Doc. Dr. Ing. Jan Černocký
| Szőke, I., Schwarz, P., Burget, L., Karafiát, M., Černocký, J.: Phoneme based acoustics keyword spotting in informal continuous speech, In: Radioelektronika 2005, Brno, CZ, FEKT VUT, 2005, p. 195-198, ISBN 80-214-2904-6 | | Publication language: | english |
|---|
| Original title: | Phoneme based acoustics keyword spotting in informal continuous speech |
|---|
| Title (cs): | Akustický detektor klíčových slov založený na fonémech pro neformální plynulou řeč |
|---|
| Pages: | 195-198 |
|---|
| Proceedings: | Radioelektronika 2005 |
|---|
| Conference: | 15th International Czech-Slovak Scientific conference Radioelektronika 2005 |
|---|
| Place: | Brno, CZ |
|---|
| Year: | 2005 |
|---|
| ISBN: | 80-214-2904-6 |
|---|
| Publisher: | Faculty of Electrical Engineering and Communication BUT |
|---|
| URL: | https://www.fit.vutbr.cz/~szoke/papers/radioelektronika_2005.pdf [PDF] |
|---|
| Keywords |
|---|
acoustic keyword spotting, hidden Markov model, phoneme, recognition network
|
| Annotation |
|---|
| This paper describes several ways of keywords spotting (KWS), based on
Gaussian mixture (GM) hidden Markov modelling (HMM).
Context-independent and dependent phoneme models are used in our
system. The system was trained and evaluated on informal continuous
speech. We used different complexities of KWS recognition networks and
different types of phoneme models. The impact of these parameters on
the accuracy and computational complexity is investigated. |
| BibTeX: |
|---|
@INPROCEEDINGS{
author = {Igor Szőke and Petr Schwarz and Lukáš Burget and Martin
Karafiát and Jan Černocký},
title = {Phoneme based acoustics keyword spotting in informal
continuous speech},
pages = {195--198},
booktitle = {Radioelektronika 2005},
year = {2005},
location = {Brno, CZ},
publisher = {Faculty of Electrical Engineering and Communication BUT},
ISBN = {80-214-2904-6},
language = {english},
url = {http://www.fit.vutbr.cz/research/view_pub.php?id=7778}
} |
|