Personalized Keyphrase Detection using Speaker and Environment Information
Abstract
In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary. The system is implemented with an end-to-end trained automatic speech recognition (ASR) model and a text-independent speaker verification model. To address the challenge of detecting these keyphrases under various noisy conditions, a speaker separation model is added to the feature frontend of the speaker verification model, and an adaptive noise cancellation (ANC) algorithm is included to exploit cross-microphone noise coherence. Our experiments show that the text-independent speaker verification model largely reduces the false triggering rate of the keyphrase detection, while the speaker separation model and adaptive noise cancellation largely reduce false rejections.
Keywords
Cite
@article{arxiv.2104.13970,
title = {Personalized Keyphrase Detection using Speaker and Environment Information},
author = {Rajeev Rikhye and Quan Wang and Qiao Liang and Yanzhang He and Ding Zhao and Yiteng and Huang and Arun Narayanan and Ian McGraw},
journal= {arXiv preprint arXiv:2104.13970},
year = {2021}
}