Dual-Branch Codec With Orthogonality Constraint and Knowledge Distillation for Noisy Environment

Audio codecs, by discretizing continuous audio signals into finite token sets, achieve high-quality reconstruction at low bitrates in clean environments. However, real-world speech often deviates from ideal conditions, particularly in noisy environments with low signal-to-noise ratios (SNRs), limiti...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters Vol. 32; pp. 3017 - 3021
Main Authors: Han, Yi, Chen, Hang, Liu, Lijuan, Du, Jun
Format: Journal Article
Language:English
Published: New York IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Audio codec
Audio signals
Bit rate
Codec
Codecs
Constraints
Decoding
Noise
Noise levels
Noise measurement
Noise reduction
Orthogonality
Quantization (signal)
residual vector quantization
Signal reconstruction
Signal to noise ratio
Speech
Speech coding
Speech enhancement
Training
ISSN:1070-9908, 1558-2361
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Audio codecs, by discretizing continuous audio signals into finite token sets, achieve high-quality reconstruction at low bitrates in clean environments. However, real-world speech often deviates from ideal conditions, particularly in noisy environments with low signal-to-noise ratios (SNRs), limiting the performance of existing codecs in restoring clean audio from noisy inputs. To address this challenge, this paper introduces a Dual-Branch Codec (DB-Codec). Leveraging the hierarchical decomposition capability of residual vector quantization (RVQ), we separate noise and speech into codebooks at different layers through dual-branch reconstruction and orthogonality constraints between noise and speech features. DB-Codec integrates enhancement and synthesis into a unified model, enabling flexible control over noise suppression or signal recovery at equivalent compression rates to conventional codecs. Experiments demonstrate that our DB-Codec achieve an average improvement of 0.83 in PESQ and 9.16 in STOI compared to traditional codecs under low SNR conditions.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2025.3591726