Cacophony: An Improved Contrastive Audio-Text Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912050835357696 |
|---|---|
| author | Zhu, Ge Darefsky, Jordan Duan, Zhiyao |
| author_facet | Zhu, Ge Darefsky, Jordan Duan, Zhiyao |
| contents | Despite recent advancements, audio-text models still lag behind their image-text counterparts in scale and performance. In this paper, we propose to improve both the data scale and the training procedure of audio-text contrastive models. Specifically, we craft a large-scale audio-text dataset containing 13,000 hours of text-labeled audio, using pretrained language models to process noisy text descriptions and automatic captioning to obtain text descriptions for unlabeled audio samples. We first train on audio-only data with a masked autoencoder (MAE) objective, which allows us to benefit from the scalability of unlabeled audio datasets. We then train a contrastive model with an auxiliary captioning objective with the audio encoder initialized from the MAE model. Our final model, which we name Cacophony, achieves state-of-the-art performance on audio-text retrieval tasks, and exhibits competitive results on the HEAR benchmark and other downstream tasks such as zero-shot classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06986 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cacophony: An Improved Contrastive Audio-Text Model Zhu, Ge Darefsky, Jordan Duan, Zhiyao Sound Audio and Speech Processing Despite recent advancements, audio-text models still lag behind their image-text counterparts in scale and performance. In this paper, we propose to improve both the data scale and the training procedure of audio-text contrastive models. Specifically, we craft a large-scale audio-text dataset containing 13,000 hours of text-labeled audio, using pretrained language models to process noisy text descriptions and automatic captioning to obtain text descriptions for unlabeled audio samples. We first train on audio-only data with a masked autoencoder (MAE) objective, which allows us to benefit from the scalability of unlabeled audio datasets. We then train a contrastive model with an auxiliary captioning objective with the audio encoder initialized from the MAE model. Our final model, which we name Cacophony, achieves state-of-the-art performance on audio-text retrieval tasks, and exhibits competitive results on the HEAR benchmark and other downstream tasks such as zero-shot classification. |
| title | Cacophony: An Improved Contrastive Audio-Text Model |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.06986 |