Towards Controllable & Interactive Generative AI for Voice

Recorded 음악 산업 동향 및 미래 음악 경험

Introduction on Researches in Gaudio

Estimating Group Fairness in Speech Recognition

Finding Tori: Self-supervised Learning for Analysing Korean Folk Song

LP-MusicCaps: LLM-Based Pseudo Music Captioning

Crossover from Theory to Real-World: Navigating the Development of Robust Sound Event Detection Algorithms

AudAi 기업 소개

ComMU: Dataset for Combinatorial Music Generation (NeurIPS 2022)

Neural Fourier Shift for Binaural Speech Rendering

All-In-One Metrical and Functional Music Structure Analysis

Introducing Music and Brain Lab / Exploring the inter-instrument interaction of independent microtiming deviations patterns on the groove experience

Take It or Make It: A Neural Synthesizer for Instrument Timbre Cloning and Text-to-Instrument Generation

Pianist Visualization with Multimodal Piano Dataset