Title :
A neutral network for isolated-word recognition
Author_Institution :
Lincoln Lab., MIT, Lexington, MA
Abstract :
Algorithms that are implementable by artificial neural networks show promise of augmenting the field of automatic speech recognition. A specific approach to the problem of isolated-word recognition was initiated by Tank and Hopfield. These ideas were applied to a concatenated systems consisting of a vector quantizer, a time concentrator with vector sequences as input and allophones as output and a final stage with allophone sequence as input and isolated words as output. Improvements in the system are discussed; included are the addition of data-dependent `phenomenological´ rules that yield improved results for a single-speaker 35-word vocabulary isolated-word recognition task
Keywords :
neural nets; speech recognition; allophones; artificial neural networks; automatic speech recognition; concatenated systems; data-dependent phonological rules; isolated-word recognition; phoneme; time concentrator; vector quantiser; vector sequences; Circuits; Delay; Error analysis; Filters; Gold; Hidden Markov models; Histograms; Speech; Testing; Vocabulary;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on
Conference_Location :
New York, NY
DOI :
10.1109/ICASSP.1988.196505
