Pith. sign in

REVIEW 2 cited by

Towards Audio Codec-based Speech Separation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

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

classification cs.SDcs.LGeess.AS
keywords taskaudiocompressionseparationspeechcodec-basedcodecformerhigh
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

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

    cs.SD 2025-09 unverdicted novelty 6.0 of 10

    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...

  2. From Continuous to Discrete: Cross-Domain Collaborative General Speech Enhancement via Hierarchical Language Models

    cs.SD 2025-07 conditional novelty 5.0 of 10

    OmniGSE combines a continuous feature enhancement stage with a RootLM/BranchLM token generation stage to improve general speech enhancement on mixed distortions.

Pith tools