Detail projektu

IARPA Building Speech Recognition for Keyword Search in a New Language in a Week with Limited Training Data (BABEL) - Babelon

Období řešení: 5. 3. 2012 - 4. 11. 2016

Typ projektu: smluvní výzkum

Kód: W911NF-12-C-0

Objednatel: Raytheon BBN Technologies Corp.

Název česky
IARPA Tvorba rozpoznávačů řeči pro vyhledávání klíčových slov v novém jazyce s omezenými trénovacími daty za týden (BABEL) - Babelon
Typ
smluvní výzkum
Abstrakt

Cílem Babel programu je vyvinout agilní a robustní technologii pro rozpoznávání řeči, která může být rychle aplikována na jakoukoli mluvenou řeč, tak aby poskytla účinnou vyhledávací kapacitu analytikům pro efektivní zpracování záznamů velmi objemných souborů dat spontánní řeči.

Řešitelé
Matějka Pavel, Ing., Ph.D. (UPGM FIT VUT) , hlavní řešitel
Burget Lukáš, doc. Ing., Ph.D. (UPGM FIT VUT) , spoluřešitel
Černocký Jan, prof. Dr. Ing. (UPGM FIT VUT) , spoluřešitel
Glembek Ondřej, Ing., Ph.D. (UPGM FIT VUT) , spoluřešitel
Grézl František, Ing., Ph.D. (UPGM FIT VUT) , spoluřešitel
Hannemann Mirko, Dipl.-Ing. (UPGM FIT VUT) , spoluřešitel
Karafiát Martin, Ing., Ph.D. (UPGM FIT VUT) , spoluřešitel
Plchot Oldřich, Ing., Ph.D. (UPGM FIT VUT) , spoluřešitel
Szőke Igor, Ing., Ph.D. (UPGM FIT VUT) , spoluřešitel
Andrla Petr, Ing. (UPGM FIT VUT)
Cipr Tomáš, Ing. (UPGM FIT VUT)
Kesiraju Santosh (IIIT)
Novotný Ondřej, Ing., Ph.D. (UPGM FIT VUT)
Ondel Yang Lucas Antoine Francois, Mgr., Ph.D. (UPGM FIT VUT)
Skála František, Ing. (UPGM FIT VUT)
Veselý Karel, Ing., Ph.D. (UPGM FIT VUT)
Publikace

2017

  • KARAFIÁT Martin, BASKAR Murali K., MATĚJKA Pavel, VESELÝ Karel, GRÉZL František, BURGET Lukáš a ČERNOCKÝ Jan. 2016 BUT Babel system: Multilingual BLSTM acoustic model with i-vector based adaptation. In: Proceedings of Interspeech 2017. Stockholm: International Speech Communication Association, 2017, s. 719-723. ISSN 1990-9772. Detail

2016

  • BRUMMER Johan Nikolaas Langenhoven, SWART Albert du Preez, PRIETO Jesús J., GARCIA Perera Leibny Paola, MATĚJKA Pavel, PLCHOT Oldřich, DIEZ Sánchez Mireia, SILNOVA Anna, JIANG Xiaowei, NOVOTNÝ Ondřej, ROHDIN Johan A., GLEMBEK Ondřej, GRÉZL František, BURGET Lukáš, ONDEL Yang Lucas Antoine Francois, PEŠÁN Jan, ČERNOCKÝ Jan, KENNY Patrick, ALAM Jahangir, BHATTACHARYA Gautam a ZEINALI Hossein a kol. ABC NIST SRE 2016 SYSTEM DESCRIPTION. San Diego: National Institute of Standards and Technology, 2016. Detail
  • MATĚJKA Pavel, GLEMBEK Ondřej, NOVOTNÝ Ondřej, PLCHOT Oldřich, GRÉZL František, BURGET Lukáš a ČERNOCKÝ Jan. Analysis Of DNN Approaches To Speaker Identification. In: Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016. Shanghai: IEEE Signal Processing Society, 2016, s. 5100-5104. ISBN 978-1-4799-9988-0. Detail
  • NOVOTNÝ Ondřej, MATĚJKA Pavel, GLEMBEK Ondřej, PLCHOT Oldřich, GRÉZL František, BURGET Lukáš a ČERNOCKÝ Jan. Analysis of the DNN-Based SRE Systems in Multi-language Conditions. In: Proceedings of SLT 2016. San Diego: IEEE Signal Processing Society, 2016, s. 199-204. ISBN 978-1-5090-4903-5. Detail
  • PLCHOT Oldřich, MATĚJKA Pavel, FÉR Radek, GLEMBEK Ondřej, NOVOTNÝ Ondřej, PEŠÁN Jan, VESELÝ Karel, ONDEL Yang Lucas Antoine Francois, KARAFIÁT Martin, GRÉZL František, KESIRAJU Santosh, BURGET Lukáš, BRUMMER Johan Nikolaas Langenhoven, SWART Albert du Preez, CUMANI Sandro, MALLIDI Sri Harish a LI Ruizhi. BAT System Description for NIST LRE 2015. In: Proceedings of Odyssey 2016, The Speaker and Language Recognition Workshop. Bilbao: International Speech Communication Association, 2016, s. 166-173. ISSN 2312-2846. Detail
  • GRÉZL František a KARAFIÁT Martin. Boosting Performance on Low-resource Languages by Standard Corpora: AN ANALYSIS. In: Proceeding of SLT 2016. San Diego: IEEE Signal Processing Society, 2016, s. 629-636. ISBN 978-1-5090-4903-5. Detail
  • GRÉZL František a KARAFIÁT Martin. Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting. In: Procedia Computer Science. Yogyakarta: Elsevier Science, 2016, s. 144-151. ISSN 1877-0509. Detail
  • KARAFIÁT Martin, BASKAR Murali K., MATĚJKA Pavel, VESELÝ Karel, GRÉZL František a ČERNOCKÝ Jan. Multilingual BLSTM and Speaker-Specific Vector Adaptation in 2016 BUT BABEL SYSTEM. In: Proceedings of SLT 2016. San Diego: IEEE Signal Processing Society, 2016, s. 637-643. ISBN 978-1-5090-4903-5. Detail
  • KARAFIÁT Martin, BURGET Lukáš, GRÉZL František, VESELÝ Karel a ČERNOCKÝ Jan. Multilingual Region-Dependent Transforms. In: Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016. Shanghai: IEEE Signal Processing Society, 2016, s. 5430-5434. ISBN 978-1-4799-9988-0. Detail
  • GRÉZL František, EGOROVA Ekaterina a KARAFIÁT Martin. Study of Large Data Resources for Multilingual Training and System Porting. In: Procedia Computer Science. Yogyakarta: Elsevier Science, 2016, s. 15-22. ISSN 1877-0509. Detail
  • KARAFIÁT Martin. Summary report for project "Multilingual speech recognition" in Year 2016. Brno: Raytheon BBN Technologies Corp., 2016. Detail

2015

  • MALLIDI Sri Harish, OGAWA Tetsuji, VESELÝ Karel, NIDADAVOLU Phani S. a HEŘMANSKÝ Hynek. Autoencoder based multi-stream combination for noise robust speech recognition. In: Proceeding of Interspeech 2015. Dresden: International Speech Communication Association, 2015, s. 3551-3555. ISBN 978-1-5108-1790-6. ISSN 1990-9772. Detail
  • PEŠÁN Jan, BURGET Lukáš, HEŘMANSKÝ Hynek a VESELÝ Karel. DNN derived filters for processing of modulation spectrum of speech. In: Proceedings of Interspeech 2015. Dresden: International Speech Communication Association, 2015, s. 1908-1911. ISBN 978-1-5108-1790-6. ISSN 1990-9772. Detail
  • FÉR Radek, MATĚJKA Pavel, GRÉZL František, PLCHOT Oldřich a ČERNOCKÝ Jan. Multilingual Bottleneck Features for Language Recognition. In: Proceedings of Interspeech 2015. Dresden: International Speech Communication Association, 2015, s. 389-393. ISBN 978-1-5108-1790-6. ISSN 1990-9772. Detail
  • HSIAO Roger, MA Jeff, HARTMANN William, KARAFIÁT Martin, GRÉZL František, BURGET Lukáš, SZŐKE Igor, ČERNOCKÝ Jan, WATANABE Shinji, CHEN Zhuo, MALLIDI Sri Harish, HEŘMANSKÝ Hynek, TSAKALIDIS Stavros a SCHWARTZ Richard. Robust Speech Recognition in Unknown Reverberant and Noisy Conditions. In: Proceedings of 2015 IEEE Automatic Speech Recognition and Understanding Workshop. Scottsdale, Arizona: IEEE Signal Processing Society, 2015, s. 533-538. ISBN 978-1-4799-7291-3. Detail
  • KARAFIÁT Martin, GRÉZL František, HANNEMANN Mirko a VESELÝ Karel. Summary report for project "Multilingual speech recognition" in Year 2015. Brno: Raytheon BBN Technologies Corp., 2015. Detail
  • HEŘMANSKÝ Hynek, BURGET Lukáš, COHEN Jordan, DUPOUX Emmanuel, FELDMAN Naomi, GODFREY John, KHUDANPUR Sanjeev, MACIEJEWSKI Matthew, MALLIDI Sri Harish, MENON Anjali, OGAWA Tetsuji, PEDDINTI Vijayaditya, ROSE Richard, STERN Richard, WIESNER Matthew a VESELÝ Karel. TOWARDS MACHINES THAT KNOW WHEN THEY DO NOT KNOW: SUMMARY OF WORK DONE AT 2014 FREDERICK JELINEK MEMORIAL WORKSHOP. In: Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing. South Brisbane, Queensland: IEEE Signal Processing Society, 2015, s. 5009-5013. ISBN 978-1-4673-6997-8. Detail

2014

  • KARAFIÁT Martin. 2014 Summary report of project "Processing and analysis of speech, automatic speaker identification". Brno: Raytheon BBN Technologies Corp., 2014. Detail
  • GRÉZL František, KARAFIÁT Martin a VESELÝ Karel. Adaptation of Multilingual Stacked Bottle-neck Neural Network Structure for New Language. In: Proceedings of ICASSP 2014. Florencie: IEEE Signal Processing Society, 2014, s. 7704-7708. ISBN 978-1-4799-2892-7. Detail
  • GRÉZL František a KARAFIÁT Martin. Adapting Multilingual Neural Network Hierarchy to a New Language. In: Proceedings of the 4th International Workshop on Spoken Language Technologies for Under- resourced Languages SLTU-2014. – St. Petersburg, Russia, 2014. St. Petersburg: International Speech Communication Association, 2014, s. 39-45. ISBN 978-5-8088-0908-6. Detail
  • KARAFIÁT Martin, GRÉZL František, VESELÝ Karel, HANNEMANN Mirko, SZŐKE Igor a ČERNOCKÝ Jan. BUT 2014 Babel System: Analysis of adaptation in NN based systems. In: Proceedings of Interspeech 2014. Singapore: International Speech Communication Association, 2014, s. 3002-3006. ISBN 978-1-63439-435-2. Detail
  • KARAFIÁT Martin, VESELÝ Karel, SZŐKE Igor, BURGET Lukáš, GRÉZL František, HANNEMANN Mirko a ČERNOCKÝ Jan. BUT ASR System for BABEL Surprise Evaluation 2014. In: Proceedings of 2014 Spoken Language Technology Workshop. South Lake Tahoe, Nevada: IEEE Signal Processing Society, 2014, s. 501-506. ISBN 978-1-4799-7129-9. Detail
  • KARAFIÁT Martin, GRÉZL František, HANNEMANN Mirko a ČERNOCKÝ Jan. BUT Neural Network Features for Spontaneous Vietnamese in BABEL. In: Proceedings of ICASSP 2014. Florencie: IEEE Signal Processing Society, 2014, s. 5659-5663. ISBN 978-1-4799-2892-7. Detail
  • GRÉZL František a KARAFIÁT Martin. Combination of Multilingual and Semi-Supervised Training for Under-Resourced Languages. In: Proceedings of Interspeech 2014. Singapore: International Speech Communication Association, 2014, s. 820-824. ISBN 978-1-63439-435-2. Detail
  • GRÉZL František, EGOROVA Ekaterina a KARAFIÁT Martin. Further Investigation into Multilingual Training and Adaptation of Stacked Bottle-neck Neural Network Structure. In: Proceedings of 2014 Spoken Language Technology Workshop. South Lake Tahoe, Nevada: IEEE Signal Processing Society, 2014, s. 48-53. ISBN 978-1-4799-7129-9. Detail

2013

  • BURGET Lukáš, PLCHOT Oldřich a SZŐKE Igor. 2013 Summary report of project "Processing and analysis of speech, automatic speaker identification". Brno: Raytheon BBN Technologies Corp., 2013. Detail
  • LEI Yun, BURGET Lukáš a SCHEFFER Nicolas. A Noise Robust I-Vector Extractor Using Vector Taylor Series For Speaker Recognition. In: Proceedings of ICASSP 2013. Vancouver: IEEE Signal Processing Society, 2013, s. 6788-6791. ISBN 978-1-4799-0355-9. Detail
  • KARAFIÁT Martin, GRÉZL František, HANNEMANN Mirko, VESELÝ Karel a ČERNOCKÝ Jan. BUT BABEL System for Spontaneous Cantonese. In: Proceedings of Interspeech 2013. Lyon: International Speech Communication Association, 2013, s. 2589-2593. ISBN 978-1-62993-443-3. ISSN 2308-457X. Detail
  • HANNEMANN Mirko, POVEY Daniel a ZWEIG Geoffrey. Combining Forward and Backward Search in Decoding. In: Proceedings of ICASSP 2013. Vancouver: IEEE Signal Processing Society, 2013, s. 6739-6743. ISBN 978-1-4799-0355-9. Detail
  • HSIAO Roger, NG Tim, GRÉZL František, KARAKOS Damianos, TSAKALIDIS Stavros, NGUYEN Long a SCHWARTZ Richard. Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages. In: Proceedings of ASRU 2013. Olomouc: IEEE Signal Processing Society, 2013, s. 440-445. ISBN 978-1-4799-2755-5. Detail
  • KARAKOS Damianos, SCHWARTZ Richard, TSAKALIDIS Stavros, ZHANG Le, RANJAN Shivesh, NG Tim, HSIAO Roger, NGUYEN Long, GRÉZL František, HANNEMANN Mirko, KARAFIÁT Martin, SZŐKE Igor a VESELÝ Karel a kol. Score Normalization and System Combination for Improved Keyword Spotting. In: Proceedings of ASRU 2013. Olomouc: IEEE Signal Processing Society, 2013, s. 210-215. ISBN 978-1-4799-2755-5. Detail
  • GRÉZL František a KARAFIÁT Martin. Semi-Supervised Bootstrapping Approach For Neural Network Feature Extractor Training. In: Proceedings of ASRU 2013. Olomouc: IEEE Signal Processing Society, 2013, s. 470-475. ISBN 978-1-4799-2755-5. Detail
  • VESELÝ Karel, HANNEMANN Mirko a BURGET Lukáš. Semi-supervised Training of Deep Neural Networks. In: Proceedings of ASRU 2013. Olomouc: IEEE Signal Processing Society, 2013, s. 267-272. ISBN 978-1-4799-2755-5. Detail
  • VESELÝ Karel, GHOSHAL Arnab, BURGET Lukáš a POVEY Daniel. Sequence-discriminative Training of Deep Neural Networks. In: Proceedings of Interspeech 2013. Lyon: International Speech Communication Association, 2013, s. 2345-2349. ISBN 978-1-62993-443-3. ISSN 2308-457X. Detail

2012

  • BURGET Lukáš, GLEMBEK Ondřej, MATĚJKA Pavel a PLCHOT Oldřich. 2012 Summary report of project "Processing and analysis of speech, automatic speaker identification". Cambridge: Raytheon BBN Technologies Corp., 2012. Detail
  • VESELÝ Karel, KARAFIÁT Martin, GRÉZL František, JANDA Miloš a EGOROVA Ekaterina. The Language-Independent Bottleneck Features. In: Proceedings of IEEE 2012 Workshop on Spoken Language Technology. Miami: IEEE Signal Processing Society, 2012, s. 336-341. ISBN 978-1-4673-5124-9. Detail
Nahoru