@inproceedings{a895905b53604735a3edf912cc69124c,
title = "Wake word detection with alignment-free lattice-free MMI",
abstract = "Always-on spoken language interfaces, e.g. personal digital assistants, rely on a wake word to start processing spoken input. We present novel methods to train a hybrid DNN/HMM wake word detection system from partially labeled training data, and to use it in on-line applications: (i) we remove the prerequisite of frame-level alignments in the LF-MMI training algorithm, permitting the use of un-transcribed training examples that are annotated only for the presence/absence of the wake word; (ii) we show that the classical keyword/filler model must be supplemented with an explicit non-speech (silence) model for good performance; (iii) we present an FST-based decoder to perform online detection. We evaluate our methods on two real data sets, showing 50%-90% reduction in false rejection rates at prespecified false alarm rates over the best previously published figures, and re-validate them on a third (large) data set.",
keywords = "Alignment free, Lattice-free MMI, Wake word detection",
author = "Yiming Wang and Hang Lv and Daniel Povey and Lei Xie and Sanjeev Khudanpur",
note = "Publisher Copyright: Copyright {\textcopyright} 2020 ISCA; 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 ; Conference date: 25-10-2020 Through 29-10-2020",
year = "2020",
doi = "10.21437/Interspeech.2020-1811",
language = "英语",
isbn = "9781713820697",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
publisher = "International Speech Communication Association",
pages = "4258--4262",
booktitle = "Interspeech 2020",
}