Paper Info
Title
Classification of clean and noisy bilingual movie audio for speech-to-speech translation corpora design
Abstract
Identifying suitable sources of bilingual audio and text data is a crucial part of statistical Speech to Speech (S2S) research and development. Movies, often dubbed in other languages, offer a good source for this purpose; but not all data are directly usable because of noise and other audio condition differences. Hence, automatically selecting the bilingual audio data that are suitable for analysis, and training S2S systems for specific environments becomes crucial. In this work, we extract bilingual speech segments from movies and aim at classifying segments as clean speech or speech with background noise (i.e. music, babble noise etc.). We examine various features in solving this problem and our best performing method delivers accuracy up to 87% in discriminating clean and noisy speech in bilingual data.
Year
DOI
Venue
2014
10.1109/ICASSP.2014.6853570
Acoustics, Speech and Signal Processing
Keywords
Field
DocType
audio signal processing,feature extraction,signal classification,speech processing,S2S research and development,audio condition difference,bilingual audio data selection,bilingual movie audio classification,bilingual speech segment extraction,clean speech,noisy speech,segment classification,speech-to-speech translation corpora design,statistical speech-to-speech,audio segmentation,bilingual movie audio clean speech detection
Speech corpus,Speech processing,Speech synthesis,Speech analytics,Speech coding,Voice activity detection,Audio mining,Computer science,Speech recognition,Natural language processing,Artificial intelligence,Acoustic model
Conference
ISSN
Citations 
PageRank 
1520-6149
0
0.34
References 
Authors
10
4
Name
Order
Citations
PageRank
Andreas Tsiartas1518.46
Prasanta Kumar Ghosh215632.78
Georgiou Panayiotis342855.79
Narayanan Shrikanth45558439.23