Petr Cerva

Publication Activity (10 Years)

Years Active: 2005-2023
Publications (10 Years): 27

Top Topics

Keyword Spotting

Speech Activity Detection

Robust Recognition

Top Venues

Publications

Jan Nouza, Lukás Mateju, Petr Cerva, Jindrich Zdánský
Developing State-of-the-Art End-to-End ASR for Norwegian. TSD (2023)
Frantisek Kynych, Jindrich Zdánský, Petr Cerva, Lukás Mateju
Online Speaker Diarization Using Optimized SE-ResNet Architecture. TSD (2023)
Martin Polácek, Petr Cerva, Jindrich Zdánský, Lenka Weingartová
Online Punctuation Restoration using ELECTRA Model for streaming ASR Systems. INTERSPEECH (2023)
Lukás Mateju, Jan Nouza, Petr Cerva, Jindrich Zdánský, Frantisek Kynych
Combining Multilingual Resources and Models to Develop State-of-the-Art E2E ASR for Swedish. INTERSPEECH (2023)
Lukás Mateju, Frantisek Kynych, Petr Cerva, Jirí Málek, Jindrich Zdánský
Overlapped Speech Detection in Broadcast Streams Using X-vectors. INTERSPEECH (2022)
Jan Nouza, Petr Cerva, Jindrich Zdánský
Lexicon-based vs. Lexicon-free ASR for Norwegian Parliament Speech Transcription. TSD (2022)
Petr Cerva, Lukás Mateju, Frantisek Kynych, Jindrich Zdánský, Jan Nouza
Identification of Scandinavian Languages from Speech Using Bottleneck Features and X-Vectors. TDS (2021)
Lukás Mateju, Frantisek Kynych, Petr Cerva, Jindrich Zdánský, Jirí Málek
Using X-Vectors for Speech Activity Detection in Broadcast Streams. Interspeech (2021)
Petr Cerva, Lukás Mateju, Jindrich Zdánský, Radek Safarík, Jan Nouza
Identification of related languages from spoken data: Moving from off-line to on-line scenario. Comput. Speech Lang. 68 (2021)
Petr Cerva, Veronika Volna, Lenka Weingartová
Dealing with Newly Emerging OOVs in Broadcast Programs by Daily Updates of the Lexicon and Language Model. SPECOM (2020)
Josef Chaloupka, Karel Palecek, Petr Cerva, Jindrich Zdánský
Optical Character Recognition for Audio-Visual Broadcast Transcription System. CogInfoCom (2020)
Jan Nouza, Petr Cerva, Jindrich Zdánský
Very Fast Keyword Spotting System with Real Time Factor Below 0.01. TDS (2020)
Jan Nouza, Petr Cerva, Jindrich Zdánský
Very Fast Keyword Spotting System with Real Time Factor below 0.01. CoRR (2020)
Lukás Mateju, Petr Cerva, Jindrich Zdánský
An Approach to Online Speaker Change Point Detection Using DNNs and WFSTs. INTERSPEECH (2019)
Lukás Mateju, Petr Cerva, Jindrich Zdánský, Radek Safarík
Using Deep Neural Networks for Identification of Slavic Languages from Acoustic Signal. INTERSPEECH (2018)
Jirí Málek, Jindrich Zdánský, Petr Cerva
Robust Recognition of Conversational Telephone Speech via Multi-condition Training and Data Augmentation. TSD (2018)
Jirí Málek, Jindrich Zdánský, Petr Cerva
Robust Recognition of Speech with Background Music in Acoustically Under-Resourced Scenarios. ICASSP (2018)
Lukás Mateju, Petr Cerva, Jindrich Zdánský, Jirí Málek
Speech Activity Detection in online broadcast transcription using Deep Neural Networks and Weighted Finite State Transducers. ICASSP (2017)
Jirí Málek, Jindrich Zdánský, Petr Cerva
Robust Automatic Recognition of Speech with background music. ICASSP (2017)
Michal Rott, Petr Cerva
Speech-to-Text Summarization Using Automatic Phrase Extraction from Recognized Text. TSD (2016)
Jirí Málek, Petr Cerva, Ladislav Seps, Jan Nouza
Study on the Use and Adaptation of Bottleneck Features for Robust Speech Recognition of Nonlinearly Distorted Speech. SIGMAP (2016)
Lukás Mateju, Petr Cerva, Jindrich Zdánský
Investigation into the Use of WFSTs and DNNs for Speech Activity Detection in Broadcast Data Transcription. ICETE (Selected Papers) (2016)
Jan Nouza, Radek Safarík, Petr Cerva
ASR for South Slavic Languages Developed in Almost Automated Way. INTERSPEECH (2016)
Lukás Mateju, Petr Cerva, Jindrich Zdánský
Study on the Use of Deep Neural Networks for Speech Activity Detection in Broadcast Recordings. SIGMAP (2016)
Jan Nouza, Petr Cerva, Radek Safarík
Cross-Lingual Adaptation of Broadcast Transcription System to Polish Language Using Public Data Sources. LTC (2015)
Jan Nouza, Karel Blavka, Marek Bohac, Petr Cerva, Jirí Málek
System for producing subtitles to internet audio-visual documents. TSP (2015)
Jirí Málek, Jan Silovský, Petr Cerva, Zbynek Koldovský, Jan Nouza, Jindrich Zdánský
Compensation of nonlinear distortions in speech for automatic recognition. TSP (2015)
Michal Rott, Petr Cerva
Investigation of Latent Semantic Analysis for Clustering of Czech News Articles. DEXA Workshops (2014)
Jan Nouza, Petr Cerva, Jindrich Zdánský, Karel Blavka, Marek Bohac, Jan Silovský, Josef Chaloupka, Michaela Kucharová, Ladislav Seps, Jirí Málek, Michal Rott
Speech-to-text technology to transcribe and disclose 100, 000+ hours of bilingual documents from historical Czech and Czechoslovak radio archive. INTERSPEECH (2014)
Ladislav Seps, Jirí Málek, Petr Cerva, Jan Nouza
Investigation of deep neural networks for robust recognition of nonlinearly distorted speech. INTERSPEECH (2014)
Marek Bohac, Michaela Kucharová, Zoraida Callejas, Jan Nouza, Petr Cerva
A cross-lingual adaptation approach for rapid development of speech recognizers for learning disabled users. EURASIP J. Audio Speech Music. Process. 2014 (2014)
Petr Cerva, Jan Silovský, Jindrich Zdánský, Jan Nouza, Ladislav Seps
Speaker-adaptive speech recognition using speaker diarization for improved transcription of large spoken archives. Speech Commun. 55 (10) (2013)
Jan Nouza, Petr Cerva, Jan Silovský
Dealing with Bilingualism in Automatic Transcription of Historical Archive of Czech Radio. ICIAP Workshops (2013)
Michal Rott, Petr Cerva
SummEC: A Summarization Engine for Czech. TSD (2013)
Jan Nouza, Petr Cerva, Jan Silovský
Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech. ICASSP (2013)
Josef Chaloupka, Jan Nouza, Petr Cerva, Jirí Málek
Downdating Lexicon and Language Model for Automatic Transcription of Czech Historical Spoken Documents. TSD (2013)
Michaela Kucharová, Jan Nouza, Petr Cerva
Impact of microphone on computer applications with voice input modality. TSP (2013)
Jan Nouza, Karel Blavka, Jindrich Zdánský, Petr Cerva, Jan Silovský, Marek Bohac, Josef Chaloupka, Michaela Kucharová, Ladislav Seps
Large-scale processing, indexing and search system for Czech audio-visual cultural heritage archives. MMSP (2012)
Jan Silovský, Jindrich Zdánský, Jan Nouza, Petr Cerva, Jan Prazak
Incorporation of the ASR output in speaker segmentation and clustering within the task of speaker diarization of broadcast streams. MMSP (2012)
Jan Nouza, Karel Blavka, Petr Cerva, Jindrich Zdánský, Jan Silovský, Marek Bohac, Jan Prazak
Making Czech Historical Radio Archive Accessible and Searchable for Wide Public. J. Multim. 7 (2) (2012)
Jan Silovský, Petr Cerva, Jindrich Zdánský, Jan Nouza
Study on Integration of Speaker Diarization with Speaker Adaptive Speech Recognition for Broadcast Transcription. INTERSPEECH (2012)
Petr Cerva, Jan Silovský, Jindrich Zdánský, Jan Nouza, Jirí Málek
Real-Time Lecture Transcription using ASR for Czech Hearing Impaired or Deaf Students. INTERSPEECH (2012)
Petr Cerva, Jan Silovský, Jindrich Zdánský, Ondrej Smola, Karel Blavka, Karel Palecek, Jan Nouza, Jirí Málek
Browsing, indexing and automatic transcription of lectures for distance learning. MMSP (2012)
Jan Nouza, Karel Blavka, Marek Bohac, Petr Cerva, Jindrich Zdánský, Jan Silovský, Jan Prazak
Voice Technology to Enable Sophisticated Access to Historical Audio Archive of the Czech Radio. MM4CH (2011)
Jan Silovský, Jan Prazak, Petr Cerva, Jindrich Zdánský, Jan Nouza
PLDA-Based Clustering for Speaker Diarization of Broadcast Streams. INTERSPEECH (2011)
Jan Nouza, Petr Cerva, Josef Chaloupka
Rainbow Bridge - Training Center based on Voice Technology for People with Physical Disabilities. HEALTHINF (2011)
Petr Cerva, Karel Palecek, Jan Silovský, Jan Nouza
Using Unsupervised Feature-Based Speaker Adaptation for Improved Transcription of Spoken Archives. INTERSPEECH (2011)
Petr Cerva, Jan Nouza, Jan Silovský
Study on Cross-Lingual Adaptation of a Czech LVCSR System towards Slovak. COST 2102 Conference (2010)
Jan Nouza, Petr Cerva, Jindrich Zdánský
Very large vocabulary voice dictation for mobile devices. INTERSPEECH (2009)
Jan Nouza, Jindrich Zdánský, Petr Cerva, Jan Silovský
Challenges in Speech Processing of Slavic Languages (Case Studies in Speech Recognition of Czech and Slovak). COST 2102 Training School (2009)
Jan Silovský, Petr Cerva, Jindrich Zdánský
MLLR Transforms Based Speaker Recognition in Broadcast Streams. COST 2102 Conference (Prague) (2008)
Jan Nouza, Jan Silovský, Jindrich Zdánský, Petr Cerva, Martin Kroul, Josef Chaloupka
Czech-to-slovak adapted broadcast news transcription system. INTERSPEECH (2008)
Josef Chaloupka, Jan Nouza, Jindrich Zdánský, Petr Cerva, Jan Silovský, Martin Kroul
Voice Technology Applied for Building a Prototype Smart Room. COST 2102 School (Vietri) (2008)
Petr Cerva, Jindrich Zdánský, Jan Silovský, Jan Nouza
Study on Speaker Adaptation Methods in the Broadcast News Transcription Task. TSD (2008)
Petr Cerva, Jan Nouza
Design and development of voice controlled aids for motor-handicapped persons. INTERSPEECH (2007)
Zoraida Callejas, Jan Nouza, Petr Cerva, Ramón López-Cózar
MyVoice goes Spanish. Cross-lingual Adaptation of a Voice Controlled PC Tool for Handicapped People. Proces. del Leng. Natural 39 (2007)
Petr Cerva, Jan Nouza, Jan Silovský
Two-step unsupervised speaker adaptation based on speaker and gender recognition and HMM combination. INTERSPEECH (2006)
Jan Nouza, Jindrich Zdánský, Petr Cerva, Jan Kolorenc
A System for Information Retrieval from Large Records of Czech Spoken Data. TSD (2006)
Jan Nouza, Jindrich Zdánský, Petr Cerva, Jan Kolorenc
Continual on-line monitoring of Czech spoken broadcast programs. INTERSPEECH (2006)
Jan Nouza, Jindrich Zdánský, Petr David, Petr Cerva, Jan Kolorenc, Dana Nejedlová
Fully automated system for Czech spoken broadcast transcription with very large (300k+) lexicon. INTERSPEECH (2005)
Petr Cerva, Jan Nouza
Supervised and Unsupervised Speaker Adaptation in Large Vocabulary Continuous Speech Recognition of Czech. TSD (2005)