What Are They Doing? Joint Audio-Speech Co-Reasoning
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_ | 1866909454256046080 |
|---|---|
| author | Wang, Yingzhi Mousavi, Pooneh Ploujnikov, Artem Ravanelli, Mirco |
| author_facet | Wang, Yingzhi Mousavi, Pooneh Ploujnikov, Artem Ravanelli, Mirco |
| contents | In audio and speech processing, tasks usually focus on either the audio or speech modality, even when both sounds and human speech are present in the same audio clip. Recent Auditory Large Language Models (ALLMs) have made it possible to process audio and speech simultaneously within a single model, leading to further considerations of joint audio-speech tasks.
In this paper, we establish a novel benchmark to investigate how well ALLMs can perform joint audio-speech processing. Specifically, we introduce Joint Audio-Speech Co-Reasoning (JASCO), a novel task that unifies audio and speech processing, strictly requiring co-reasoning across both modalities. We also release a scene-reasoning dataset called "What Are They Doing". Additionally, we provide deeper insights into the models' behaviors by analyzing their dependence on each modality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14526 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | What Are They Doing? Joint Audio-Speech Co-Reasoning Wang, Yingzhi Mousavi, Pooneh Ploujnikov, Artem Ravanelli, Mirco Sound Computation and Language Audio and Speech Processing In audio and speech processing, tasks usually focus on either the audio or speech modality, even when both sounds and human speech are present in the same audio clip. Recent Auditory Large Language Models (ALLMs) have made it possible to process audio and speech simultaneously within a single model, leading to further considerations of joint audio-speech tasks. In this paper, we establish a novel benchmark to investigate how well ALLMs can perform joint audio-speech processing. Specifically, we introduce Joint Audio-Speech Co-Reasoning (JASCO), a novel task that unifies audio and speech processing, strictly requiring co-reasoning across both modalities. We also release a scene-reasoning dataset called "What Are They Doing". Additionally, we provide deeper insights into the models' behaviors by analyzing their dependence on each modality. |
| title | What Are They Doing? Joint Audio-Speech Co-Reasoning |
| topic | Sound Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.14526 |