Voice based interface for route search system
作者： Tomas Rasymas , Vytautas Rudzionis
DOI: 10.1109/ESTREAM.2017.7950318
关键词:
摘要: In this paper we are presenting our approach of creating voice based interface for one the leading Lithuania bus route search system — www.autobusubilietai.lt. We designed a hybrid speech recognition which is on Lithuanian recognizer (LIEPA) and two foreign language recognizers (German Spanish). experimented with different methods that may be used combining outputs these recognizers: k-Nearest Neighbors, Naive Bayes, Support Vector Machines, Decision tree (CART), Linear discriminant analysis Logistic regression. achieved 88.0 % accuracy by using 3-Nearest Neighbors as combination method. Compared best single increased 3.5 %. Our experiments proved can improved recognizers. What more decreased time spent from 10–15 sec. to 5–10 end user satisfaction.
sci-hub.se 参考文章(17)
Hugo Meinedo, João Paulo Neto, Combination of acoustic models in continuous speech recognition hybrid systems. conference of the international speech communication association. pp. 931- 934 ,(2000)
Vytautas Rudžionis, Kastytis Ratkevičius, Algimantas Rudžionis, Gailius Raškinis, Rytis Maskeliunas, Recognition of Voice Commands Using Hybrid Approach international conference on information and software technologies. pp. 249- 260 ,(2013) , 10.1007/978-3-642-41947-8_21
Pijus Kasparaitis, Transcribing of the Lithuanian Text Using Formal Rules Informatica (lithuanian Academy of Sciences). ,vol. 10, pp. 367- 376 ,(1999) , 10.3233/INF-1999-10401
K. Ratkevičius, V. Rudžionis, R. Maskeliūnas, A. Rudžionis, Investigation of Foreign Languages Models for Lithuanian Speech Recognition Elektronika Ir Elektrotechnika. ,vol. 91, pp. 15- 20 ,(2009) , 10.5755/J01.EEE.91.3.10271
Pijus Kasparaitis, Lithuanian Speech Recognition Using the English Recognizer Informatica (lithuanian Academy of Sciences). ,vol. 19, pp. 505- 516 ,(2008) , 10.15388/INFORMATICA.2008.227
Tomas Rasymas, Vytautas Rudžionis, Evaluation of methods to combine different speech recognizers federated conference on computer science and information systems. ,vol. 5, pp. 1043- 1047 ,(2015) , 10.15439/2015F62
V. Rudzionis, G. Raskinis, R. Maskeliunas, A. Rudzionis, K. Ratkevicius, G. Bartisiute, Web Services Based Hybrid Recognizer of Lithuanian Voice Commands Elektronika Ir Elektrotechnika. ,vol. 20, pp. 50- 53 ,(2014) , 10.5755/J01.EEE.20.9.8713
Tanja Schultz, Alex Waibel, Language-independent and language-adaptive acoustic modeling for speech recognition Speech Communication. ,vol. 35, pp. 31- 51 ,(2001) , 10.1016/S0167-6393(00)00094-7
Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Andreas Müller, Joel Nothman, Gilles Louppe, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, Édouard Duchesnay, Scikit-learn: Machine Learning in Python Journal of Machine Learning Research. ,vol. 12, pp. 2825- 2830 ,(2011)
Martin Lojka, Jozef Juhar, Hypothesis combination for Slovak dictation speech recognition international symposium elmar. pp. 1- 4 ,(2014) , 10.1109/ELMAR.2014.6923311