Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects

Junghyun, Koo,; Martínez-Ramírez, Marco A.; Liao, Wei-Hsiang; Uhlich, Stefan; Kyogu, Lee,; Mitsufuji, Yuki

doi:10.1109/icassp49357.2023.10096458

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar findings have been observed in the music recording process regarding the use of reference songs. Ongoing research exploring the use of reference sound and reference songs for audio effects [37] and mixing style transfer [38,25] has shown promising success in capturing context and the user's intentions.…”

Section: Discussionmentioning

confidence: 99%

“…Through the analysis of audio signals and the application of predefined rules or machine learning models, automatic mixing algorithms aim to create balanced and cohesive mixes. Various approaches have been explored [17,19], including knowledge-engineered [20], machine learning-based [21], and deep learning-based methods [22][23][24][25]. Most of these systems take raw tracks or stems as input and generate a mix as output.…”

Section: Intelligent Music Production and Automatic Mixingmentioning

confidence: 99%

See 1 more Smart Citation

The Role of Communication and Reference Songs in the Mixing Process: Insights From Professional Mix Engineers

Sai Vanka,

Safi,

Rolland

et al. 2024

J. Audio Eng. Soc.

View full text Add to dashboard Cite

Effective music mixing requires technical and creative finesse, but clear communication with the client is crucial. The mixing engineer must grasp the client's expectations and preferences and collaborate to achieve the desired sound. The tacit agreement for the desired sound of the mix is established using guides like reference songs and demo mixes exchanged between the artist and the engineer. This paper presents the findings of a two-phased exploratory study aimed at understanding how professional mixing engineers interact with clients and use their feedback to guide the mixing process. For phase one, semistructured interviews were conducted with five mixing engineers with the aim of gathering insights about their communication strategies, creative processes, and decision-making criteria. Based on the inferences from these interviews, an online questionnaire was designed and administered to a larger group of 22 mixing engineers during the second phase. The results shed light on the importance of collaboration and intention in the mixing process and can inform the development of smart multitrack mixing systems. By highlighting the significance of these findings, this paper contributes to the research on the collaborative nature of music production and provides actionable recommendations for the design and implementation of innovative mixing tools.

show abstract

Section: Discussionmentioning

confidence: 99%