DocumentCode :
667489
Title :
Learning an intelligibility map of individual utterances
Author :
Mandel, Michael I.
Author_Institution :
Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA
fYear :
2013
fDate :
20-23 Oct. 2013
Firstpage :
1
Lastpage :
4
Abstract :
Predicting the intelligibility of noisy recordings is difficult and most current algorithms only aim to be correct on average across many recordings. This paper describes a listening test paradigm and associated analysis technique that can predict the intelligibility of a specific recording of a word in the presence of a specific noise instance. The analysis learns a map of the importance of each point in the recording´s spectrogram to the overall intelligibility of the word when glimpsed through “bubbles” in many noise instances. By treating this as a classification problem, a linear classifier can be used to predict intelligibility and can be examined to determine the importance of spectral regions. This approach was tested on recordings of vowels and consonants. The important regions identified by the model in these tests agreed with those identified by a standard, non-predictive statistical test of independence and with the acoustic phonetics literature.
Keywords :
speech intelligibility; statistical testing; acoustic phonetics literature; classification problem; individual utterances; intelligibility map; linear classifier; listening test paradigm; noisy recordings; nonpredictive statistical test; overall intelligibility; spectral regions; Acoustics; Noise; Predictive models; Spectrogram; Speech; Support vector machines; Time-frequency analysis; Glimpse; Intelligibility; Noise; Objective; Subjective;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Applications of Signal Processing to Audio and Acoustics (WASPAA), 2013 IEEE Workshop on
Conference_Location :
New Paltz, NY
ISSN :
1931-1168
Type :
conf
DOI :
10.1109/WASPAA.2013.6701835
Filename :
6701835
Link To Document :
بازگشت