Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.08795 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912030148001792 |
|---|---|
| author | Zhang, Huan Cheung, Vincent Nishioka, Hayato Dixon, Simon Furuya, Shinichi |
| author_facet | Zhang, Huan Cheung, Vincent Nishioka, Hayato Dixon, Simon Furuya, Shinichi |
| contents | Research in music understanding has extensively explored composition-level attributes such as key, genre, and instrumentation through advanced representations, leading to cross-modal applications using large language models. However, aspects of musical performance such as stylistic expression and technique remain underexplored, along with the potential of using large language models to enhance educational outcomes with customized feedback. To bridge this gap, we introduce LLaQo, a Large Language Query-based music coach that leverages audio language modeling to provide detailed and formative assessments of music performances. We also introduce instruction-tuned query-response datasets that cover a variety of performance dimensions from pitch accuracy to articulation, as well as contextual performance understanding (such as difficulty and performance techniques). Utilizing AudioMAE encoder and Vicuna-7b LLM backend, our model achieved state-of-the-art (SOTA) results in predicting teachers' performance ratings, as well as in identifying piece difficulty and playing techniques. Textual responses from LLaQo was moreover rated significantly higher compared to other baseline models in a user study using audio-text matching. Our proposed model can thus provide informative answers to open-ended questions related to musical performance from audio data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08795 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLaQo: Towards a Query-Based Coach in Expressive Music Performance Assessment Zhang, Huan Cheung, Vincent Nishioka, Hayato Dixon, Simon Furuya, Shinichi Audio and Speech Processing Multimedia Research in music understanding has extensively explored composition-level attributes such as key, genre, and instrumentation through advanced representations, leading to cross-modal applications using large language models. However, aspects of musical performance such as stylistic expression and technique remain underexplored, along with the potential of using large language models to enhance educational outcomes with customized feedback. To bridge this gap, we introduce LLaQo, a Large Language Query-based music coach that leverages audio language modeling to provide detailed and formative assessments of music performances. We also introduce instruction-tuned query-response datasets that cover a variety of performance dimensions from pitch accuracy to articulation, as well as contextual performance understanding (such as difficulty and performance techniques). Utilizing AudioMAE encoder and Vicuna-7b LLM backend, our model achieved state-of-the-art (SOTA) results in predicting teachers' performance ratings, as well as in identifying piece difficulty and playing techniques. Textual responses from LLaQo was moreover rated significantly higher compared to other baseline models in a user study using audio-text matching. Our proposed model can thus provide informative answers to open-ended questions related to musical performance from audio data. |
| title | LLaQo: Towards a Query-Based Coach in Expressive Music Performance Assessment |
| topic | Audio and Speech Processing Multimedia |
| url | https://arxiv.org/abs/2409.08795 |