Title | ||
---|---|---|
Acoustic Training From Heterogeneous Data Sources: Experiments In Mandarin Conversational Telephone Speech Transcription |
Abstract | ||
---|---|---|
In this paper we investigate the use of heterogeneous data sources for acoustic training. We describe an acoustic normalization procedure for enlarging an ASR acoustic training set with out-of-domain acoustic data. A larger in-domain training set is created by effectively transforming the out-of-domain data before incorporation in training. Baseline experimental results in Mandarin conversational telephone speech transcription show that a simple attempt to add out-of-domain data degrades performance. Preliminary experiments assess the effectiveness of the proposed cross-corpus acoustic normalization. Furthermore, we investigate the behavior of speaker adaptive training in conjunction with the cross-corpus normalization procedure. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICASSP.2005.1415150 | 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING |
Keywords | Field | DocType |
data engineering,degradation,automatic speech recognition,speech recognition,sampling methods,natural languages,acoustical engineering,telephony,speech processing,loudspeakers | Speech corpus,Speech processing,Normalization (statistics),Voice activity detection,Computer science,Speech recognition,Telephony,VoxForge,Speech technology,Acoustic model | Conference |
ISSN | Citations | PageRank |
1520-6149 | 5 | 0.53 |
References | Authors | |
13 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stavros Tsakalidis | 1 | 213 | 13.83 |
William Byrne | 2 | 245 | 33.80 |