Selected work

Representative Papers

From Textural Counterpoint to Feature Encoding: A Multi-Dimensional Machine Representation Study of Haydn's "The Lark" Integrating Electroacoustic Analysis

Jul 07, 2026

This study addresses the challenge that existing deep music generation models struggle to perceive the distinct roles of individual voices in polyphonic music. Focusing on Haydn’s “Lark” Quartet, the work integrates auditory analysis, electroacoustic measurement, and machine-based representational reconstruction to establish a mapping from classical contrapuntal structures to computable AI features. It introduces a novel “role-aware encoding” mechanism that abandons conventional quantized grids in favor of event-based timestamps to capture micro-temporal nuances, while transforming acoustic features into phenomenological anchors informed by aesthetic intuition. By combining DAW-based spectral and dynamic analysis, event modeling, and symbolic generation techniques, the research achieves a coherent loop linking classical music analysis, electronic representation, and AI-driven composition, thereby laying a theoretical foundation for human–AI collaborative systems endowed with social awareness and intersubjective musical understanding.

0 citationsRead paper

LK Jam: System Architecture and Implementation of a Real-Time Human-AI Interactive Music Generation System using Role-Aware GRU

Jun 18, 2026

This work addresses critical limitations in current AI music generation systems—namely high latency, unidirectional output, and insufficient role awareness and micro-temporal responsiveness during real-time human–AI improvisational interaction. To overcome these challenges, the authors propose a lightweight, role-aware GRU architecture that unifies modeling of time shifts, harmony, and interaction roles through a multidimensional sparse event stream. They introduce an O(1)-complexity, allocation-free autoregressive decoding mechanism and a three-stage progressive training strategy. Implemented in C++ with JUCE, the system employs lock-free multithreading and integrates the RTNeural inference engine, leveraging compile-time network topology freezing and zero-memory-allocation techniques. Deployed as a DAW plugin, it achieves stable, low-latency human–AI co-performance for the first time, ensuring musical coherence and interactive role dynamics while meeting stringent real-time constraints, thereby establishing a robust and deployable paradigm for AI co-performers.

0 citationsRead paper

ChladniSonify: A Visual-Acoustic Mapping Method for Chladni Patterns in New Media Art Creation

May 10, 2026

This study addresses the high entry barrier, lack of real-time interactivity, and uncontrollable mapping inherent in Chladni pattern–based audiovisual systems in new media art. Leveraging Kirchhoff–Love plate theory, the authors construct an ANSYS-calibrated simulation dataset and propose a lightweight CNN architecture integrated with a CBAM attention mechanism to enable high-precision, low-latency nodal line classification. Building upon this model, they implement an end-to-end real-time mapping system in Python and Max/MSP that, for the first time, achieves controllable, zero-bias, and highly accurate real-time mapping from Chladni patterns to audio frequencies. The system attains a classification accuracy of 99.33%, with an inference latency of 7.03 ms and end-to-end latency under 50 ms, fulfilling real-time interaction requirements and offering a reproducible engineering prototype for new media art applications.

0 citationsRead paper

Recent publications

Latest Papers

From Textural Counterpoint to Feature Encoding: A Multi-Dimensional Machine Representation Study of Haydn's "The Lark" Integrating Electroacoustic Analysis

Jul 07, 2026

This study addresses the challenge that existing deep music generation models struggle to perceive the distinct roles of individual voices in polyphonic music. Focusing on Haydn’s “Lark” Quartet, the work integrates auditory analysis, electroacoustic measurement, and machine-based representational reconstruction to establish a mapping from classical contrapuntal structures to computable AI features. It introduces a novel “role-aware encoding” mechanism that abandons conventional quantized grids in favor of event-based timestamps to capture micro-temporal nuances, while transforming acoustic features into phenomenological anchors informed by aesthetic intuition. By combining DAW-based spectral and dynamic analysis, event modeling, and symbolic generation techniques, the research achieves a coherent loop linking classical music analysis, electronic representation, and AI-driven composition, thereby laying a theoretical foundation for human–AI collaborative systems endowed with social awareness and intersubjective musical understanding.

0 citationsRead paper

LK Jam: System Architecture and Implementation of a Real-Time Human-AI Interactive Music Generation System using Role-Aware GRU

Jun 18, 2026

This work addresses critical limitations in current AI music generation systems—namely high latency, unidirectional output, and insufficient role awareness and micro-temporal responsiveness during real-time human–AI improvisational interaction. To overcome these challenges, the authors propose a lightweight, role-aware GRU architecture that unifies modeling of time shifts, harmony, and interaction roles through a multidimensional sparse event stream. They introduce an O(1)-complexity, allocation-free autoregressive decoding mechanism and a three-stage progressive training strategy. Implemented in C++ with JUCE, the system employs lock-free multithreading and integrates the RTNeural inference engine, leveraging compile-time network topology freezing and zero-memory-allocation techniques. Deployed as a DAW plugin, it achieves stable, low-latency human–AI co-performance for the first time, ensuring musical coherence and interactive role dynamics while meeting stringent real-time constraints, thereby establishing a robust and deployable paradigm for AI co-performers.

0 citationsRead paper

ChladniSonify: A Visual-Acoustic Mapping Method for Chladni Patterns in New Media Art Creation

May 10, 2026

This study addresses the high entry barrier, lack of real-time interactivity, and uncontrollable mapping inherent in Chladni pattern–based audiovisual systems in new media art. Leveraging Kirchhoff–Love plate theory, the authors construct an ANSYS-calibrated simulation dataset and propose a lightweight CNN architecture integrated with a CBAM attention mechanism to enable high-precision, low-latency nodal line classification. Building upon this model, they implement an end-to-end real-time mapping system in Python and Max/MSP that, for the first time, achieves controllable, zero-bias, and highly accurate real-time mapping from Chladni patterns to audio frequencies. The system attains a classification accuracy of 99.33%, with an inference latency of 7.03 ms and end-to-end latency under 50 ms, fulfilling real-time interaction requirements and offering a reproducible engineering prototype for new media art applications.

0 citationsRead paper