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 Komori | 1 | 25 | 7.43 |
Kaichiro Hatazaki | 2 | 14 | 5.76 |