Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917092110893056 |
|---|---|
| author | Huo, Mingyue Tseng, Wei-Cheng Shao, Yiwen Zhang, Hao Yu, Dong |
| author_facet | Huo, Mingyue Tseng, Wei-Cheng Shao, Yiwen Zhang, Hao Yu, Dong |
| contents | Human voice encodes both identity and paralinguistic cues, yet encoders in large audio-language models (LALMs) rarely balance both aspects. In this work, we present a study toward building a general-purpose voice encoder that captures nuanced voice cues. Through a comprehensive evaluation, we find that multi-task training yields the most balanced representations, whereas contrastive language-audio pretraining (CLAP) primarily improves retrieval without enhancing paralinguistic understanding. Our final encoder, Auden-Voice, also demonstrates strong performance when integrated with LLMs. The code and training recipes will be released with the audio understanding toolkit Auden. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding Huo, Mingyue Tseng, Wei-Cheng Shao, Yiwen Zhang, Hao Yu, Dong Audio and Speech Processing Sound Human voice encodes both identity and paralinguistic cues, yet encoders in large audio-language models (LALMs) rarely balance both aspects. In this work, we present a study toward building a general-purpose voice encoder that captures nuanced voice cues. Through a comprehensive evaluation, we find that multi-task training yields the most balanced representations, whereas contrastive language-audio pretraining (CLAP) primarily improves retrieval without enhancing paralinguistic understanding. Our final encoder, Auden-Voice, also demonstrates strong performance when integrated with LLMs. The code and training recipes will be released with the audio understanding toolkit Auden. |
| title | Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2511.15145 |