Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2408.10383 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911995768340480 |
|---|---|
| author | Lu, Zhenyu Sethi, Lakshay |
| author_facet | Lu, Zhenyu Sethi, Lakshay |
| contents | Previous methods for audio-image matching generally fall into one of two categories: pipeline models or End-to-End models. Pipeline models first transcribe speech and then encode the resulting text; End-to-End models encode speech directly. Generally, pipeline models outperform end-to-end models, but the intermediate transcription necessarily discards some potentially useful non-textual information. In addition to textual information, speech can convey details such as accent, mood, and and emphasis, which should be effectively captured in the encoded representation. In this paper, we investigate whether non-textual information, which is overlooked by pipeline-based models, can be leveraged to improve speech-image matching performance. We thoroughly analyze and compare End-to-End models, pipeline models, and our proposed dual-channel model for robust audio-image retrieval on a variety of datasets. Our approach achieves a substantial performance gain over the previous state-of-the-art by leveraging strong pretrained models, a prompting mechanism and a bifurcated design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10383 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BrewCLIP: A Bifurcated Representation Learning Framework for Audio-Visual Retrieval Lu, Zhenyu Sethi, Lakshay Sound Artificial Intelligence Audio and Speech Processing Previous methods for audio-image matching generally fall into one of two categories: pipeline models or End-to-End models. Pipeline models first transcribe speech and then encode the resulting text; End-to-End models encode speech directly. Generally, pipeline models outperform end-to-end models, but the intermediate transcription necessarily discards some potentially useful non-textual information. In addition to textual information, speech can convey details such as accent, mood, and and emphasis, which should be effectively captured in the encoded representation. In this paper, we investigate whether non-textual information, which is overlooked by pipeline-based models, can be leveraged to improve speech-image matching performance. We thoroughly analyze and compare End-to-End models, pipeline models, and our proposed dual-channel model for robust audio-image retrieval on a variety of datasets. Our approach achieves a substantial performance gain over the previous state-of-the-art by leveraging strong pretrained models, a prompting mechanism and a bifurcated design. |
| title | BrewCLIP: A Bifurcated Representation Learning Framework for Audio-Visual Retrieval |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.10383 |