EFFECTS OF TRANSCRIPTION ERRORS ON SUPERVISED LEARNING IN SPEECH RECOGNITION

منو

" EFFECTS OF TRANSCRIPTION ERRORS ON SUPERVISED LEARNING IN SPEECH RECOGNITION "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	150689
Doc. No	:	ET22481
Main Entry	:	Ramasubramanian Sundaram
Title Proper	:	EFFECTS OF TRANSCRIPTION ERRORS ON SUPERVISED LEARNING IN SPEECH RECOGNITION
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Supervised learning using Hidden Markov Models has been used to train acousticmodels for automatic speech recognition for several years. Typically clean transcriptionsform the basis for this training regimen. However, results have shown that using sourcesof readily available transcriptions, which can be erroneous at times (e.g., closed captions)do not degrade the performance significantly. This work analyzes the effects of mislabeleddata on recognition accuracy. For this purpose, the training is performed....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL45702.pdf
Title and statement of responsibility and	:	EFFECTS OF TRANSCRIPTION ERRORS ON SUPERVISED LEARNING IN SPEECH RECOGNITION [Thesis]