Petr Cerva

According to our database, Petr Cerva authored at least 62 papers between 2005 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2024

A lightweight approach to real-time speaker diarization: from audio toward audio-visual data streams.

Frantisek Kynych, Petr Cerva, Jindrich Zdánský, Torbjørn Svendsen, Giampiero Salvi

EURASIP J. Audio Speech Music. Process., December, 2024

2023

Developing State-of-the-Art End-to-End ASR for Norwegian.

Jan Nouza, Lukás Mateju, Petr Cerva, Jindrich Zdánský

Proceedings of the Text, Speech, and Dialogue - 26th International Conference, 2023

Online Speaker Diarization Using Optimized SE-ResNet Architecture.

Frantisek Kynych, Jindrich Zdánský, Petr Cerva, Lukás Mateju

Proceedings of the Text, Speech, and Dialogue - 26th International Conference, 2023

Online Punctuation Restoration using ELECTRA Model for streaming ASR Systems.

Martin Polácek, Petr Cerva, Jindrich Zdánský, Lenka Weingartová

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Combining Multilingual Resources and Models to Develop State-of-the-Art E2E ASR for Swedish.

Lukás Mateju, Jan Nouza, Petr Cerva, Jindrich Zdánský, Frantisek Kynych

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

2022

Lexicon-based vs. Lexicon-free ASR for Norwegian Parliament Speech Transcription.

Jan Nouza, Petr Cerva, Jindrich Zdánský

Proceedings of the Text, Speech, and Dialogue - 25th International Conference, 2022

Overlapped Speech Detection in Broadcast Streams Using X-vectors.

Lukás Mateju, Frantisek Kynych, Petr Cerva, Jirí Málek, Jindrich Zdánský

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2021

Identification of related languages from spoken data: Moving from off-line to on-line scenario.

Petr Cerva, Lukás Mateju, Jindrich Zdánský, Radek Safarík, Jan Nouza

Comput. Speech Lang., 2021

Identification of Scandinavian Languages from Speech Using Bottleneck Features and X-Vectors.

Petr Cerva, Lukás Mateju, Frantisek Kynych, Jindrich Zdánský, Jan Nouza

Proceedings of the Text, Speech, and Dialogue - 24th International Conference, 2021

Using X-Vectors for Speech Activity Detection in Broadcast Streams.

Lukás Mateju, Frantisek Kynych, Petr Cerva, Jindrich Zdánský, Jirí Málek

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

2020

Very Fast Keyword Spotting System with Real Time Factor Below 0.01.

Jan Nouza, Petr Cerva, Jindrich Zdánský

Proceedings of the Text, Speech, and Dialogue, 2020

Dealing with Newly Emerging OOVs in Broadcast Programs by Daily Updates of the Lexicon and Language Model.

Petr Cerva, Veronika Volna, Lenka Weingartová

Proceedings of the Speech and Computer - 22nd International Conference, 2020

Optical Character Recognition for Audio-Visual Broadcast Transcription System.

Josef Chaloupka, Karel Palecek, Petr Cerva, Jindrich Zdánský

Proceedings of the 11th IEEE International Conference on Cognitive Infocommunications, 2020

2019

An Approach to Online Speaker Change Point Detection Using DNNs and WFSTs.

Lukás Mateju, Petr Cerva, Jindrich Zdánský

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

2018

Robust Recognition of Conversational Telephone Speech via Multi-condition Training and Data Augmentation.

Jirí Málek, Jindrich Zdánský, Petr Cerva

Proceedings of the Text, Speech, and Dialogue - 21st International Conference, 2018

Using Deep Neural Networks for Identification of Slavic Languages from Acoustic Signal.

Lukás Mateju, Petr Cerva, Jindrich Zdánský, Radek Safarík

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

Robust Recognition of Speech with Background Music in Acoustically Under-Resourced Scenarios.

Jirí Málek, Jindrich Zdánský, Petr Cerva

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

Speech Activity Detection in online broadcast transcription using Deep Neural Networks and Weighted Finite State Transducers.

Lukás Mateju, Petr Cerva, Jindrich Zdánský, Jirí Málek

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Robust Automatic Recognition of Speech with background music.

Jirí Málek, Jindrich Zdánský, Petr Cerva

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Speech-to-Text Summarization Using Automatic Phrase Extraction from Recognized Text.

Michal Rott, Petr Cerva

Proceedings of the Text, Speech, and Dialogue - 19th International Conference, 2016

Study on the Use of Deep Neural Networks for Speech Activity Detection in Broadcast Recordings.

Lukás Mateju, Petr Cerva, Jindrich Zdánský

Proceedings of the 13th International Joint Conference on e-Business and Telecommunications (ICETE 2016), 2016

Study on the Use and Adaptation of Bottleneck Features for Robust Speech Recognition of Nonlinearly Distorted Speech.

Jirí Málek, Petr Cerva, Ladislav Seps, Jan Nouza

Proceedings of the 13th International Joint Conference on e-Business and Telecommunications (ICETE 2016), 2016

ASR for South Slavic Languages Developed in Almost Automated Way.

Jan Nouza, Radek Safarík, Petr Cerva

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Investigation into the Use of WFSTs and DNNs for Speech Activity Detection in Broadcast Data Transcription.

Lukás Mateju, Petr Cerva, Jindrich Zdánský

Proceedings of the E-Business and Telecommunications - 13th International Joint Conference, 2016

2015

System for producing subtitles to internet audio-visual documents.

Jan Nouza, Karel Blavka, Marek Bohac, Petr Cerva, Jirí Málek

Proceedings of the 38th International Conference on Telecommunications and Signal Processing, 2015

Compensation of nonlinear distortions in speech for automatic recognition.

Jirí Málek, Jan Silovský, Petr Cerva, Zbynek Koldovský, Jan Nouza, Jindrich Zdánský

Proceedings of the 38th International Conference on Telecommunications and Signal Processing, 2015

Cross-Lingual Adaptation of Broadcast Transcription System to Polish Language Using Public Data Sources.

Jan Nouza, Petr Cerva, Radek Safarík

Proceedings of the Human Language Technology. Challenges for Computer Science and Linguistics, 2015

2014

A cross-lingual adaptation approach for rapid development of speech recognizers for learning disabled users.

Marek Bohac, Michaela Kucharová, Zoraida Callejas, Jan Nouza, Petr Cerva

EURASIP J. Audio Speech Music. Process., 2014

Investigation of deep neural networks for robust recognition of nonlinearly distorted speech.

Ladislav Seps, Jirí Málek, Petr Cerva, Jan Nouza

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Speech-to-text technology to transcribe and disclose 100, 000+ hours of bilingual documents from historical Czech and Czechoslovak radio archive.

Jan Nouza, Petr Cerva, Jindrich Zdánský, Karel Blavka, Marek Bohac, Jan Silovský, Josef Chaloupka, Michaela Kucharová, Ladislav Seps, Jirí Málek, Michal Rott

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Investigation of Latent Semantic Analysis for Clustering of Czech News Articles.

Michal Rott, Petr Cerva

Proceedings of the 25th International Workshop on Database and Expert Systems Applications, 2014

2013

Speaker-adaptive speech recognition using speaker diarization for improved transcription of large spoken archives.

Petr Cerva, Jan Silovský, Jindrich Zdánský, Jan Nouza, Ladislav Seps

Speech Commun., 2013

Impact of microphone on computer applications with voice input modality.

Michaela Kucharová, Jan Nouza, Petr Cerva

Proceedings of the 36th International Conference on Telecommunications and Signal Processing, 2013

SummEC: A Summarization Engine for Czech.

Michal Rott, Petr Cerva

Proceedings of the Text, Speech, and Dialogue - 16th International Conference, 2013

Downdating Lexicon and Language Model for Automatic Transcription of Czech Historical Spoken Documents.

Josef Chaloupka, Jan Nouza, Petr Cerva, Jirí Málek

Proceedings of the Text, Speech, and Dialogue - 16th International Conference, 2013

Dealing with Bilingualism in Automatic Transcription of Historical Archive of Czech Radio.

Jan Nouza, Petr Cerva, Jan Silovský

Proceedings of the New Trends in Image Analysis and Processing - ICIAP 2013, 2013

Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech.

Jan Nouza, Petr Cerva, Jan Silovský

Proceedings of the IEEE International Conference on Acoustics, 2013

2012

Making Czech Historical Radio Archive Accessible and Searchable for Wide Public.

Jan Nouza, Karel Blavka, Petr Cerva, Jindrich Zdánský, Jan Silovský, Marek Bohac, Jan Prazak

J. Multim., 2012

Incorporation of the ASR output in speaker segmentation and clustering within the task of speaker diarization of broadcast streams.

Jan Silovský, Jindrich Zdánský, Jan Nouza, Petr Cerva, Jan Prazak

Proceedings of the 14th IEEE International Workshop on Multimedia Signal Processing, 2012

Large-scale processing, indexing and search system for Czech audio-visual cultural heritage archives.

Jan Nouza, Karel Blavka, Jindrich Zdánský, Petr Cerva, Jan Silovský, Marek Bohac, Josef Chaloupka, Michaela Kucharová, Ladislav Seps

Proceedings of the 14th IEEE International Workshop on Multimedia Signal Processing, 2012

Browsing, indexing and automatic transcription of lectures for distance learning.

Petr Cerva, Jan Silovský, Jindrich Zdánský, Ondrej Smola, Karel Blavka, Karel Palecek, Jan Nouza, Jirí Málek

Proceedings of the 14th IEEE International Workshop on Multimedia Signal Processing, 2012

Study on Integration of Speaker Diarization with Speaker Adaptive Speech Recognition for Broadcast Transcription.

Jan Silovský, Petr Cerva, Jindrich Zdánský, Jan Nouza

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Real-Time Lecture Transcription using ASR for Czech Hearing Impaired or Deaf Students.

Petr Cerva, Jan Silovský, Jindrich Zdánský, Jan Nouza, Jirí Málek

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

2011

Voice Technology to Enable Sophisticated Access to Historical Audio Archive of the Czech Radio.

Jan Nouza, Karel Blavka, Marek Bohac, Petr Cerva, Jindrich Zdánský, Jan Silovský, Jan Prazak

Proceedings of the Multimedia for Cultural Heritage - First International Workshop, 2011

PLDA-Based Clustering for Speaker Diarization of Broadcast Streams.

Jan Silovský, Jan Prazak, Petr Cerva, Jindrich Zdánský, Jan Nouza

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Using Unsupervised Feature-Based Speaker Adaptation for Improved Transcription of Spoken Archives.

Petr Cerva, Karel Palecek, Jan Silovský, Jan Nouza

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Rainbow Bridge - Training Center based on Voice Technology for People with Physical Disabilities.

Jan Nouza, Petr Cerva, Josef Chaloupka

Proceedings of the HEALTHINF 2011, 2011

2010

Study on Cross-Lingual Adaptation of a Czech LVCSR System towards Slovak.

Petr Cerva, Jan Nouza, Jan Silovský

Proceedings of the Analysis of Verbal and Nonverbal Communication and Enactment. The Processing Issues, 2010

2009

Cost-Efficient Cross-Lingual Adaptation of a Speech Recognition System.

Zoraida Callejas, Jan Nouza, Petr Cerva, Ramón López-Cózar

Proceedings of the Computer Recognition Systems 3, 2009

Very large vocabulary voice dictation for mobile devices.

Jan Nouza, Petr Cerva, Jindrich Zdánský

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Challenges in Speech Processing of Slavic Languages (Case Studies in Speech Recognition of Czech and Slovak).

Jan Nouza, Jindrich Zdánský, Petr Cerva, Jan Silovský

Proceedings of the Development of Multimodal Interfaces: Active Listening and Synchrony, 2009

2008

Study on Speaker Adaptation Methods in the Broadcast News Transcription Task.

Petr Cerva, Jindrich Zdánský, Jan Silovský, Jan Nouza

Proceedings of the Text, Speech and Dialogue, 11th International Conference, 2008

Czech-to-slovak adapted broadcast news transcription system.

Jan Nouza, Jan Silovský, Jindrich Zdánský, Petr Cerva, Martin Kroul, Josef Chaloupka

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

MLLR Transforms Based Speaker Recognition in Broadcast Streams.

Jan Silovský, Petr Cerva, Jindrich Zdánský

Proceedings of the Cross-Modal Analysis of Speech, Gestures, Gaze and Facial Expressions, 2008

Voice Technology Applied for Building a Prototype Smart Room.

Josef Chaloupka, Jan Nouza, Jindrich Zdánský, Petr Cerva, Jan Silovský, Martin Kroul

Proceedings of the Multimodal Signals: Cognitive and Algorithmic Issues, 2008

2007

MyVoice goes Spanish. Cross-lingual Adaptation of a Voice Controlled PC Tool for Handicapped People.

Zoraida Callejas, Jan Nouza, Petr Cerva, Ramón López-Cózar

Proces. del Leng. Natural, 2007

Design and development of voice controlled aids for motor-handicapped persons.

Petr Cerva, Jan Nouza

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

2006

A System for Information Retrieval from Large Records of Czech Spoken Data.

Jan Nouza, Jindrich Zdánský, Petr Cerva, Jan Kolorenc

Proceedings of the Text, Speech and Dialogue, 9th International Conference, 2006

Continual on-line monitoring of Czech spoken broadcast programs.

Jan Nouza, Jindrich Zdánský, Petr Cerva, Jan Kolorenc

Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

Two-step unsupervised speaker adaptation based on speaker and gender recognition and HMM combination.

Petr Cerva, Jan Nouza, Jan Silovský

Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

2005

Supervised and Unsupervised Speaker Adaptation in Large Vocabulary Continuous Speech Recognition of Czech.

Petr Cerva, Jan Nouza

Proceedings of the Text, Speech and Dialogue, 8th International Conference, 2005

Fully automated system for Czech spoken broadcast transcription with very large (300k+) lexicon.

Jan Nouza, Jindrich Zdánský, Petr David, Petr Cerva, Jan Kolorenc, Dana Nejedlová

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005