Saved in:
Bibliographic Details
Main Authors: Clemens, Michael, Marasović, Ana
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.06329
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915378928549888
author Clemens, Michael
Marasović, Ana
author_facet Clemens, Michael
Marasović, Ana
contents While AI presents significant potential for enhancing music mixing and mastering workflows, current research predominantly emphasizes end-to-end automation or generation, often overlooking the collaborative and instructional dimensions vital for co-creative processes. This gap leaves artists, particularly amateurs seeking to develop expertise, underserved. To bridge this, we introduce MixAssist, a novel audio-language dataset capturing the situated, multi-turn dialogue between expert and amateur music producers during collaborative mixing sessions. Comprising 431 audio-grounded conversational turns derived from 7 in-depth sessions involving 12 producers, MixAssist provides a unique resource for training and evaluating audio-language models that can comprehend and respond to the complexities of real-world music production dialogues. Our evaluations, including automated LLM-as-a-judge assessments and human expert comparisons, demonstrate that fine-tuning models such as Qwen-Audio on MixAssist can yield promising results, with Qwen significantly outperforming other tested models in generating helpful, contextually relevant mixing advice. By focusing on co-creative instruction grounded in audio context, MixAssist enables the development of intelligent AI assistants designed to support and augment the creative process in music mixing.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06329
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixing
Clemens, Michael
Marasović, Ana
Sound
Artificial Intelligence
Audio and Speech Processing
While AI presents significant potential for enhancing music mixing and mastering workflows, current research predominantly emphasizes end-to-end automation or generation, often overlooking the collaborative and instructional dimensions vital for co-creative processes. This gap leaves artists, particularly amateurs seeking to develop expertise, underserved. To bridge this, we introduce MixAssist, a novel audio-language dataset capturing the situated, multi-turn dialogue between expert and amateur music producers during collaborative mixing sessions. Comprising 431 audio-grounded conversational turns derived from 7 in-depth sessions involving 12 producers, MixAssist provides a unique resource for training and evaluating audio-language models that can comprehend and respond to the complexities of real-world music production dialogues. Our evaluations, including automated LLM-as-a-judge assessments and human expert comparisons, demonstrate that fine-tuning models such as Qwen-Audio on MixAssist can yield promising results, with Qwen significantly outperforming other tested models in generating helpful, contextually relevant mixing advice. By focusing on co-creative instruction grounded in audio context, MixAssist enables the development of intelligent AI assistants designed to support and augment the creative process in music mixing.
title MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixing
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2507.06329