A pairwise discriminant approach to robust phoneme recognition by time-delay neural networks

Takami, Jun-ichi; Sagayama, Shigeki

doi:10.1109/icassp.1991.150285

Search citation statements

Order By: Relevance

Paper Sections

Select...

Phoneme Recognition1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

1992

Publication Types

Select...

Article2

Other1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features are classified by classical methods14 and neural network approaches. [15][16][17][18] Adaptive wavelets offer two potential approaches. First, a super-wavelet could be generated for each phoneme using the function representation method of Sec.…”

Section: Phoneme Recognitionmentioning

confidence: 99%

Neural network adaptive wavelets for signal representation and classification

Szu

Telfer

Kadambe³

1992

Opt. Eng.

329

129

View full text Add to dashboard Cite

Section: Phoneme Recognitionmentioning

confidence: 99%

Neural network adaptive wavelets for signal representation and classification

Szu

Telfer

Kadambe³

1992

Opt. Eng.

329

129

View full text Add to dashboard Cite

Speech recognition by combining pairwise discriminant time-delay neural networks and predictive LR-parser

Takami

Kai²,

Sagayama³

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop

View full text Add to dashboard Cite

A pairwise discriminant approach using artificial neural networks for continuous speech recognition.

Takami¹,

Kai

Sagayama³

1992

J. Acoust. Soc. Jpn. (E), J Acoust Soc Jpn E

View full text Add to dashboard Cite

This paper describes a pairwise discrimination approach using artificial neural networks for robust phoneme recognition and its application to continuous speech recognition. Until now, it is known that classification-type neural networks show poor robustness against the difference in speaking rates between training data and testing data. To improve the robustness, we developed Pairwise Discriminant Time-Delay Neural Net -works (PD-TDNNs) by applying the principle of pair discrimination to a conventional Time-Delay Neural Network.In this approach, pair discrimination scores for all com -binations of two phonemes are calculated by PD-TDNNs, each of which has a less sharp discrimination boundary, and final phoneme candidates are decided by majority decision of the pair discrimination scores. Through phoneme and continuous speech recognition experiments, it was found that this approach performs better than the conventional TDNN.

show abstract

A pairwise discriminant approach to robust phoneme recognition by time-delay neural networks

Cited by 3 publications

References 8 publications

Neural network adaptive wavelets for signal representation and classification

Neural network adaptive wavelets for signal representation and classification

Speech recognition by combining pairwise discriminant time-delay neural networks and predictive LR-parser

A pairwise discriminant approach using artificial neural networks for continuous speech recognition.

Contact Info

Product

Resources

About