nach oben

Soft Computing

Erschienen in:

09.08.2015 | Focus

Simplified scoring methods for HMM-based speech recognition

verfasst von: Pavel Paramonov, Nadezhda Sutula

Erschienen in: Soft Computing | Ausgabe 9/2016

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Most of the contemporary speech recognition systems exploit complex algorithms based on Hidden Markov Models (HMMs) to achieve high accuracy. However, in some cases rich computational resources are not available, and even isolated words recognition becomes challenging task. In this paper, we present two ways to simplify scoring in HMM-based speech recognition in order to reduce its computational complexity. We focus on core HMM procedure—forward algorithm, which is used to find the probability of generating observation sequence by given HMM, applying methods of dynamic programming. All proposed approaches were tested on Russian words recognition and the results were compared with those demonstrated by conventional forward algorithm.

Vorheriger Artikel Decomposition-based multi-objective evolutionary algorithm for vehicle routing problem with stochastic demands

Nächster Artikel Use of line based symmetry for developing cluster validity indices

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Baker JK (1975) The DRAGON system: an overview. IEEE Trans Acoust Speech Signal Process 23:24–29CrossRef

Baker JM, Deng L, Glass J, Khudanpur S, Lee C, Morgan N, OShaughnessy D (2009) Research developments and directions in speech recognition and understanding, part 1. IEEE Signal Process Mag 26:75–80CrossRef

Bertsekas D, Tsitsiklis J (2008) Introduction to probability, 2nd edn. Athena Scientific, Belmont

Dahl GE, Yu D, Deng L, Acero A (2012) Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans Audio Speech Lang Process 20:30–42CrossRef

Deng L, Li X (2013) Machine learning paradigms for speech recognition: an overview. IEEE Trans Audio Speech Lang Process 21:1060–1089CrossRef

Hinton G, Deng L, Yu D, Dahl GE, Mohamed A, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN, Kingsbury B (2012) Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process Mag 29:82–97CrossRef

Huang X, Acero A (2001) Spoken language processing: a guide to theory, algorithm, and system development. Prentice-Hall International, New Jersey

Jelinek F (1976) Continuous speech recognition by statistical methods. IEEE Proc 64:532–556CrossRef

Ke S, Hou Y, Huang Z, Li H (2008) A HMM speech recognition system based on FPGA. Congr Image Signal Process 5:305–309CrossRef

Mohamed A, Dahl GE, Hinton G (2012) Acoustic modeling using deep belief networks. IEEE Trans Audio Speech Lang Process 20:14–22CrossRef

Mohamed A, Hinton G, Penn G, (2012) Understanding how deep belief networks perform acoustic modeling. IEEE Int Conf Acoust Speech Signal Process, pp 4273–4276

Mosleh M, Setayeshi S, Mehdi Lotfinejad M, Mirshekari A (2010) FPGA implementation of a linear systolic array for speech recognition based on HMM. The 2nd International Conference on Computer and Automation Engineering 3:75–78

Rabiner L (1989) Tutorial on hidden Markov models and selected applications in speech recognition. IEEE Proc 77:257–286CrossRef

Tamuleviius G, Arminas V, Ivanovas E, Navakauskas D, (2010) Hardware accelerated FPGA implementation of lithuanian isolated word recognition system. Elektronika ir Elektrotechnika, pp 57–62

Trentin E, Gori M (2001) A survey of hybrid ANN/HMM models for automatic speech recognition. Neurocomputing 37:91–126CrossRefMATH

Titel: Simplified scoring methods for HMM-based speech recognition
verfasst von: Pavel Paramonov
Nadezhda Sutula
Publikationsdatum: 09.08.2015
Verlag: Springer Berlin Heidelberg
Erschienen in: Soft Computing / Ausgabe 9/2016
Print ISSN: 1432-7643
Elektronische ISSN: 1433-7479
DOI: https://doi.org/10.1007/s00500-015-1831-1

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Weitere Artikel der Ausgabe 9/2016

A taint based approach for automatic reverse engineering of gray-box file formats

Picture fuzzy clustering: a new computational intelligence method

Use of line based symmetry for developing cluster validity indices

Invasive weed optimization for solving index tracking problems

Sentiment analysis of movie reviews: finding most important movie aspects using driving factors

On the applicability of diploid genetic algorithms in dynamic environments