Pith Number

pith:6OOMKLUU

pith:2026:6OOMKLUURZGQ3YZ2QUHCWHTRUU

not attested not anchored not stored refs resolved

Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation

Hyung-Min Park, Ui-Hyeop Shin

SR-CorrNet separates speech by splitting coarse separation into the encoder and progressive reconstruction into a shared-weight decoder that interacts across speakers.

arxiv:2603.29097 v2 · 2026-03-31 · eess.AS · cs.SD

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6OOMKLUURZGQ3YZ2QUHCWHTRUU}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Experimental results on WSJ0-{2,3,4,5}Mix, WHAMR!, and LibriCSS demonstrate consistent improvements across anechoic, noisy-reverberant, and real-recorded conditions in both single- and multi-channel settings, highlighting the effectiveness of TF-domain SepRe with correlation-based filter estimation for speech separation.

C2weakest assumption

That the proposed asymmetric encoder-decoder with SepRe strategy and cross-speaker interaction in the decoder will reliably avoid information bottlenecks and yield better speaker discriminability than late-split architectures under adverse conditions, without the gains depending on dataset-specific tuning or post-hoc architectural choices.

C3one line summary

SR-CorrNet introduces an asymmetric TF-domain architecture with separation-reconstruction strategy and correlation-to-filter estimation that yields consistent gains on WSJ0-Mix, WHAMR!, and LibriCSS under anechoic, noisy-reverberant, and real-recorded conditions.

References

79 extracted · 79 resolved · 0 Pith anchors

[1] TasNet: time-domain audio separation network for real-time, single-channel speech separation, 2018

[2] Conv-TasNet: Surpassing ideal time–frequency magnitude mask- ing for speech separation, 2019

[3] Dual-Path RNN: Efficient long sequence modeling for time-domain single-channel speech separation, 2020

[4] Attention is all you need in speech separation, 2021

[5] TFPSNet: Time-frequency domain path scanning network for speech separation, 2022

Receipt and verification

First computed	2026-05-17T23:39:04.352814Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f39cc52e948e4d0de33a850e2b1e71a52b436e20d857644a469d44aa349a26ca

Aliases

arxiv: 2603.29097 · arxiv_version: 2603.29097v2 · doi: 10.48550/arxiv.2603.29097 · pith_short_12: 6OOMKLUURZGQ · pith_short_16: 6OOMKLUURZGQ3YZ2 · pith_short_8: 6OOMKLUU

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: f39cc52e948e4d0de33a850e2b1e71a52b436e20d857644a469d44aa349a26ca

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "996cdfdeaeda70f5ab6d67852da8c007b858dcbd85d0751264d53581d0532087",
    "cross_cats_sorted": [
      "cs.SD"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "eess.AS",
    "submitted_at": "2026-03-31T00:37:15Z",
    "title_canon_sha256": "95ddab5de4dad70024e0d67343ae4af64b98351d04ad3b72b3bb7700c506e4be"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.29097",
    "kind": "arxiv",
    "version": 2
  }
}