scispace - formally typeset
Search or ask a question

Showing papers on "Intelligent word recognition published in 1983"


Proceedings ArticleDOI
01 Apr 1983
TL;DR: New technique for use in a word recognition system where word templates are represented as sequences of descrete phoneme-like (pseudo-phoneme) templates which are automatically determined from a training set of word utterances by a clustering technique.
Abstract: This paper describes new technique for use in a word recognition system. This recognition system is especially efffective in speaker-dependent large vocabulary word recognition based on multiple reference templates. In this system, word templates are represented as sequences of descrete phoneme-like (pseudo-phoneme) templates which are automatically determined from a training set of word utterances by a clustering technique. In speaker-dependent 641 city names word recognition experiments, 96.3% recognition accuracy was obtained using 256 phoneme-like templates.

56 citations


Journal ArticleDOI
TL;DR: The whole word pattern-matching principles used in these machines are described, and it is shown how these principles can be extended to deal with continuously spoken sequences of words.
Abstract: Machines that recognize isolated words from a small, predefined vocabulary have been commercially available for many years. The whole word pattern-matching principles used in these machines are described, and it is shown how these principles can be extended to deal with continuously spoken sequences of words. Details are given of the resulting connected word recognition algorithm which has several novel features and potentially useful extensions. The algorithm has already been implemented in real-time hardware, which will be used to explore the full potential and limitations of the method in many different applications.

51 citations


Patent
16 Jun 1983
TL;DR: In this paper, the similarity between a candidate word and words registered in a word dictionary is calculated using the similarity measure calculated by a system control part to calculate the similarity of the candidate words and the words in a dictionary.
Abstract: PURPOSE: To perform recognition easily and efficiently by employing processing which utilizes hierarchical structure and performing its recognition retrial processing when the result of recognition of a word in some hierarchy is not obtained CONSTITUTION: A word recognizing part 5 is brought under the control of a system control part 10 to calculate 8 the similarity between a candidate word and words registered in a word dictionary, performing word recognition If the result of recognition of a word in some hierarchy of an input word data string is not obtained in the word recognition, at least one of combination processing, omission recovery processing, integration processing, coupling processing, and separation processing which utilize the hierarchical structure is used to perform its recognition retrial processing Consequently, the word data string is recognaized effectively from the relation among the words forming the hierarchical structure of the input word data string Therefore, a word data string for adress display, etc, is recognized effectively COPYRIGHT: (C)1985,JPO&Japio

5 citations



Patent
28 Jun 1983
TL;DR: In this paper, a character information given from a reading part 1 is stored temporarily at a memory part 2 and then supplied to a recognition processing part 3, where the part 3 contains a buffer circuit 31, a feature extracting circuit 32, a collating circuit 33, a recognition dictionary part 34, an indirect recognition subject character selection circuit 35 and an indirect relation subject character connection dictionary part 36.
Abstract: PURPOSE: To increase the number of characters to be recognized with small memory capacity and to improve the responsiveness of recognition, by storing a character different from the character to be recognized with the prescribed relation to the character to be recognized. CONSTITUTION: The character information given from a reading part 1 is stored temporarily at a memory part 2 and then supplied to a recognition processing part 3. The part 3 contains a buffer circuit 31, a feature extracting circuit 32, a collating circuit 33, a recognition dictionary part 34, an indirect recognition subject character selection circuit 35 and an indirect recognition subject character connection dictionary part 36. The circuit 33 calculates the distance between a pattern extracted by the circuit 32 and a feature pattern of the part 34. Then the direct recognition subject character having the highest degree of resemblance is extracted, and the characters to be recognized are displayed in order of higher degree of resemblance. Here the data of the part 36 is referred to for different characters which are not displayed, and the character information related to the extracted character information is displayed to be selected by a keyboard 5. COPYRIGHT: (C)1985,JPO&Japio

4 citations


Journal ArticleDOI
Jean Hudson1, John Haworth1
01 Jul 1983-Literacy

3 citations