Work

A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models

Year: 2023

Type: conference-paper

Abstract: We propose a multi-dimensional structured state space (S4) approach to speech enhancement. To better capture the spectral dependencies across the frequency axis, we focus on modifying the multi-dimensional S4 layer with whitening transformation to build new small-footprint models that also achieve good performance. We explore several S4-based deep architectures in time (T) and time-frequency (TF) domains. The 2-D S4 layer can be considered a particular convolutional layer with an infinite receptive field although it utilizes fewer parameters than a conventional convolutional layer. Evaluated on the VoiceBank-DEMAND data set, when compared with the conventional U-net model based on convolutional layers, the proposed TF-domain S4-based model is 78.6% smaller in size, yet it still achieves competitive results with a PESQ score of 3.15 with data augmentation. By increasing the model size, we can even reach a PESQ score of 3.18.

Source: Interspeech (USB)

DOI: 10.21437/interspeech.2023-1084

Authors: Pin-Jui Ku, Chao-Han Huck Yang, Sabato Siniscalchi, Chin-Hui Lee

Institutions: Georgia Institute of Technology, Norwegian University of Science and Technology, Università degli Studi di Enna Kore

Language: English

Topic: Speech and Audio Processing

Subfield: Signal Processing

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4385822478

FWCI: 3.152

Cites: 43

Cited by: 15

Related to: 10