Neural Text Formatting for ASR |
| topic | Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2501.05948 |