Speech recognition using sub-word neural tree network models and multiple classifier fusion

Manish Sharma; Richard Mammone

Speech recognition using sub-word neural tree network models and multiple classifier fusion

School of Engineering, Electrical & Computer Engineering

Research output: Contribution to journal › Conference article › peer-review

Abstract

A new neural tree network (NTN) -based speech recognition system is presented. In the sub-word unit-based system, the NTNs model sub-word speech segments. Durational probability is associated with each sub-word NTN. An iterative algorithm is proposed for training the sub-word NTNs. The sub-word NTN models, as well as the sub-word segment boundaries within a vocabulary word, are re-estimated. Thus, this paradigm can be argued to represent a class of discriminatory training-based, homogeneous, sub-word unit-based, speech recognition systems. Hence, the results reported can be generalized to other similar systems.

Original language	English (US)
Pages (from-to)	3323-3326
Number of pages	4
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	5
State	Published - 1995
Event	Proceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 2 (of 5) - Detroit, MI, USA Duration: May 9 1995 → May 12 1995

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Electrical and Electronic Engineering

Cite this

@article{bdf8dc71dfd9471aa47f296246c40eeb,

title = "Speech recognition using sub-word neural tree network models and multiple classifier fusion",

abstract = "A new neural tree network (NTN) -based speech recognition system is presented. In the sub-word unit-based system, the NTNs model sub-word speech segments. Durational probability is associated with each sub-word NTN. An iterative algorithm is proposed for training the sub-word NTNs. The sub-word NTN models, as well as the sub-word segment boundaries within a vocabulary word, are re-estimated. Thus, this paradigm can be argued to represent a class of discriminatory training-based, homogeneous, sub-word unit-based, speech recognition systems. Hence, the results reported can be generalized to other similar systems.",

author = "Manish Sharma and Richard Mammone",

year = "1995",

language = "English (US)",

volume = "5",

pages = "3323--3326",

journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",

issn = "0736-7791",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Proceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 2 (of 5) ; Conference date: 09-05-1995 Through 12-05-1995",

}

TY - JOUR

T1 - Speech recognition using sub-word neural tree network models and multiple classifier fusion

AU - Sharma, Manish

AU - Mammone, Richard

PY - 1995

Y1 - 1995

N2 - A new neural tree network (NTN) -based speech recognition system is presented. In the sub-word unit-based system, the NTNs model sub-word speech segments. Durational probability is associated with each sub-word NTN. An iterative algorithm is proposed for training the sub-word NTNs. The sub-word NTN models, as well as the sub-word segment boundaries within a vocabulary word, are re-estimated. Thus, this paradigm can be argued to represent a class of discriminatory training-based, homogeneous, sub-word unit-based, speech recognition systems. Hence, the results reported can be generalized to other similar systems.

AB - A new neural tree network (NTN) -based speech recognition system is presented. In the sub-word unit-based system, the NTNs model sub-word speech segments. Durational probability is associated with each sub-word NTN. An iterative algorithm is proposed for training the sub-word NTNs. The sub-word NTN models, as well as the sub-word segment boundaries within a vocabulary word, are re-estimated. Thus, this paradigm can be argued to represent a class of discriminatory training-based, homogeneous, sub-word unit-based, speech recognition systems. Hence, the results reported can be generalized to other similar systems.

UR - http://www.scopus.com/inward/record.url?scp=0028996599&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028996599&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0028996599

VL - 5

SP - 3323

EP - 3326

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

SN - 0736-7791

T2 - Proceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 2 (of 5)

Y2 - 9 May 1995 through 12 May 1995

ER -

Speech recognition using sub-word neural tree network models and multiple classifier fusion

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this