Title :
Acoustic Training from Heterogeneous Data Sources: Experiments in Mandarin Conversational Telephone Speech Transcription
Author :
Tsakalidis, Stavros ; Byrne, William
Author_Institution :
Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA
fDate :
March 18-23, 2005
Keywords :
speech recognition; telephony; ASR acoustic training set; Mandarin conversational telephone speech; acoustic normalization; cross-corpus normalization; heterogeneous data sources; out-of-domain acoustic data; speaker adaptive training; speech transcription; Acoustical engineering; Automatic speech recognition; Data engineering; Degradation; Loudspeakers; Natural languages; Sampling methods; Speech analysis; Speech processing; Telephony;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415150
