PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zou, Dinghao, Gong, Yicheng, Li, Xiaokang, Cao, Xin, Lee, Sunbowen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911170975236096
author Zou, Dinghao
Gong, Yicheng
Li, Xiaokang
Cao, Xin
Lee, Sunbowen
author_facet Zou, Dinghao
Gong, Yicheng
Li, Xiaokang
Cao, Xin
Lee, Sunbowen
contents Multimodal music emotion analysis leverages both audio and MIDI modalities to enhance performance. While mainstream approaches focus on complex feature extraction networks, we propose that shortening the length of audio sequence features to mitigate redundancy, especially in contrast to MIDI's compact representation, may effectively boost task performance. To achieve this, we developed PoolingVQ by combining Vector Quantized Variational Autoencoder (VQVAE) with spatial pooling, which directly compresses audio feature sequences through codebook-guided local aggregation to reduce redundancy, then devised a two-stage co-attention approach to fuse audio and MIDI information. Experimental results on the public datasets EMOPIA and VGMIDI demonstrate that our multimodal framework achieves state-of-the-art performance, with PoolingVQ yielding effective improvement. Our proposed metho's code is available at Anonymous GitHub
format Preprint
id arxiv_https___arxiv_org_abs_2509_11976
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis
Zou, Dinghao
Gong, Yicheng
Li, Xiaokang
Cao, Xin
Lee, Sunbowen
Sound
Audio and Speech Processing
Multimodal music emotion analysis leverages both audio and MIDI modalities to enhance performance. While mainstream approaches focus on complex feature extraction networks, we propose that shortening the length of audio sequence features to mitigate redundancy, especially in contrast to MIDI's compact representation, may effectively boost task performance. To achieve this, we developed PoolingVQ by combining Vector Quantized Variational Autoencoder (VQVAE) with spatial pooling, which directly compresses audio feature sequences through codebook-guided local aggregation to reduce redundancy, then devised a two-stage co-attention approach to fuse audio and MIDI information. Experimental results on the public datasets EMOPIA and VGMIDI demonstrate that our multimodal framework achieves state-of-the-art performance, with PoolingVQ yielding effective improvement. Our proposed metho's code is available at Anonymous GitHub
title PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2509.11976