DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913549810401280 |
|---|---|
| author | Xin, Yifei Cheng, Xuxin Zhu, Zhihong Yang, Xusheng Zou, Yuexian |
| author_facet | Xin, Yifei Cheng, Xuxin Zhu, Zhihong Yang, Xusheng Zou, Yuexian |
| contents | Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data distribution p(query), leading to difficulties in discerning out-of-distribution data. In this work, we attempt to tackle this constraint through a generative perspective and model the relationship between audio and text as their joint probability p(candidates,query). To this end, we present a diffusion-based ATR framework (DiffATR), which models ATR as an iterative procedure that progressively generates joint distribution from noise. Throughout its training phase, DiffATR is optimized from both generative and discriminative viewpoints: the generator is refined through a generation loss, while the feature extractor benefits from a contrastive loss, thus combining the merits of both methodologies. Experiments on the AudioCaps and Clotho datasets with superior performances, verify the effectiveness of our approach. Notably, without any alterations, our DiffATR consistently exhibits strong performance in out-of-domain retrieval settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10025 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval Xin, Yifei Cheng, Xuxin Zhu, Zhihong Yang, Xusheng Zou, Yuexian Sound Information Retrieval Audio and Speech Processing Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data distribution p(query), leading to difficulties in discerning out-of-distribution data. In this work, we attempt to tackle this constraint through a generative perspective and model the relationship between audio and text as their joint probability p(candidates,query). To this end, we present a diffusion-based ATR framework (DiffATR), which models ATR as an iterative procedure that progressively generates joint distribution from noise. Throughout its training phase, DiffATR is optimized from both generative and discriminative viewpoints: the generator is refined through a generation loss, while the feature extractor benefits from a contrastive loss, thus combining the merits of both methodologies. Experiments on the AudioCaps and Clotho datasets with superior performances, verify the effectiveness of our approach. Notably, without any alterations, our DiffATR consistently exhibits strong performance in out-of-domain retrieval settings. |
| title | DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval |
| topic | Sound Information Retrieval Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.10025 |