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 paramete
A fine-tuned causal target-speaker extraction model achieves near-commercial speech recognition accuracy on real recordings with low CPU usage and latency.
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…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step was first seen on Hugging Face · Daily papers on Nov 3, 2026. Since then it has appeared in 2 checks on 1 different day. Its best position was #30 of 30, reached on Nov 3, 09:28 UTC. It dropped off the list after Nov 3, 11:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 3, 11:28 UTC, after 1 day of trending.
#30 on Hugging Face · Daily papers, on Nov 3, 09:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 3, 2026 and has been on the list on 1 day (2 checks) since.