pith. sign in
Pith Number

pith:7SMNMVJC

pith:2026:7SMNMVJCZIILXIOGGZW3752UKW
not attested not anchored not stored refs pending

Unmixing The Crowd: Learning Persistent Speaker Representations from Mixture-Derived Multi-Speaker Embeddings

Dhruv Jain, Hao-Wen Dong, Meysam Asgari, Sidharth Sidharth

A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording.

arxiv:2604.03219 v2 · 2026-04-03 · eess.AS · cs.SD

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{7SMNMVJCZIILXIOGGZW3752UKW}

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

Our model maps a noisy mixture directly to a small set of candidate speaker embeddings trained to align with a strong single-speaker speaker-embedding space via permutation-invariant teacher supervision.

C2weakest assumption

That embeddings predicted from the mixture alone will align sufficiently with the single-speaker embedding space to serve as effective control signals for downstream extraction without any enrollment data.

C3one line summary

A neural model predicts a set of speaker embeddings from noisy mixtures to enable enrollment-free target speech extraction, outperforming baselines on LibriMix and generalizing to real recordings.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Receipt and verification
First computed 2026-06-23T02:13:23.339025Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac

Aliases

arxiv: 2604.03219 · arxiv_version: 2604.03219v2 · doi: 10.48550/arxiv.2604.03219 · pith_short_12: 7SMNMVJCZIIL · pith_short_16: 7SMNMVJCZIILXIOG · pith_short_8: 7SMNMVJC
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW \
  | 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: fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "798069f89262b5ca4208d8fd28fa522cc6a59da69c749feda774f07e9d57db94",
    "cross_cats_sorted": [
      "cs.SD"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "eess.AS",
    "submitted_at": "2026-04-03T17:46:17Z",
    "title_canon_sha256": "1d3460bf8a729aa28105543e7f3dc9b44465459ff32c8630a63adf8a3c5de4e1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.03219",
    "kind": "arxiv",
    "version": 2
  }
}