pith. sign in

arxiv: 2406.12434 · v2 · pith:3EL5PL6O · submitted 2024-06-18 · cs.SD · cs.LG· eess.AS

Towards Audio Codec-based Speech Separation

pith:3EL5PL6Oopen to challenge →

classification cs.SD cs.LGeess.AS
keywords taskaudiocompressionseparationspeechcodec-basedcodecformerhigh
0
0 comments X
read the original abstract

Recent improvements in neural audio codec (NAC) models have generated interest in adopting pre-trained codecs for a variety of speech processing applications to take advantage of the efficiencies gained from high compression, but these have yet been applied to the speech separation (SS) task. SS can benefit from high compression because the compute required for traditional SS models makes them impractical for many edge computing use cases. However, SS is a waveform-masking task where compression tends to introduce distortions that severely impact performance. Here we propose a novel task of Audio Codec-based SS, where SS is performed within the embedding space of a NAC, and propose a new model, Codecformer, to address this task. At inference, Codecformer achieves a 52x reduction in MAC while producing separation performance comparable to a cloud deployment of Sepformer. This method charts a new direction for performing efficient SS in practical scenarios.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents

    cs.SD 2025-09 unverdicted novelty 6.0

    CodecSep performs prompt-driven universal sound separation directly in neural audio codec latents by combining a frozen DAC backbone with a lightweight FiLM-conditioned Transformer masker driven by CLAP embeddings, yi...