Title :
Word recognition using whole word and subword models
Author :
Lee, Chia-Han ; Juang, Biing-hwang ; Soong, Frank K. ; Rabiner, L.R.
Author_Institution :
AT&T Bell Lab., Murray Hill, NJ, USA
Abstract :
The problem of how to select and construct a set of fundamental unit statistical models suitable for speech recognition is addressed. A unified framework is discussed which can be used to accomplish the goal of creating effective basic models of speech. The performances of three types of fundamental units, namely whole word, phoneme-like, and acoustic segment units, in a 1109-word vocabulary speech recognition task are compared. The authors point out the relative advantages of each type of speech unit based on the results of a series of recognition experiments
Keywords :
speech recognition; acoustic segment units; fundamental unit statistical models; phoneme unit; recognition experiments; speech recognition; speech unit; subword models; vocabulary; whole word model; whole word unit; word recognition; Automatic speech recognition; Context modeling; Data mining; Databases; Dictionaries; Signal mapping; Speech coding; Speech recognition; Vocabulary;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266519
