Speaker independent speech recognition system and method using n

Details Speaker independent speech recognition system and method using n Speaker independent speech recognition system and method using n

1993-07-12

1996-06-18

MacDonald, Allen R.

395 263, G01L 506, G01L 900

Patent

active

055287280

ABSTRACT:
Improved speaker independent speech recognition system and method are disclosed in which an utterance by an unspecified person into an electrical signal is input through a device such as a telephone, the electrical signal from the input telephone converting the electrical signal into a time series of characteristic multidimensional vectors, the time series of characteristic multidimensional vectors are received, each of the vectors being converted into a plurality of candidates so that the plurality of phonemes constitutes a plurality of strings of phonemes in time series as a plurality of candidates, the plurality of candidates of phonemes are compared simultaneously (one at a time) with a reference pattern of a reference string of phonemes for each word previously stored in a dictionary to determine which string of phonemes derived from the phoneme recognition means has a highest similarity to one of the reference strings of the phonemes for the respective words stored in the dictionary using a predetermined word matching technique, and at least one candidate of the words as a result of word recognition on the basis of one of the plurality of the strings of phonemes which has the highest similarity to the corresponding one of the reference strings of the respective words is output as the result of speech recognition.

REFERENCES:
patent: 4637045 (1987-01-01), Noso et al.
patent: 4799261 (1989-01-01), Lin et al.
patent: 5228087 (1993-07-01), Bickerton
Continuous Speech Recognition Using Linked predictive neural Networks Tebelskis et al, IEEE 14-17 May 1991.
Phoneme base Word Recognition by NN:--Hirai et al., IEEE 17-21 June 1990.
Speech Recognition Using Dynamic NN Botros et al., IEEE 7-11 Jun. 1992.
Multiple NN Topologies applied to Keyword spotting Morgan et al., IEEE/14-17 May 1991.
Robust Speech Parameters Extraction for Word Recognition in Noise Using NN Barbier et al., IEEE 14-17 May 1991.
Dayhoff, Neural Network Architectures, Chapter 5, 1990.
Takami et al, "Phoneme Recognition by Pairwise Discriminant TDNNs", ATR Interpreting Telephony Research Laboratories, vol. 16:677-680.
Ryohei Nakatsu, A Japanese Paper of Information Processing vol. 24, No. 8, (Yokoshuki Electrical Communication Laboratory), pp. 984-992, 1983.
Japanese book entitled "Pattern Recognition", Published by a Japanese society of electronic, information, and communication on Apr. 26, 1993, pp. 116-123.
Lynn et al, "Introductory Digital Signal Processing With Computer Applications", The Fourier Transform Method, pp. 148-157, (1992).
Lynn et al, "Introductory Digital Signal Processing With Computer Applications", FFT Processing, pp. 251-283, (1992).

Affiliated with

Also associated with

Rating

Speaker independent speech recognition system and method using n does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speaker independent speech recognition system and method using n, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speaker independent speech recognition system and method using n will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-230005