A lightweight and robust method for blind wideband-to-fullband extension of speech

TL;DR

This paper introduces a lightweight, robust method for extending the bandwidth of wideband speech signals, significantly improving quality in resource-constrained environments without increasing complexity.

Contribution

A novel, low-complexity bandwidth extension model inspired by classical speech coding methods, compatible with existing codecs and capable of enhancing speech quality at low bitrates.

Findings

Model has ~370K parameters and ~140 MFLOPS complexity.

Significantly improves speech quality from 6 to 12 kb/s in tests.

Achieves quality comparable to higher-bitrate standards like EVS and Opus at lower bitrates.

Abstract

Reducing the bandwidth of speech is common practice in resource constrained environments like low-bandwidth speech transmission or low-complexity vocoding. We propose a lightweight and robust method for extending the bandwidth of wideband speech signals that is inspired by classical methods developed in the speech coding context. The resulting model has just ~370K parameters and a complexity of ~140 MFLOPS (or ~70 MMACS). With a frame size of 10 ms and a lookahead of only 0.27 ms, the model is well-suited for use with common wideband speech codecs. We evaluate the model's robustness by pairing it with the Opus SILK speech codec (1.5 release) and verify in a P.808 DCR listening test that it significantly improves quality from 6 to 12 kb/s. We also demonstrate that Opus 1.5 together with the proposed bandwidth extension at 9 kb/s meets the quality of 3GPP EVS at 9.6 kb/s and that of Opus 1.4 at 18 kb/s showing that the blind bandwidth extension can meet the quality of classical guided bandwidth extensions thus providing a way for backward-compatible quality improvement.