Project Details

Jazykově nezávislá detekce klíčových slov

Project Period: 1. 1. 2012 – 31. 12. 2014

Project Type: grant

Code: GPP202/12/P567

Agency: Czech Science Foundation

Program: Postdoktorandské granty

English title
Language-independent spoken term detection
Type
grant
Keywords

keyword spotting, query-by-example, language independent, hidden Markov models, artificial neural network

Abstract

This project aims at research and development of language-independent keyword spotter in spoken speech. The keywords will be entered as examples (Query-by-Example). The application of project results is in search in speech where current approaches fail: exotic languages (insufficient or no training data) and recordings where speakers change language within the conversation. The first goal is to define evaluation data for several languages and to evaluate the state-of-the-art Query-by-Example systems in cross-lingual environment. Main goals are: (1) to design and evaluate an approach to language-independent high-level feature extraction from speech. We will use combination of several language-dependent artificial neural network classifiers. (2) To design and evaluate a GMM/HMM approach to Query-by-Example. It will be important to correctly estimate the keyword model on several examples and to investigate training of the universal background model. We will also compare achieved results with standard language-dependent approaches.

Team members
Szőke Igor, Ing., Ph.D. (DCGM) – research leader
Janda Miloš, Ing.
Veselý Karel, Ing., Ph.D. (DCGM)
Publications

2015

  • ANGUERA, X.; RODRIGUEZ-FUENTES, L.; BUZO, A.; METZE, F.; SZŐKE, I.; PENAGARIKANO, M. QUESST 2014: Evaluating Query-By-Example Speech Search in a Zero-Resource. In Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing. South Brisbane, Queensland: IEEE Signal Processing Society, 2015. p. 5833-5837. ISBN: 978-1-4673-6997-8. Detail
  • SZŐKE, I.; SKÁCEL, M.; ČERNOCKÝ, J.; BURGET, L. Coping with Channel Mismatch in Query-By-Example - BUT QUESST 2014. In Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing. South Brisbane, Queensland: IEEE Signal Processing Society, 2015. p. 5838-5842. ISBN: 978-1-4673-6997-8. Detail

2014

  • ANGUERA, X.; RODRIGUEZ-FUENTES, L.; SZŐKE, I.; BUZO, A.; METZE, F. Query-by-example Spoken Term Detection Evaluation on Low-resource Languages. Proceedings of the 4th International Workshop on Spoken Language Technologies for Under- resourced Languages SLTU-2014. St. Petersburg, Russia. St. Petersburg: International Speech Communication Association, 2014. p. 24-31. ISBN: 978-5-8088-0908-6. Detail
  • ANGUERA, X.; RODRIGUEZ-FUENTES, L.; SZŐKE, I.; BUZO, A.; METZE, F. Query by Example Search on Speech at Mediaeval 2014. In CEUR Workshop Proceedings. CEUR Workshop Proceedings. Barcelona: CEUR-WS.org, 2014. p. 1-2. ISSN: 1613-0073. Detail
  • SZŐKE, I.; BURGET, L.; GRÉZL, F.; ČERNOCKÝ, J.; ONDEL YANG, L. Calibration and Fusion of Query-by-example Systems - BUT SWS 2013. In Proceedings of ICASSP 2014. Florencie: IEEE Signal Processing Society, 2014. p. 7899-7903. ISBN: 978-1-4799-2892-7. Detail
  • SZŐKE, I.; SKÁCEL, M.; BURGET, L. BUT QUESST 2014 System Description. In CEUR Workshop Proceedings. CEUR Workshop Proceedings. Barcelona: CEUR-WS.org, 2014. p. 1-2. ISSN: 1613-0073. Detail

2013

  • ANGUERA, X.; METZE, F.; BUZO, A.; SZŐKE, I.; RODRIGUEZ-FUENTES, L. The Spoken Web Search Task. CEUR Workshop Proceedings. CEUR Workshop Proceedings. Barcelona: CEUR-WS.org, 2013. p. 1-2. ISSN: 1613-0073. Detail
  • SZŐKE, I.; BURGET, L.; GRÉZL, F.; ONDEL YANG, L. BUT SWS 2013 - Massive Parallel Approach. In Proceedings of the MediaEval 2013 Multimedia Benchmark Workshop. CEUR Workshop Proceedings. Barcelona: CEUR-WS.org, 2013. p. 1-2. ISSN: 1613-0073. Detail

2012

  • SZŐKE, I.; FAPŠO, M.; VESELÝ, K. BUT2012 přístup pro Spoken Web Search úkol na MediaEval2012. Working Notes Proceedings of the MediaEval 2012 Workshop. CEUR Workshop Proceedings. Pisa: CEUR-WS.org, 2012. s. 1-2. ISSN: 1613-0073. Detail
  • SZŐKE, I.; FAPŠO, M.; ŽIŽKA, J.; BERAN, V.; ČERNOCKÝ, J. Efektivní přístup ke znalostem v audio-vizuálních záznamech. Proceedings of the Annual Database Conference. Praha: Technická univerzita v Košiciach, 2012. s. 57-74. ISBN: 978-80-553-1049-7. Detail
  • TEJEDOR, J.; FAPŠO, M.; SZŐKE, I.; ČERNOCKÝ, J.; GRÉZL, F. Comparison of methods for language-dependent and language-independent query-by-example spoken term detection. ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2012, vol. 2012, no. 30, p. 1-34. ISSN: 1046-8188. Detail
Back to top