Dynamic classifier combination using utterance-level confidence values

Kirchhoff K, Bilmes J (1999)
In: International Conference on Acoustics, Speech and Signal Processing. Phoenix, Arizona, USA.

Conference Paper | Published | English

No fulltext has been uploaded

Author
;
Abstract
A recent development in the hybrid HMM/ANN speech recognition paradigm is the use of several subword classifiers, each of which provides different information about the speech signal. Although the combining methods have obtained promising results, the combination strategies so far proposed have been relatively simple. In most cases frame-level subword unit probabilities are combined using an unweighted product or sum rule. In this paper, we argue and empirically demonstrate that the classifier combination approach can benefit from a weighted combination rule, where the weights are derived from higher-than-frame-level confidence values.
Publishing Year
PUB-ID

Cite this

Kirchhoff K, Bilmes J. Dynamic classifier combination using utterance-level confidence values. In: International Conference on Acoustics, Speech and Signal Processing. Phoenix, Arizona, USA; 1999.
Kirchhoff, K., & Bilmes, J. (1999). Dynamic classifier combination using utterance-level confidence values. International Conference on Acoustics, Speech and Signal Processing.
Kirchhoff, K., and Bilmes, J. (1999). “Dynamic classifier combination using utterance-level confidence values” in International Conference on Acoustics, Speech and Signal Processing (Phoenix, Arizona, USA).
Kirchhoff, K., & Bilmes, J., 1999. Dynamic classifier combination using utterance-level confidence values. In International Conference on Acoustics, Speech and Signal Processing. Phoenix, Arizona, USA.
K. Kirchhoff and J. Bilmes, “Dynamic classifier combination using utterance-level confidence values”, International Conference on Acoustics, Speech and Signal Processing, Phoenix, Arizona, USA: 1999.
Kirchhoff, K., Bilmes, J.: Dynamic classifier combination using utterance-level confidence values. International Conference on Acoustics, Speech and Signal Processing. Phoenix, Arizona, USA (1999).
Kirchhoff, Katrin, and Bilmes, J. “Dynamic classifier combination using utterance-level confidence values”. International Conference on Acoustics, Speech and Signal Processing. Phoenix, Arizona, USA, 1999.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar