Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chang, Andrew, Li, Yike, Roman, Iran R., Poeppel, David
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.23509
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918126961033216
author Chang, Andrew
Li, Yike
Roman, Iran R.
Poeppel, David
author_facet Chang, Andrew
Li, Yike
Roman, Iran R.
Poeppel, David
contents Audio DNNs have demonstrated impressive performance on various machine listening tasks; however, most of their representations are computationally costly and uninterpretable, leaving room for optimization. Here, we propose a novel approach centered on spectrotemporal modulation (STM) features, a signal processing method that mimics the neurophysiological representation in the human auditory cortex. The classification performance of our STM-based model, without any pretraining, is comparable to that of pretrained audio DNNs across diverse naturalistic speech, music, and environmental sounds, which are essential categories for both human cognition and machine perception. These results show that STM is an efficient and interpretable feature representation for audio classification, advancing the development of machine listening and unlocking exciting new possibilities for basic understanding of speech and auditory sciences, as well as developing audio BCI and cognitive computing.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23509
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds
Chang, Andrew
Li, Yike
Roman, Iran R.
Poeppel, David
Sound
Machine Learning
Audio and Speech Processing
Audio DNNs have demonstrated impressive performance on various machine listening tasks; however, most of their representations are computationally costly and uninterpretable, leaving room for optimization. Here, we propose a novel approach centered on spectrotemporal modulation (STM) features, a signal processing method that mimics the neurophysiological representation in the human auditory cortex. The classification performance of our STM-based model, without any pretraining, is comparable to that of pretrained audio DNNs across diverse naturalistic speech, music, and environmental sounds, which are essential categories for both human cognition and machine perception. These results show that STM is an efficient and interpretable feature representation for audio classification, advancing the development of machine listening and unlocking exciting new possibilities for basic understanding of speech and auditory sciences, as well as developing audio BCI and cognitive computing.
title Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2505.23509