A new confidence measure combining hidden Markov models and artificial neural networks of phonemes for effective keyword spotting
In this paper, we present an acoustic keyword spotter that operates in two stages, detection and verification. In the detection stage, keywords are detected in the utterances, and in the verification stage, confidence measures are used to verify the detected keywords and reject false alarms. A new c...
Main Authors: | Leow, Su Jun., Lau, Tze Siong., Goh, Alvina., Peh, Han Meng., Ng, Teck Khim., Siniscalchi, Sabato Marco., Lee, Chin-Hui. |
---|---|
Other Authors: | School of Computer Engineering |
Format: | Conference Paper |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/84231 http://hdl.handle.net/10220/11852 |
Similar Items
Similar Items
-
Hidden Markov Model
by: Sudirman, Rubita, et al.
Published: (2008) -
Small footprint model for noisy far-field keyword spotting
by: Pang, Jin Hui
Published: (2022) -
Algorithms and low power hardware for keyword spotting
by: Wang, Miaorong
Published: (2018) -
Morphological segmentation : an unsupervised method and application to Keyword Spotting
by: Narasimhan, Karthik Rajagopal
Published: (2014) -
Model reduction for Hidden Markov models
by: Kotsalis, Georgios
Published: (2007)