A system for understanding continuous german speech

Abstract The system described for understanding continuous German speech consists of a relational database for intermediate results or hypotheses, and a set of specialized processing modules for various tasks such as acoustic-phonetic transcription, finding words, syntactic and semantic analysis, or pragmatic evaluation; system activities are directed via several global parameters which can be specified by a control module. Presently, a vocabulary of about 1300 words is used, and the task domain consists of inquires about German intercity train schedules. Operational modules are the database, acoustic-phonetic, dictionary, syntax, and a simple control module. The semantics and pragmatics module are now in the test phase.

[1]  K. Kohler.  Einführung in die Phonetik des Deutschen , 1981 .

[2]  Madeleine Bates,et al.  The Theory and Practice of Augmented Transition Network Grammars , 1978, Natural Language Communication with Computers.

[3]  Seiichi Nakagawa.  A connected spoken word recognition method by O(n) dynamic programming pattern matching algorithm , 1983, ICASSP.

[4]  Astrid Brietzmann,et al.  Pragmatics in Speech Understanding - Revisited , 1982, COLING.

[5]  Heinrich Niemann,et al.  The Erlangen System for Recognition and Understanding of Continous German Speech , 1982, GI Jahrestagung.

[6]  Harvey F. Silverman,et al.  The 1976 modular acoustic processor(MAP) , 1977 .

[7]  Renato De Mori,et al.  Recent advances in automatic speech recognition , 1979 .

[8]  C. Weinstein,et al.  A system for acoustic-phonetic analysis of continuous speech , 1975 .

[9]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .

[10]  Hans-Werner Hein.  Das Erlanger Spracherkennungssystem , 1982 .

[11]  Lalit R. Bahl,et al.  Decoding for channels with insertions, deletions, and substitutions with applications to speech recognition , 1975, IEEE Trans. Inf. Theory.

[12]  T. Pavlidis,et al.  Fuzzy sets and their applications to cognitive and decision processes , 1977 .

[13]  David J. Broad.  Toward Defining Acoustic Phonetic Equivalence for Vowels , 1976 .

[14]  L. Gerstman.  Classification of self-normalized vowels , 1968 .

[15]  Vladimir I. Levenshtein,et al.  Binary codes capable of correcting deletions, insertions, and reversals , 1965 .

[16]  V. Zue,et al.  The role of phonological rules in speech understanding research , 1975 .

[17]  Lawrence R. Rabiner,et al.  A pattern recognition approach to voiced-unvoiced-silence classification with applications to speech recognition , 1976 .

[18]  Murat Kunt.  On Computation of the Hadamard Transform and the R Transform in Ordered Form , 1975, IEEE Transactions on Computers.

[19]  Heinrich Niemann,et al.  Automatische Erkennung zusammenhängend gesprochener Sprache , 1981, DAGM-Symposium.

[20]  D.R. Reddy,et al.  Speech recognition by machine: A review , 1976, Proceedings of the IEEE.

[21]  M. Sambur.  Speaker recognition using orthogonal linear prediction , 1976 .

[22]  T.B. Martin,et al.  Practical applications of voice input to machines , 1976, Proceedings of the IEEE.

[23]  H. Wakita.  Normalization of vowels by vocal-tract length and its application to vowel identification , 1977 .

[24]  Ronald J. Brachman,et al.  A Structural Paradigm for Representing Knowledge. , 1978 .