Speaker adaptation using ICA-based feature transformation

Speaker adaptation techniques are generally used to reduce speaker differences in speech recognition. In this work we focus on the features fitted to a linear regression-based speaker adaptation. These are obtained by feature transformation based on independent component analysis (ICA), and the feature transformation matrices are estimated from the training data and adaptation data. Since the adaptation data is not sufficient to reliably estimate the ICA-based feature transformation matrix, it is necessary to adjust the ICA-based feature transformation matrix estimated from a new speaker utterance. To cope with this problem, we propose a smoothing method through a linear interpolation between the speaker-independent (SI) feature transformation matrix and the speaker-dependent (SD) feature transformation matrix. From our experiments, we observed that the proposed method is more effective in the mismatched case. In the mismatched case, the adaptation performance is improved because the smoothed feature transformation matrix makes speaker adaptation using noisy speech more robust.
Publisher
ELECTRONICS TELECOMMUNICATIONS RESEARCH INST
Issue Date
2002-12
Language
ENG
Keywords

RECOGNITION

Citation

ETRI JOURNAL, v.24, pp.469 - 472

ISSN
1225-6463
URI
http://hdl.handle.net/10203/23731
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
3.pdf(269.46 kB)Download
  • Hit : 101
  • Download : 133
  • Cited 0 times in thomson ci
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡClick to seewebofscience_button
⊙ Cited 3 items in WoSClick to see citing articles inrecords_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0