Acoustic Training from Heterogeneous Data Sources: Experiments in Mandarin Conversational Telephone Speech Transcription

Stavros Tsakalidis, Bill Byrne

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.
BibTeX
@inproceedings{tsakalidis2005acoustic,
  author = {Stavros Tsakalidis and Bill Byrne},
  title = {{Acoustic Training from Heterogeneous Data Sources: Experiments in Mandarin Conversational Telephone Speech Transcription}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2005},
  url = {https://openreview.net/forum?id=qKJ7xUKxRWc},
}

Loading related content...

Figure