Contrastive Representation Learning for Acoustic Parameter Estimation

2023/02/22 by Götz, Philipp, Tuna, Cagdas, Walther, Andreas +1 · 1 citation
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2302.11205

Abstract

A study is presented in which a contrastive learning approach is used to extract low-dimensional representations of the acoustic environment from single-channel, reverberant speech signals. Convolution of room impulse responses (RIRs) with anechoic source signals is leveraged as a data augmentation technique that offers considerable flexibility in the design of the upstream task. We evaluate the embeddings across three different downstream tasks, which include the regression of acoustic parameters reverberation time RT60 and clarity index C50, and the classification into small and large rooms. We demonstrate that the learned representations generalize well to unseen data and perform similarly to a fully-supervised baseline.

Cited by

• Loss functions incorporating auditory spatial perception in deep learning -- a review

Related

• RevRIR: Joint Reverberant Speech and Room Impulse Response Embedding using Contrastive Learning with Application to Room Shape Classification
• Blind Acoustic Parameter Estimation Through Task-Agnostic Embeddings Using Latent Approximations
• Joint Blind Room Acoustic Characterization From Speech And Music Signals Using Convolutional Recurrent Neural Networks
• Filtered Noise Shaping for Time Domain Room Impulse Response Estimation From Reverberant Speech
• AV-RIR: Audio-Visual Room Impulse Response Estimation