The Interaction of Word Recognition and Linguistic Processing in Speech Understanding

This contribution describes an approach to integrate a speech understanding and dialog system into a homogeneous architecture based on semantic networks. The definition of the network as well as its use in speech understanding is described briefly. A scoring function for word hypotheses meeting the requirements of a graph search algorithm is presented. The main steps of the linguistic analysis, i.e. syntax, semantics, and pragmatics, are described and their realization in the semantic network is shown. The processing steps alternating between data- and model-driven phases are outlined using an example sentence which demonstrates a tight interaction between word recognition and linguistic processing.

[1]  Roland Kuhn,et al.  A probabilistic approach to person-robot dialogue , 1991 .

[2]  Lawrence R. Rabiner,et al.  Mathematical foundations of hidden Markov models , 1988 .

[3]  William A. Woods.  Optimal Search Strategies for Speech Understanding Control , 1982, Artif. Intell..

[4]  Frederick Jelinek,et al.  The development of an experimental discrete dictation recognizer , 1985 .

[5]  Heinrich Niemann,et al.  Generating word hypotheses in continuous speech , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  N. Geschwind.  Specializations of the human brain. , 1979, Scientific American.

[7]  Charles J. Fillmore,et al.  THE CASE FOR CASE. , 1967 .

[8]  Steve Young,et al.  The design and implementation of dialogue control in voice operated database inquiry systems , 1989 .

[9]  Thomas B. Martin.  Communications: One way to talk to computers: Voice commands to computers may substitute in part for conventional input devices , 1977, IEEE Spectrum.

[10]  P. Regel,et al.  The speech understanding and dialog system EVAR , 1987 .

[11]  John S. Bridle,et al.  Alpha-nets: A recurrent 'neural' network architecture with a hidden Markov model interpretation , 1990, Speech Commun..

[12]  L. Fissore,et al.  A word hypothesizer for a large vocabulary continuous speech understanding system , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[13]  Heinrich Niemann.  Pattern Analysis and Understanding , 1990 .

[14]  Victor R. Lesser,et al.  Parallelism in Artificial Intelligence Problem Solving: A Case Study of Hearsay II , 1977, IEEE Transactions on Computers.

[15]  Dennis H. Klatt,et al.  Review of the ARPA speech understanding project , 1990 .

[16]  Douglas E. Appelt,et al.  TEAM: An Experiment in the Design of Transportable Natural-Language Interfaces , 1987, Artif. Intell..

[17]  Gerhard Sagerer,et al.  Automatisches Verstehen gesprochener Sprache , 1990, Reihe Informatik.

[18]  Heinrich Niemann,et al.  Control Strategies in Image and Speech Understanding , 1983, GWAI.

[19]  Stephanie Seneff.  TINA: a probabilistic syntactic parser for speech understanding systems , 1989 .

[20]  Jack Hollingum,et al.  Speech Technology at Work , 1988 .

[21]  Bruce T. Lowerre,et al.  The HARPY speech recognition system , 1976 .

[22]  Hy Murveit,et al.  Integrating Speech and Natural-Language Processing , 1989, HLT.

[23]  Norbert Reithinger,et al.  XTRA: A Natural-Language Access System to Expert Systems , 1989, Int. J. Man Mach. Stud..

[24]  Heinrich Niemann,et al.  ERNEST: A Semantic Network System for Pattern Understanding , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Heinrich Niemann,et al.  Recent Advances in Speech Understanding and Dialog Systems , 2012, NATO ASI Series.

[26]  Nils J. Nilsson,et al.  Principles of Artificial Intelligence , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Victor Zue,et al.  The VOYAGER Speech Understanding System: A Progress Report , 1989, HLT.

[28]  Steve Young,et al.  Applications of stochastic context-free grammars using the Inside-Outside algorithm , 1990 .

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

[30]  Renato De Mori,et al.  Computer Models of Speech Using Fuzzy Algorithms , 1983, Advanced Applications in Pattern Recognition.

[31]  Ernst Günter Schukat-Talamazzini.  Generierung von Worthypothesen in kontinuierlicher Sprache , 1987, Informatik-Fachberichte.

[32]  Hsiao-Wuen Hon,et al.  An overview of the SPHINX speech recognition system , 1990, IEEE Trans. Acoust. Speech Signal Process..

[33]  Heinrich Niemann,et al.  Control Strategies in a Hierarchical Knowledge Structure , 1988, Int. J. Pattern Recognit. Artif. Intell..

[34]  Ching Y. Suen,et al.  New Systems and Architectures for Automatic Speech Recognition and Synthesis , 1987, NATO ASI Series.

[35]  William A. Ainsworth,et al.  Speech Recognition by Machine , 1988 .

[36]  Ute Ehrlich,et al.  A Knowledge Based speech Understanding System , 1988, Int. J. Pattern Recognit. Artif. Intell..

[37]  Ute Ehrlich,et al.  Bedeutungsanalyse in einem sprachverstehenden System unter Berücksichtigung pragmatischer Faktoren , 1990 .

[38]  Keikichi Hirose,et al.  A new approach to continuous speech recognition based on considerations on human processes of speech perception , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[39]  Hermann Ney,et al.  The use of a one-stage dynamic programming algorithm for connected word recognition , 1984 .

[40]  Leonard Bolc,et al.  Natural Language Based Computer Systems , 1980 .

[41]  Lynette Hirschman,et al.  Porting PUNDIT to the Resource Management Domain , 1989, HLT.