M2D-CLAP: Exploring General-purpose Audio-Language Representations Beyond CLAP
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_ | 1866912586777231360 |
|---|---|
| author | Niizumi, Daisuke Takeuchi, Daiki Yasuda, Masahiro Nguyen, Binh Thien Ohishi, Yasunori Harada, Noboru |
| author_facet | Niizumi, Daisuke Takeuchi, Daiki Yasuda, Masahiro Nguyen, Binh Thien Ohishi, Yasunori Harada, Noboru |
| contents | Contrastive language-audio pre-training (CLAP), which learns audio-language representations by aligning audio and text in a common feature space, has become popular for solving audio tasks. However, CLAP's audio features lack generalizability, whereas self-supervised learning (SSL) models offer general-purpose features that perform well across diverse audio tasks. We aim to develop a broadly applicable audio representation and hypothesize that a model that learns both general audio and CLAP features should achieve our goal, which we call a general-purpose audio-language representation. To implement our hypothesis, we propose M2D-CLAP, the first approach to jointly learn effective general audio and CLAP features. It extends an SSL masked modeling duo (M2D) by incorporating CLAP and utilizes LLM-based sentence embeddings. The training process consists of multiple stages. In the first stage, generalizable audio features are pre-trained via a multitask objective combining M2D and CLAP, with CLAP leveraging LLM-based semantic embeddings to distill semantic knowledge into them. In the following stages, CLAP features are pre-trained and refined with guidance from the learned audio features. Experiments demonstrated that M2D-CLAP learns high-performing general audio features (e.g., AudioSet mAP of 49.0, SOTA results in music tasks) and CLAP features, thereby enabling a general-purpose audio-language representation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22104 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | M2D-CLAP: Exploring General-purpose Audio-Language Representations Beyond CLAP Niizumi, Daisuke Takeuchi, Daiki Yasuda, Masahiro Nguyen, Binh Thien Ohishi, Yasunori Harada, Noboru Audio and Speech Processing 68T07 I.2.4 Contrastive language-audio pre-training (CLAP), which learns audio-language representations by aligning audio and text in a common feature space, has become popular for solving audio tasks. However, CLAP's audio features lack generalizability, whereas self-supervised learning (SSL) models offer general-purpose features that perform well across diverse audio tasks. We aim to develop a broadly applicable audio representation and hypothesize that a model that learns both general audio and CLAP features should achieve our goal, which we call a general-purpose audio-language representation. To implement our hypothesis, we propose M2D-CLAP, the first approach to jointly learn effective general audio and CLAP features. It extends an SSL masked modeling duo (M2D) by incorporating CLAP and utilizes LLM-based sentence embeddings. The training process consists of multiple stages. In the first stage, generalizable audio features are pre-trained via a multitask objective combining M2D and CLAP, with CLAP leveraging LLM-based semantic embeddings to distill semantic knowledge into them. In the following stages, CLAP features are pre-trained and refined with guidance from the learned audio features. Experiments demonstrated that M2D-CLAP learns high-performing general audio features (e.g., AudioSet mAP of 49.0, SOTA results in music tasks) and CLAP features, thereby enabling a general-purpose audio-language representation. |
| title | M2D-CLAP: Exploring General-purpose Audio-Language Representations Beyond CLAP |
| topic | Audio and Speech Processing 68T07 I.2.4 |
| url | https://arxiv.org/abs/2503.22104 |