Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine
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_ | 1866916881783324672 |
|---|---|
| author | Kuznetsova, Anastasia Jang, Inseon Lim, Wootaek Kim, Minje |
| author_facet | Kuznetsova, Anastasia Jang, Inseon Lim, Wootaek Kim, Minje |
| contents | Neural audio codecs, leveraging quantization algorithms, have significantly impacted various speech/audio tasks. While high-fidelity reconstruction is paramount for human perception, audio coding for machines (ACoM) prioritizes efficient compression and downstream task performance, disregarding perceptual nuances. This work introduces an efficient ACoM method that can compress and quantize any chosen intermediate feature representation of an already trained speech/audio downstream model. Our approach employs task-specific loss guidance alongside residual vector quantization (RVQ) losses, providing ultra-low bitrates (i.e., less than 200 bps) with a minimal loss of the downstream model performance. The resulting tokenizer is adaptable to various bitrates and model sizes for flexible deployment. Evaluated on automatic speech recognition and audio classification, our method demonstrates its efficacy and potential for broader task and architectural applicability through appropriate regularization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12701 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine Kuznetsova, Anastasia Jang, Inseon Lim, Wootaek Kim, Minje Sound Artificial Intelligence Audio and Speech Processing Neural audio codecs, leveraging quantization algorithms, have significantly impacted various speech/audio tasks. While high-fidelity reconstruction is paramount for human perception, audio coding for machines (ACoM) prioritizes efficient compression and downstream task performance, disregarding perceptual nuances. This work introduces an efficient ACoM method that can compress and quantize any chosen intermediate feature representation of an already trained speech/audio downstream model. Our approach employs task-specific loss guidance alongside residual vector quantization (RVQ) losses, providing ultra-low bitrates (i.e., less than 200 bps) with a minimal loss of the downstream model performance. The resulting tokenizer is adaptable to various bitrates and model sizes for flexible deployment. Evaluated on automatic speech recognition and audio classification, our method demonstrates its efficacy and potential for broader task and architectural applicability through appropriate regularization. |
| title | Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.12701 |