Paper Info
Title
An Integration Of Knowledge And Neural Networks Toward A Phoneme Typewriter Without A Language Model
Abstract
In this paper, a speech recognition system toward a phoneme typewriter without a language model is proposed. The system is realized as an integration of spectrogram reading knowledge and Time-Delay Neural Networks (TDNNs). The system mainly consists of two parts: in the consonant recognition part, a sophisticated integration of knowledge and TDNN is proposed. This improves not only recognition performance and segmentation accuracy, but also reduces insertion errors drastically. In the vowel recognition part, a TDNN is used for detection and rough segmentation using its time shift tolerance advantage. The knowledge part is mainly used for verification of categories and boundaries. A phoneme recognition experiment on 2,620 Japanese words, uttered by one male speaker showed a 91.4% (11,612/12,710) recognition rate, a 3.6% deletion error rate, a 5.0% substitution error rate and a 20.7% insertion error rate, for all Japanese phonemes. This good result was obtained without any language model.
Year
Venue
Keywords
1991
IEICE TRANSACTIONS ON COMMUNICATIONS ELECTRONICS INFORMATION AND SYSTEMS
neural network,language model
Field
DocType
Volume
Computer science,Speech recognition,Time delay neural network,Artificial neural network,Language model
Conference
74
Issue
ISSN
Citations 
7
0917-1673
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Yasuhiro Komori1257.43
Kaichiro Hatazaki2145.76