Paper Detail

VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step

Arbaz Siddiqui

huggingface Score 8.5

Published 2026-10-29 · First seen 2026-11-02

General AI

Abstract

A voice agent's speech recognizer transcribes everyone near the microphone, including people other than the caller. I fine-tuned a public causal target-speaker extraction model (REAL-TSE, 27M parameters) on one GPU to work from a voice sample cut from the call itself, and released it as VoxLock. I score it by what a recognizer writes on real recordings. On Krisp's 265-recording benchmark it reaches 4.95% WER against 23.21% unprocessed and lets 9 background words into the transcript over 85 minutes of background-only speech. Its WER is not significantly different from Krisp's best filters and is significantly lower than the other commercial and open systems I tested. On 400 AMI meeting windows built and frozen before scoring, it cuts WER from 42.95% to 10.63%. The 8-bit model runs a live call on 77% of one CPU thread with 24 ms of algorithmic latency. Model, code and per-file scores are open.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{siddiqui2026voxlock,
  title = {VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step},
  author = {Arbaz Siddiqui},
  year = {2026},
  abstract = {A voice agent's speech recognizer transcribes everyone near the microphone, including people other than the caller. I fine-tuned a public causal target-speaker extraction model (REAL-TSE, 27M parameters) on one GPU to work from a voice sample cut from the call itself, and released it as VoxLock. I score it by what a recognizer writes on real recordings. On Krisp's 265-recording benchmark it reaches 4.95\% WER against 23.21\% unprocessed and lets 9 background words into the transcript over 85 minut},
  url = {https://huggingface.co/papers/2610.40727},
  keywords = {causal target-speaker extraction, REAL-TSE, VoxLock, WER, 8-bit model, algorithmic latency, code available, huggingface daily},
  eprint = {2610.40727},
  archiveprefix = {arXiv},
}

Metadata

{}