VoxLock:語音智能體無需預先登記的目標説話者提取模型
VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step
VoxLock 是一款供語音智能體使用的因果式目標説話者提取模型,可利用通話本身截取的語音樣本,無需預先登記。在 Krisp 的 265 段錄音基準中,WER 為 4.95%,未處理音訊為 23.21%;在 400 個 AMI 會議片段中,WER 由 42.95% 降至 10.63%。
Published on Oct 29
Authors:
Abstract
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 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.
View arXiv page View PDF Project page GitHub 85 Add to collection
Get this paper in your agent:
hf papers read 2610.40727
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Audio-to-Audio • 27.3M • Updated 9 minutes ago • 1.32k • 39arbazsiddiqui/voxlock
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.40727 in a dataset README.md to link it from this page.
Spaces citing this paper 1
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co