An integrated-circuit-based speech recognition system

A high-performance, flexible, and potentially inexpensive speech recognition system is described. The system is based on two special-purpose integrated circuits that perform the speech recognition algorithms very efficiently. One of these integrated circuits is the front-end processor, which computes spectral coefficients from incoming speech. The second integrated circuit computes a dynamic-time-warp algorithm. The system can compare an input word with 1000-word templates and respond to a user within \frac{1}{4} s. The system demonstrates that computational complexity need not be a major limiting factor in the design of speech recognition systems.

[1]  S. Pope,et al.  Computer generation of digital filter banks , 1984, 1984 IEEE International Solid-State Circuits Conference. Digest of Technical Papers.

[2]  G. White,et al.  Speech recognition experiments with linear predication, bandpass filtering, and dynamic programming , 1976 .

[3]  G. R. Doddington,et al.  Computers: Speech recognition: Turning theory to practice: New ICs have brought the requisite computer power to speech technology; an evaluation of equipment shows where it stands today , 1981, IEEE Spectrum.

[4]  Jared Bernstein,et al.  Speaker sampling for enhanced diversity , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Subhro Das.  Some experiments in discrete utterance recognition , 1982 .

[6]  L. Rabiner,et al.  An algorithm for determining the endpoints of isolated utterances , 1974, The Bell System Technical Journal.

[7]  A. Richard Smith,et al.  Solid State Audio/Speech Processor Analysis. , 1980 .

[8]  Lalit R. Bahl,et al.  A Maximum Likelihood Approach to Continuous Speech Recognition , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Aaron E. Rosenberg,et al.  Speaker-independent recognition of isolated words using clustering techniques , 1979 .

[10]  Aaron E. Rosenberg,et al.  Performance tradeoffs in dynamic time warping algorithms for isolated word recognition , 1980 .

[11]  F. Itakura,et al.  Minimum prediction residual principle applied to speech recognition , 1975 .

[12]  Robert W. Brodersen,et al.  Computer Generation of Digital Filter Banks , 1986, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[13]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[14]  Chiu-Kuang Chuang,et al.  Speech recognition using variable frame rate coding , 1983, ICASSP.

[15]  L. Rabiner,et al.  Isolated and Connected Word Recognition - Theory and Selected Applications , 1981, IEEE Transactions on Communications.

[16]  Robert W. Brodersen,et al.  Macrocell Design for Concurrent Signal Processing , 1983 .

[17]  Roberto Billi,et al.  Experimental comparison among data compression techniques in isolated word recognition , 1983, ICASSP.

[18]  Lawrence R. Rabiner,et al.  An algorithm for determining the endpoints of isolated utterances , 1975, Bell Syst. Tech. J..

[19]  Michael D. Brown,et al.  An algorithm for connected word recognition , 1982, ICASSP.