1 February 1994 Neural tree network for speech segmentation into subword acoustic units
Author Affiliations +
Proceedings Volume 2093, Substance Identification Analytics; (1994) https://doi.org/10.1117/12.172489
Event: Substance Identification Technologies, 1993, Innsbruck, Austria
A novel method of segmenting un-transcribed speech into sub-word acoustic units using neural tree networks (NTN) is presented. A NTN is a hierarchical classifier that combines the properties of decision trees and feed-forward neural networks. Segmentation of speech into sub-word units (of acoustic significance) is vital for large vocabulary, continuous speech recognition on un-transcribed speech database.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Manish Sharma, Richard J. Mammone, "Neural tree network for speech segmentation into subword acoustic units", Proc. SPIE 2093, Substance Identification Analytics, (1 February 1994); doi: 10.1117/12.172489; https://doi.org/10.1117/12.172489

Back to Top