Sound Separation and Classification with Object and Semantic Guidance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwon, Younghoo, Choi, Jung-Woo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916957752655872
author Kwon, Younghoo
Choi, Jung-Woo
author_facet Kwon, Younghoo
Choi, Jung-Woo
contents The spatial semantic segmentation task focuses on separating and classifying sound objects from multichannel signals. To achieve two different goals, conventional methods fine-tune a large classification model cascaded with the separation model and inject classified labels as separation clues for the next iteration step. However, such integration is not ideal, in that fine-tuning over a smaller dataset loses the diversity of large classification models, features from the source separation model are different from the inputs of the pretrained classifier, and injected one-hot class labels lack semantic depth, often leading to error propagation. To resolve these issues, we propose a Dual-Path Classifier (DPC) architecture that combines object features from a source separation model with semantic representations acquired from a pretrained classification model without fine-tuning. We also introduce a Semantic Clue Encoder (SCE) that enriches the semantic depth of injected clues. Our system achieves a state-of-the-art 11.19 dB CA-SDRi and enhanced semantic fidelity on the DCASE 2025 task4 evaluation set, surpassing the top-rank performance of 11.00 dB. These results highlight the effectiveness of integrating separator-derived features and rich semantic clues.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15899
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sound Separation and Classification with Object and Semantic Guidance
Kwon, Younghoo
Choi, Jung-Woo
Audio and Speech Processing
The spatial semantic segmentation task focuses on separating and classifying sound objects from multichannel signals. To achieve two different goals, conventional methods fine-tune a large classification model cascaded with the separation model and inject classified labels as separation clues for the next iteration step. However, such integration is not ideal, in that fine-tuning over a smaller dataset loses the diversity of large classification models, features from the source separation model are different from the inputs of the pretrained classifier, and injected one-hot class labels lack semantic depth, often leading to error propagation. To resolve these issues, we propose a Dual-Path Classifier (DPC) architecture that combines object features from a source separation model with semantic representations acquired from a pretrained classification model without fine-tuning. We also introduce a Semantic Clue Encoder (SCE) that enriches the semantic depth of injected clues. Our system achieves a state-of-the-art 11.19 dB CA-SDRi and enhanced semantic fidelity on the DCASE 2025 task4 evaluation set, surpassing the top-rank performance of 11.00 dB. These results highlight the effectiveness of integrating separator-derived features and rich semantic clues.
title Sound Separation and Classification with Object and Semantic Guidance
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.15899