Department of Computer Graphics and Multimedia

Big speech data analytics for contact centers

Czech title:Analytika velkých řečových dat pro kontaktní centra
Reseach leader:Černocký Jan
Team leaders:Burget Lukáš
Team members:Beneš Karel, Cao Yujia, Grézl František, Hannemann Mirko, Matějka Pavel, Mošner Ladislav (FIT VUT), Nathans Riva (UPGM FIT VUT), Žmolíková Kateřina
Agency:European Comission EU - Horizon 2020
Code:645523
Start:2015-01-01
End:2017-12-31
Keywords:contact centres, speech data mining, big data, speech recognition, keyword spotting
Annotation:
Contact centers (CC) are an important business for Europe: 35,000 contact centers generate 3.2 Million jobs (~1% of Europes active population). A typical CC produces a wealth of multilingual spoken data that is nowadays mined by humans (CC agents and supervisors) or by rudimentary technical means. BISON consortium plans to bring significant innovations in three areas: (1) basic speech data mining technologies (systems quickly adaptable to new languages, domains and CC campaigns), (2) business outcome mining from speech (translated into improvement of CCs Key Performance Indicators) and (3) CC support systems integrating both speech and business outcome mining in user-friendly way. The project will produce two prototypes: smallBison (end of the 1st year) will be a functioning system for real, though limited, deployment and user feedback collection. bigBison (end of the project) will include full range of capabilities and be fully integrated with CC hardware and software infrastructure. Generation of business outputs will be demonstrated on real data. Business indicators and values for the market were instrumental for the definition of the project and will be crucial for project execution. BISON consortium is composed of eight players with complementary skills. Two end users running large CC operations (EBOS, Atento) are generating user requirements and are ready to deploy the prototypes immediately in real scenarios. Phonexia (the coordinator), Brno University of Technology and Telefónica I+D are experts in speech data mining - from R&D, data processing to developing products placed on the market. Telefónica Móviles is an expert in business outcome mining and MyForce is a skilled Contact Center hardware and software integrator. CC data involve a number of legal issues, therefore, the University of Bologna (with significant experience in regulatory and legal aspects) complements the consortium.
Project description:
The objective of BISON is to create a multi-lingual, modular and highly versatile system for big speech data analytics in contact centers.

Publications

2017BASKAR Murali K., KARAFIÁT Martin, BURGET Lukáš, VESELÝ Karel, GRÉZL František and ČERNOCKÝ Jan. Residual Memory Networks: Feed-forward approach to learn long-term temporal dependencies. In: Proceedings of ICASSP 2017. New Orleans: IEEE Signal Processing Society, 2017, pp. 4810-4814. ISBN 978-1-5090-4117-6.
 ONDEL Lucas, BURGET Lukáš, ČERNOCKÝ Jan and KESIRAJU Santosh. Bayesian phonotactic language model for acoustic unit discovery. In: Proceedings of ICASSP 2017. New Orleans: IEEE Signal Processing Society, 2017, pp. 5750-5754. ISBN 978-1-5090-4117-6.
 ZEINALI Hossein, SAMETI Hossein and BURGET Lukáš. HMM-Based Phrase-Independent i-Vector Extractor for Text-Dependent Speaker Verification. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING. New York City: IEEE Signal Processing Society, 2017, vol. 25, no. 7, pp. 1421-1435. ISSN 2329-9290.
2016BRUMMER Niko, 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 Lucas, PEŠÁN Jan, ČERNOCKÝ Jan, KENNY Patrick, ALAM Jahangir, BHATTACHARYA Gautam and ZEINALI Hossein et al. ABC NIST SRE 2016 SYSTEM DESCRIPTION. San Diego: National Institute of Standards and Technology, 2016.
 EGOROVA Ekaterina and SERRANO Jordi Lugue. Semi-Supervised Training of Language Model on Spanish Conversational Telephone Speech Data. In: Procedia Computer Science. Yogyakarta: Elsevier Science, 2016, pp. 114-120. ISSN 1877-0509.
 GRÉZL František and KARAFIÁT Martin. Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting. In: Procedia Computer Science. Yogyakarta: Elsevier Science, 2016, pp. 144-151. ISSN 1877-0509.
 GRÉZL František, EGOROVA Ekaterina and KARAFIÁT Martin. Study of Large Data Resources for Multilingual Training and System Porting. In: Procedia Computer Science. Yogyakarta: Elsevier Science, 2016, pp. 15-22. ISSN 1877-0509.
 MATĚJKA Pavel, GLEMBEK Ondřej, NOVOTNÝ Ondřej, PLCHOT Oldřich, GRÉZL František, BURGET Lukáš and 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, pp. 5100-5104. ISBN 978-1-4799-9988-0.
 NOVOTNÝ Ondřej, MATĚJKA Pavel, GLEMBEK Ondřej, PLCHOT Oldřich, GRÉZL František, BURGET Lukáš and 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, pp. 199-204. ISBN 978-1-5090-4903-5.
 ONDEL Lucas, BURGET Lukáš and ČERNOCKÝ Jan. Variational Inference for Acoustic Unit Discovery. In: Procedia Computer Science. Yogyakarta: Elsevier Science, 2016, pp. 80-86. ISSN 1877-0509.
 PEŠÁN Jan, BURGET Lukáš and ČERNOCKÝ Jan. Sequence Summarizing Neural Networks for Spoken Language Recognition. In: Proceedings of Interspeech 2016. San Francisco: International Speech Communication Association, 2016, pp. 3285-3289. ISBN 978-1-5108-3313-5.
 PLCHOT Oldřich, BURGET Lukáš, ARONOWITZ Hagai and MATĚJKA Pavel. Audio Enhancing With DNN Autoencoder For Speaker Recognition. In: Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016. Shanghai: IEEE Signal Processing Society, 2016, pp. 5090-5094. ISBN 978-1-4799-9988-0.
2015GLEMBEK Ondřej, MATĚJKA Pavel, BURGET Lukáš, SCHWARZ Petr, PEŠÁN Jan and PLCHOT Oldřich. Voice-print transformation for migration between automatic speaker identification systems. Abstract book of the 7th European Academy of Forensic Science Conference. Praha: Criminal Police Department Prague, 2015. ISBN 978-80-260-8659-8.
 KARAFIÁT Martin, GRÉZL František, BURGET Lukáš, SZŐKE Igor and ČERNOCKÝ Jan. Three ways to adapt a CTS recognizer to unseen reverberated speech in BUT system for the ASpIRE challenge. In: Proceedings of Interspeech 2015. Dresden: International Speech Communication Association, 2015, pp. 2454-2458. ISBN 978-1-5108-1790-6. ISSN 1990-9772.

Your IPv4 address: 107.22.17.220
Switch to IPv6 connection

DNSSEC [dnssec]