Abstract
Grammatical Inference (GI) is a well established discipline dealing with theory and methods for learning grammars from training data. GI concepts and techniques are reviewed in this paper, along with their applications in Automatic Speech Recognition and Understanding.
Work supported in part by the Spanish CICYT under grant TIC 1026/92-CO2. Part of the first author’s work was carried out during a stay at AT&T Bell-Labs. A more complete version of this paper is in [42]
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
E.M. Gold: “Language Identification in the Limit”. Inf. and Control, Vol. 10, 447–474, 1967.
K.S. Fu: “Grammatical Inference: Introduction and Survey”. Parts 1 & 2, IEEE Trans. SMC, 55, 95–11, 409-423, 1975.
K.S. Fu: “Syntactic Pattern Recognition and Applications”. Prentice Hall, 1982
R. González and M. Thomason: “Syntactic Pattern Recognition. An Introduction”. Addison-Wesley, 1978.
L. Miclet: “Grammatical Inference”. In “Syntactic and Structural Pattern Recognition and applications”.H. Bunke, A. Sanfeliu (eds.), 237–290. World Scientific, 1990.
F. Casacuberta: “Some Relations Among Stochastic Finite State Networks Used in Automatic Speech Recognition”. IEEE Trans. PAM?, 12, 7, 1990.
F. Jelinek: “Up from Trigrams: The Struggle for Improved Language Models” EUROESPEECH’91.
J.E. Hoptcroft and J.D. Ullman: “Introduction to Automata Theory, Languages and Computation”. Addison-Wesley, 1979.
F.J. Maryanski, T.L. Booth. “Inference of Finite-State Probabilistic Grammars”. IEEE Trans, on Computation, 26, 531–536, 1977.
R. Chandhuri, A.N.V. Rhao. “Aproximating Grammar Probabilities: Solution of a Conjecture”. JACM, 33, 4, 702–705, 1986.
F.R. Jelinek, J.D. Lafferty, R.L. Mercer: “Basic Methods of Probabilistic Context-Free Grammars” in “Speech Recognition and Understanding”. P. Laface and R. DeMori Eds.. Springer Verlag, 345–360, 1992.
H. Ney: “Stochastic Grammars and Pattern Recognition” in “Speech Recognition and Understanding”. P. Laface and R. DeMori. Eds. Springer Verlag, 319–344. 1992
F. Casacuberta: “Growth Tranformations for Probabilistic Functions of Stochastic Grammars”. To be published, 1993
D. Angluin: “On the Complexity of Minimun Inference of Regular Sets” Inf. & Control, 39, 337–350, 1978.
E.M. Gold: ”Complexity of Automaton Identification from Given Data”. Inf. and Control, 37, 302–320, 1978.
D. Angluin & C.H. Smith: “Inductive Inference: Theory and Methods”. Comp. Surveys, 15, N°3, 46–62, 1983.
D. Angluin: Inductive Inference of Formal Languages from Positive Data”. Inf. & Control, 45, 117–135, 1980.
D. Angluin: “Inference of Reversible Languages” J.ACM, 29, 3, 741–765, 1982.
V. Radhakrishnan and G. Nagaraja:: ““Inference of Regular Grammars via Skeletons”. IEEE Trans SMC, 17, 6, 11–21, 1987.
P. Garcia and E. Vidal: “Inference of K-Testable Languages In the Strict Sense and Application to Syntactic Pattern Recognition”. IEEE Trans, on PAM?, 12, 9, 920–925, 1990.
A.W. Biermann and J.A. Feldmann: “On the Synthesis of Finite-State Machines from Samples of their behavior” IEEE Trans. Compt., C-21, 592–597.
L. Miclet: “Regular Inference with a Tail-Clustering Method”. IEEE Trans. SMC, 10, 737–743. 1980.
S. Muggleton: “Induction of Regular Languages from Positive Examples” Tech. Rep, Turing Institute Research Memoranda, Glasgow, 1984.
H. Rulot and E. Vidal: “Modelling (sub) string-lenght-based constraints through a Grammatical Inference Methods”, Devijver and Kittler, eds. (Springer, Berlin).
P. García, E. Vidal and F. Casacuberta: “Local Languages, the Successor Method, and a step towards a General methodology for the Inference of Regular Grammars”. IEEE Trans. PAMI, 9, 6, 841–845. 1987.
R.M. Wharton: “Approximate Language Identification”. Inf. and Control, 26, 236–255.
L.G. Valiant: “A Theory of the learnable”. Communications of the ACM, 27, 11, 1134–1142, 1984.
B.K. Natarajan.: “Machine Learning. A theoretical approach”. Morgan Kaufmann, 1991.
M.G. Thomason, E. Granum and R,E, Blake: “Experiments in dynamic programming inference of Markov netwrks whit strings representing speech data”. Patt. Recog, 19, 5, 343–351, 1986.
A. Falaschi: “Phonetic Structure inference of phonemic HMM” in “Speech Recognition and Understanding. Recent Advances”. Ed. P. Laface and R. deMori. Springer-Verlag, 71–76, 1992.
P. Lockwood, M.Blanchet: “An Algorithm for the Dynamic Inference of Hidden Markov Models (DIHMM)”. ICASSP’92. Vol. II. 251–254.
G.D. Forney: “The Viterbi algorithm”. IEEE proc. N 3, 268–278, 1973.
E. Vidal, H. Rulot, J.M. Valiente, G. Andreu.: “Application of the Error-Correcting Grammatical Inference Algorithm (ECGI) to Planar Shape Recognition”. ICGI’93, Essex, April, 1993.
H. Rulot, N. Prieto, E. Vidal: “Learning Accurate Finite-State Structural Models of Words through the ECGI algorithm”. ICASSP’89 proc, Vol. 1, 643–646.
H. Rulot: “ECGI: Un Algoritmo de Inferencia Gramatical Mediante correccion de Errores”. Doctoral dissertation, Universitat de València. 1992.
F. Casacuberta, E. Vidal, B. Mas, H. Rulot: “Learning the Structure of HMM’s Trrough Grammatical Inference Techniques”. ICASSP’90 proc., 717–720.
E. Vidal, H. Rulot, J.M. Valiente, G. Andreu: “Font-Independent Mixed-Size Digit Recognition Through the Error-Correctinh Grammatical Inference Algorithm (ECGI)”. ICPR’92, 334–337. 1992.
Y. Zalcstein: “Locally Testable Languages”. Jour. Comp. Sys. Sci., 6, 151–167, 1972.
E. Segarra,: “Una Aproximación Inductiva a la Comprension del Discurso Continuo”. PhD diss., Universidad Politecnica de Valencia. 1993.
A. Guerrero, E. Segarra and P. Garcia.: “Utilizatión de un Modelo de Error basado en la Extension Semicontinua del Algoritmo k-EE en tareas de Reconocimiento del Habla”. V Simposium de Reconocimiento de Formas y Analisis de Imagenes, 196–203, 1992.
P. García, E. Segarra, E. Vidal and I. Galiano: “On the use of the Morphic Generator Grammatical Inference (MGGI) methodology in automatic speech recognition”. IJPRAI, 4, 667–685, 1990.
E. Vidal, F. García and F. Casacuberta: “Grammatical Inference and Applications to Automatic Speech Recognition and Understanding”. Tech. Rep. DSIC Polyt. Univ. of Valencia, 1993.
J. Oncina and P. Garcia: “Inferring Regular Languages in Polynomial Updated Time”. In Pattern Recognition and Image Analysis. N. Perez de la Blanca, A. Sanfeliu and E. Vidal (eds) Series in Machine Perception and Artificial Intelligence, Vol-1, 49–61. World Scientific Pub, 1992.
K.J. Lang: “Random DFA’s can be Approximately Learned from Sparse Uniform Examples”. COLT’92.
M. Perles, M.O. Rabin, and E. Shamir: “The theory of definite automata” IEEE Trans. EC-12, 233–243, 1963.
R.C. Berwick and S. Pilato: “Learning Syntax by Automata Induction”. Machine Learning 2, 9–38, 1987.
J. Oncina: “Aprendizaje de Lenguajes Regulares y Funciones Subsecuenciales” Ph.D. Dis., Univ. Polit, de Valencia. 1991.
J. Oncina, P. Garcia and E. Vidal: “Learning Subsequential Transducers for Pattern Recognition Interpretation Tasks”. IEEE Trans, on PAM?, May 1993.
A. Stoike and S. Omohundro: “Hidden Markov Model Induction by Bayesian Model Merging”. To appear in: C.L. Giles, S.J. Hanson, and J.D. Cowan, eds., Advances in Neural Information Processing Systems 5, San Mateo, CA, Morgan Kaufman, 1993.
X.D. Huang, Y. Ariki, M.A. Jack: “Hidden Markov Models for Speech Recognition” Edinburgh Univ. Press. 1990.
J. Ziv & N. Merhav.: “Estimating the Number of States of a Finite-State Source” IEEE Trans. IT, 38, 1, 1992.
K. Lari and S.J. Young: “The Estimation of Stochastic context-free grammars using the Inside-Outside Algorithm”. Comp. Speech Lang., 4, 35–36, 1990.
Y. Sakakibara: “Efficient Learning of Context-Free Grammars from Positive Structural Examples”. Inf. and Comput. 97, 23–60, 1992.
E. Mäkinen: “On the Structural Grammatical Inference Problem for some Classes of Context-Free Grammars”. Inf. Procc. Letters 41, 1–5, 1992.
J.K. Baker: “Trainable Grammars for Speeach Recognition” In Speach Communication Papers, 97th Meeting of the ASA (Klatt, D. H. and Wolf, J.J. eds), 547–550.
K. Lari and S. J. Young: “Aplications of Stochastic Context-Free Grammars Using the Inside-Outside Algorithm”. CSL, 5, 237–257, 1991.
F. Pereira and Y. Schabes: “Inside-Outside Reestimation from Partially Bracketed Corpora”. 30 Annual Meeting of the ACL, 128–135, 1992.
J. Oncina, P. Garcia and E. Vidal: “Transducer Learning in Pattern Recognition” ICPR. Proc. 1992.
J. Berstel. “Transductions and Context-Free Langages”. Teubner, Stuggart, 1979.
P.F. Brown et al.: “A Stochastical Approach to Machine Translation” Comput. Linguistics 16, 2, 1990.
E. Vidal, R. Pieraccini and E. Levin: “Learning Associations Between Grammars: a New Approach to Natural Language Understanding” EUROSPEECH-93, proc. 1993.
T.M. Cover and J.A. Thomas: “Elements of information theory” John Wiley, 1991.
G. Bordel: “Language Modelling using k-TS Grammars” DSIC Research Report, 11/40/93, 1993.
J. E. Diaz, A. J. Rubio, A. M. Peinado, E. Segarra, N. Prieto and F. Casacuberta. “Development of task oriented Spanish Speech Corpora” Eurospeech 93.
N. Prieto, E. Vidal: “Learning Languages Model Through the ECGI method”. Speech Com., 11, 299–309, 1992.
P. J. Price: “Evaluation of Spoken Language Systems: the ATIS Domain”. Proc. of 3rd. DARPA Workshop on SNL, 91–95, Hidden Valley (PA), June 1990.
R. Gansner, E. Koutsofios, S.C. North and K.P. Vo: “A Technique for Drawing Directed Graphs”, IEEE Trans. Sofware Eng., March 1993.
R. Pieraccini, E. Levin: “A Learning Approach to Natural Language Understanding” NATO-ASI on ASR 1993.
E. Sanchís and N. Prieto: “kIncorporación de modelos acústico-fonéticos y semúnticos en un sistema de reconocimiento del discurso continuo” Tech. Report,DSIC (in preparation)
A. Castellanos, E. Vidal and J. Oncina: “Language Understanding and Subsequential Tansducer Learning”. First ICGI, Proc. Univer. of Essex, April 1993.
J. A. Feldman, G. Lakoff, A. Stoike and S. Hollbach Weber: “Miniature Language Acquisition: A touchstone for cognitive science” International Computer Science Institute. TR-90-009. 1990.
L.R. Bahl, P.F. Brown, P.V. de Souza, R.L. Mercer and M.A. Picheney: “Acoustic Markov Models used in the Tangóra Speech Recognition System”. Proc. ICASSP’90, 497–500.
L.R. Bahl, J.R. Bellegarda, P.V. de Souza, P.S. Gopalakrishnan, D. Nahamoo and M.A. Picheney: “A New Class of Fenonic Markov Word Models for Large Vocabulary Continuous Speech Recognition”. Proc. ICASSP′91, 177–180.
L.R. Bahl, J.R. Bellegarda, P.V. de Souza, P.S. Gopalakrishnan, D. Nahamoo, M.A. Picheny:Multonic Markov Word Models for Large Vocabulary Continuous Speech Recognition”. IEEE Trans on Speech and Audio Processing. Vol. 1(3), 334–344. 1993.
[75] D.J. Pepper, M.A. Clements “On the phonetic structure of a large HMM”. ICASSP’91, 465–468,.
D. Jouvet, L. Manuary, M. Monné: “Automatic adjustments of the structure of Markov models for speech recognition applications”. EUROSPEECH’91, 927–930.
J. Takami, S. Sagayama: “A succesive state splitting algorithm for efficient allophone modeling”. Proc. ICASSP, J-573/576, 1992.
I. Galiano, F. Casacuberta, E. Sanchís. “On the Structure of Subword units for a Speaker Independent Continuous Speech Task” EUROSPEECH’91.
I. Galiano: “Decodificación Acústico-Fonética en Castellano mediante una metofdología de Inferencia Gramatical basadaen Generadores Mórficos”. Ph.D dissertation. Univ. Politécnica de Valencia. Nov. 1992.
I. Galiano, E. Sanchís, I. Torres, F. Casacuberta: “Acoustic-Phonetic Decoding of Spanish Continuous Speech” IJPRAI, To be published, 1993.
I. Galiano, F. Casacuberta: “Experiments on Spanish Phone Recognition using automatically Derived Phonemeic Baseforms”. EUROSPEECH′93.
E. Sanchís, F. Casacuberta. “Learning Structural Models of Sublexical Units”, in “Speech Recognition and Understanding Recent Advances, Trends and Applications”. NATO ASI Series.Editor P. Laface Springer-Verlag, 525–530, 1991.
E. Sanchis, F. Casacuberta, I. Galiano. “Learning Structural models of Subwords Units through Grammatical Inference Techniques”. International Conference on Acoustic, Speech and Signal Processing. Toronto (Canadá).1991.
E. Segarra, I. Galiano, F. Casacuberta: “A Semicontinuous extension of the Morphic Generator Grammatical Inference Methodology”. IAPR Workshop of Structural and Syntactic Pattern Recognition, Bern, 1992.
T. Yu. Medvedev: “On the Class of Events Representable in a Finite Automaton” (translated from Russian), in Sequential Machines-Selected Papers, ed. E. F. Moor, Addison-Wesley, 227–315. 1964.
J. Oncina: “Inference of Probabilistic Automata”. Tech. Rep. DSIC Pol. Univ. of Valencia, 1993.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vidal, E., Casacuberta, F., García, P. (1995). Grammatical Inference and Automatic Speech Recognition. In: Ayuso, A.J.R., Soler, J.M.L. (eds) Speech Recognition and Coding. NATO ASI Series, vol 147. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-57745-1_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-57745-1_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63344-7
Online ISBN: 978-3-642-57745-1
eBook Packages: Springer Book Archive