Dolphin-CN-Dialect: Where Chinese Dialects Matter
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909029829181440 |
|---|---|
| author | Meng, Yangyang Zhong, Huihang Lin, Guodong Wang, Guanbo Du, Hu Shao, Zhiming Huang, Yukai Li, Ke Zhang, Wei-Qiang |
| author_facet | Meng, Yangyang Zhong, Huihang Lin, Guodong Wang, Guanbo Du, Hu Shao, Zhiming Huang, Yukai Li, Ke Zhang, Wei-Qiang |
| contents | We present Dolphin-CN-Dialect, a streaming-capable ASR model with a focus on Chinese and dialect-rich scenarios. Compared to the previous version, Dolphin-CN-Dialect introduces substantial improvements in data processing, tokenization, training stability, and data sampling strategies. To address the challenges of highly imbalanced dialect data, we propose a temperature-based sampling strategy that effectively balances standard Mandarin and low-resource dialects, leading to significant gains in dialect recognition performance. In addition, we redesign the tokenizer to better align with linguistic characteristics, adopting character-level modeling for Chinese and subword modeling for English, while introducing extensible dialect tokens. Experimental results show that Dolphin-CN-Dialect achieves improvement in dialect recognition accuracy and CER reduction compared to Dolphin. Furthermore, Dolphin-CN-Dialect reaches competitive performance with recent SOTA open-source ASR models, while maintaining a significantly smaller model size. Dolphin-CN-Dialect supports both streaming and non-streaming inference, enabling a practical balance between latency and accuracy. It also provides flexible customization through hotword support and efficient deployment optimized for specialized hardware. These improvements make Dolphin-CN-Dialect a strong and practical solution for real-world multi-dialect ASR applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08961 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dolphin-CN-Dialect: Where Chinese Dialects Matter Meng, Yangyang Zhong, Huihang Lin, Guodong Wang, Guanbo Du, Hu Shao, Zhiming Huang, Yukai Li, Ke Zhang, Wei-Qiang Computation and Language Audio and Speech Processing We present Dolphin-CN-Dialect, a streaming-capable ASR model with a focus on Chinese and dialect-rich scenarios. Compared to the previous version, Dolphin-CN-Dialect introduces substantial improvements in data processing, tokenization, training stability, and data sampling strategies. To address the challenges of highly imbalanced dialect data, we propose a temperature-based sampling strategy that effectively balances standard Mandarin and low-resource dialects, leading to significant gains in dialect recognition performance. In addition, we redesign the tokenizer to better align with linguistic characteristics, adopting character-level modeling for Chinese and subword modeling for English, while introducing extensible dialect tokens. Experimental results show that Dolphin-CN-Dialect achieves improvement in dialect recognition accuracy and CER reduction compared to Dolphin. Furthermore, Dolphin-CN-Dialect reaches competitive performance with recent SOTA open-source ASR models, while maintaining a significantly smaller model size. Dolphin-CN-Dialect supports both streaming and non-streaming inference, enabling a practical balance between latency and accuracy. It also provides flexible customization through hotword support and efficient deployment optimized for specialized hardware. These improvements make Dolphin-CN-Dialect a strong and practical solution for real-world multi-dialect ASR applications. |
| title | Dolphin-CN-Dialect: Where Chinese Dialects Matter |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2605.08961 |