Audio Dialogues: Dialogues dataset for audio and music understanding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913310191910912 |
|---|---|
| author | Goel, Arushi Kong, Zhifeng Valle, Rafael Catanzaro, Bryan |
| author_facet | Goel, Arushi Kong, Zhifeng Valle, Rafael Catanzaro, Bryan |
| contents | Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To address this gap, we introduce Audio Dialogues: a multi-turn dialogue dataset containing 163.8k samples for general audio sounds and music. In addition to dialogues, Audio Dialogues also has question-answer pairs to understand and compare multiple input audios together. Audio Dialogues leverages a prompting-based approach and caption annotations from existing datasets to generate multi-turn dialogues using a Large Language Model (LLM). We evaluate existing audio-augmented large language models on our proposed dataset to demonstrate the complexity and applicability of Audio Dialogues. Our code for generating the dataset will be made publicly available. Detailed prompts and generated dialogues can be found on the demo website https://audiodialogues.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07616 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Audio Dialogues: Dialogues dataset for audio and music understanding Goel, Arushi Kong, Zhifeng Valle, Rafael Catanzaro, Bryan Computation and Language Sound Audio and Speech Processing Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To address this gap, we introduce Audio Dialogues: a multi-turn dialogue dataset containing 163.8k samples for general audio sounds and music. In addition to dialogues, Audio Dialogues also has question-answer pairs to understand and compare multiple input audios together. Audio Dialogues leverages a prompting-based approach and caption annotations from existing datasets to generate multi-turn dialogues using a Large Language Model (LLM). We evaluate existing audio-augmented large language models on our proposed dataset to demonstrate the complexity and applicability of Audio Dialogues. Our code for generating the dataset will be made publicly available. Detailed prompts and generated dialogues can be found on the demo website https://audiodialogues.github.io/. |
| title | Audio Dialogues: Dialogues dataset for audio and music understanding |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2404.07616 |