2025/10/16 by Qixin Deng, Bryan Pardo, Deng, Qixin +3
Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music Technology and Sound Studies #Music and Audio Processing #Neuroscience and Music Perception #Sound (cs.SD) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2510.14249
openalex publication_date 2025/10/16 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28
Understanding and modeling the relationship between language and sound is critical for applications such as music information retrieval,text-guided music generation, and audio captioning. Central to these tasks is the use of joint language-audio embedding spaces, which map textual descriptions and auditory content into a shared embedding space. While multimodal embedding models such as MS-CLAP, LAION-CLAP, and MuQ-MuLan have shown strong performance in aligning language and audio, their correspondence to human perception of timbre, a multifaceted attribute encompassing qualities such as brightness, roughness, and warmth, remains underexplored. In this paper, we evaluate the above three joint language-audio embedding models on their ability to capture perceptual dimensions of timbre. Our findings show that LAION-CLAP consistently provides the most reliable alignment with human-perceived timbre semantics across both instrumental sounds and audio effects.