Title
Polish Whispery Speech Recognition - Minimum Sampling Frequency
Authors
[ 1 ] Instytut Automatyki i Inżynierii Informatycznej, Wydział Elektryczny, Politechnika Poznańska | [ 2 ] Instytut Automatyki i Robotyki, Wydział Informatyki, Politechnika Poznańska | [ P ] employee | [ D ] phd student
Scientific discipline (Law 2.0)
Year of publication
2017
Chapter type
chapter in monograph / paper
Publication language
english
Keywords
EN
- automatic speech recognition
- ASR
- polish speech corpus
- whispered speech
- continuous speech recognition
Abstract
EN The article presents studies on the automatic whispery speech recognition. In the performed research a new corpus with whispery speech has been used. It has been checked how is the speech recognition quality changing at variables sampling frequency and signal frame length. It has been found that the optimal sampling frequency of whispery speech is about 32-48 kHz, while the optimal signal frame length is about 32-43 ms. The comparison of spectrograms between the normal and whispery speech has been also presented.
Date of online publication
2017
Pages (from - to)
611 - 615
Ministry points / chapter
20
Publication indexed in
WoS (15)
System created by Poznań University of Technology
and Poznan Supercomputing and Networking Center
Log in through eKonto to add to SIS