Ludek Müller

Publication Activity (10 Years)

Years Active: 1996-2021
Publications (10 Years): 16

Top Topics

Scanned Documents

Speech Recognition

Top Venues

Publications

Zbynek Zajíc, Marie Kunesová, Ludek Müller
Applying EEND Diarization to Telephone Recordings from a Call Center. SPECOM (2021)
Lukás Bures, Ludek Müller
Semantic Segmentation in the Task of Long-Term Visual Localization. ICR (2021)
Lukás Bures, Petr Neduchal, Ludek Müller
Automatic Information Extraction from Scanned Documents. SPECOM (2020)
Zbynek Zajíc, Josef V. Psutka, Ludek Müller
Diarization Based on Identification with X-Vectors. SPECOM (2020)
Zbynek Zajíc, Josef V. Psutka, Lucie Zajícová, Ludek Müller, Petr Salajka
Diarization of the Language Consulting Center Telephone Calls. SPECOM (2019)
Zbynek Zajíc, Lucie Zajícová, Josef V. Psutka, Petr Salajka, Jaromír Novotný, Ales Prazák, Ludek Müller
First Insight into the Processing of the Language Consulting Center Data. SPECOM (2018)
Zbynek Zajíc, Daniel Soutner, Marek Hrúz, Ludek Müller, Vlasta Radová
Recurrent Neural Network Based Speaker Change Detection from Text Transcription Applied in Telephone Speaker Diarization System. TSD (2018)
Zbynek Zajíc, Lucie Skorkovská, Petr Neduchal, Pavel Ircing, Josef V. Psutka, Marek Hrúz, Ales Prazák, Daniel Soutner, Jan Svec, Lukás Bures, Ludek Müller
Towards Processing of the Oral History Interviews and Related Printed Documents. LREC (2018)
Zbynek Zajíc, Marek Hrúz, Ludek Müller
Speaker Diarization Using Convolutional Neural Network for Statistics Accumulation Refinement. INTERSPEECH (2017)
Lukás Bures, Filip Berka, Ludek Müller
Comparsion of Feature Extraction Methods for Finding Similar Images. ICR (2017)
Zbynek Zajíc, Jan Zelinka, Ludek Müller
Neural Network Speaker Descriptor in Speaker Diarization of Telephone Speech. SPECOM (2017)
Lukás Bures, Ludek Müller
Selecting Keypoint Detector and Descriptor Combination for Augmented Reality Application. SPECOM (2016)
Jan Zelinka, Jan Vanek, Ludek Müller
Simultaneously Trained NN-Based Acoustic Model and NN-Based Feature Extractor. TSD (2015)
Jan Zelinka, Jan Vanek, Ludek Müller
Neural-Network-Based Spectrum Processing for Speech Recognition and Speaker Verification. SLSP (2015)
Jan Zelinka, Petr Salajka, Ludek Müller
On Deep and Shallow Neural Networks in Speech Recognition from Speech Spectrum. SPECOM (2015)
Daniel Soutner, Ludek Müller
On Continuous Space Word Representations as Input of LSTM Language Model. SLSP (2015)
Daniel Soutner, Ludek Müller
Continuous Distributed Representations of Words as Input of LSTM Network Language Model. TSD (2014)
Daniel Soutner, Jan Zelinka, Ludek Müller
On a Hybrid NN/HMM Speech Recognition System with a RNN-Based Language Model. SPECOM (2014)
Zbynek Zajíc, Jan Zelinka, Jan Vanek, Ludek Müller
Convolutional Neural Network for Refinement of Speaker Adaptation Transformation. SPECOM (2014)
Lucie Skorkovská, Zbynek Zajíc, Ludek Müller
Comparison of score normalization methods applied to multi-label classification. ISSPIT (2014)
Daniel Soutner, Ludek Müller
Application of LSTM Neural Networks in Language Modelling. TSD (2013)
Daniel Soutner, Zdenek Loose, Ludek Müller, Ales Prazák
Neural Network Language Model with Cache. TSD (2012)
Zbynek Zajíc, Lukás Machlica, Ludek Müller
Robust Adaptation Techniques Dealing with Small Amount of Data. TSD (2012)
Lukás Machlica, Zbynek Zajíc, Ludek Müller
On complementarity of state-of-the-art speaker recognition systems. ISSPIT (2012)
Ales Prazák, Zdenek Loose, Josef Psutka, Vlasta Radová, Ludek Müller
Four-phase Re-speaker Training System. SIGMAP (2011)
Zbynek Zajíc, Lukás Machlica, Ludek Müller
Initialization of fMLLR with Sufficient Statistics from Similar Speakers. TSD (2011)
Marek Hrúz, Zdenek Krnoul, Pavel Campr, Ludek Müller
Towards Automatic Annotation of Sign Language Dictionary Corpora. TSD (2011)
Jan Zelinka, Jan Romportl, Ludek Müller
Statistical-Based Abbreviation Expansion. TSD (2011)
Jan Zelinka, Jan Trmal, Ludek Müller
Low-dimensional space transforms of posteriors in speech recognition. INTERSPEECH (2010)
Lukás Machlica, Zbynek Zajíc, Ludek Müller
Discriminative adaptation based on fast combination of DMAP and dfMLLR. INTERSPEECH (2010)
Jan Zelinka, Jan Romportl, Ludek Müller
A Priori and A Posteriori Machine Learning and Nonlinear Artificial Neural Networks. TSD (2010)
Jan Trmal, Jan Zelinka, Ludek Müller
Adaptation of a Feedforward Artificial Neural Network Using a Linear Transform. TSD (2010)
Jan Trmal, Jan Zelinka, Ludek Müller
On speaker adaptive training of artificial neural networks. INTERSPEECH (2010)
Jan Zelinka, Lubos Smídl, Jan Trmal, Ludek Müller
Posterior Estimates and Transforms for Speech Recognition. TSD (2010)
Zbynek Zajíc, Lukás Machlica, Ludek Müller
Robust Statistic Estimates for Adaptation in the Task of Speech Recognition. TSD (2010)
Jakub Kanis, Ludek Müller
Advances in Czech - Signed Speech Translation. TSD (2009)
Zbynek Zajíc, Lukás Machlica, Ludek Müller
Refinement Approach for Adaptation Based on Combination of MAP and fMLLR. TSD (2009)
Filip Jurcícek, Jan Svec, Ludek Müller
Extension of HVS semantic parser by allowing left-right branching. ICASSP (2008)
Jan Trmal, Marek Hrúz, Jan Zelinka, Pavel Campr, Ludek Müller
Feature space transforms for Czech sign-language recognition. INTERSPEECH (2008)
Ales Prazák, Ludek Müller, Josef V. Psutka, Josef Psutka
Live TV Subtitling - Fast 2-pass LVCSR System for Online Subtitling. SIGMAP (2007)
Pavel Ircing, Ludek Müller
Czech Monolingual Information Retrieval Using Off-The-Shelf Components - the University of West Bohemia at CLEF 2007 Ad-Hoc track. CLEF (Working Notes) (2007)
Jakub Kanis, Ludek Müller
Automatic Czech - Sign Speech Translation. TSD (2007)
Zdenek Krnoul, Jakub Kanis, Milos Zelezný, Ludek Müller
Czech Text-to-Sign Speech Synthesizer. MLMI (2007)
Josef V. Psutka, Ludek Müller, Lubos Smídl, Josef Psutka
Feature space reduction and decorrelation in a large number of speech recognition experiments. SIP (2007)
Jan Svec, Filip Jurcícek, Ludek Müller
Parameterization of the Input in Training the HVS Semantic Parser. TSD (2007)
Pavel Ircing, Ludek Müller
Attempts to Search Czech Spontaneous Spoken Interviews - the University of West Bohemia at CLEF 2007 CL-SR track. CLEF (Working Notes) (2007)
Pavel Ircing, Ludek Müller
The University of West Bohemia at CLEF 2006, the CL-SR Track. CLEF (Working Notes) (2006)
Jan Trmal, Jan Zelinka, Jan Vanek, Ludek Müller
Silence/Speech Detection Method Based on Set of Decision Graphs. TSD (2006)
Pavel Ircing, Ludek Müller
Benefit of Proper Language Processing for Czech Speech Retrieval in the CL-SR Task at CLEF 2006. CLEF (2006)
Ales Prazák, Josef V. Psutka, Jan Hoidekr, Jakub Kanis, Ludek Müller, Josef Psutka
Automatic Online Subtitling of the Czech Parliament Meetings. TSD (2006)
Ales Prazák, Josef V. Psutka, Jan Hoidekr, Jakub Kanis, Ludek Müller, Josef Psutka
Adaptive language model in automatic online subtitling. Computational Intelligence (2006)
Jan Trmal, Jan Vanek, Ludek Müller, Jan Zelinka
Independent components for acoustic modeling. INTERSPEECH (2006)
Jakub Kanis, Jirí Zahradil, Filip Jurcícek, Ludek Müller
Czech-Sign Speech Corpus for Semantic Based Machine Translation. TSD (2006)
Zdenek Krnoul, Milos Zelezný, Ludek Müller, Jakub Kanis
Training of coarticulation models using dominance functions and visual unit selection methods for audio-visual speech synthesis. INTERSPEECH (2006)
Tomás Bartos, Ludek Müller
Detection of recognition errors based on classifiers trained on artificially created data. INTERSPEECH (2005)
Jan Zelinka, Jakub Kanis, Ludek Müller
Automatic Transcription of Numerals in Inflectional Languages. TSD (2005)
Petr Císar, Milos Zelezný, Zdenek Krnoul, Jakub Kanis, Jan Zelinka, Ludek Müller
Design and recording of Czech speech corpus for audio-visual continuous speech recognition. AVSP (2005)
Jakub Kanis, Ludek Müller
Automatic Lemmatizer Construction with Focus on OOV Words Lemmatization. TSD (2005)
Jakub Kanis, Ludek Müller
Using the Lemmatization Technique for Phonetic Transcription in Text-to-Speech System. TSD (2004)
Lubos Smídl, Ludek Müller
Keyword spotting for highly inflectional languages. INTERSPEECH (2004)
Jan Zelinka, Ludek Müller
Automatic General Letter-to-Sound Rules Generation for German Text-to-Speech System. TSD (2004)
Ludek Müller, Tomás Bartos
Statistically based approach to rejection of incorrectly recognized words. INTERSPEECH (2002)
Michal Prcín, Ludek Müller
Heuristic and Statistical Methods for Speech/Non-Speech Detector Design. TSD (2002)
Tomás Bartos, Ludek Müller
Rejection Technique Based on the Mumble Model. TSD (2002)
Josef Psutka, Ludek Müller, Josef V. Psutka
Comparison of MFCC and PLP parameterizations in the speaker independent continuous speech recognition task. INTERSPEECH (2001)
Josef Psutka, Ludek Müller, Josef V. Psutka
The Influence of a Filter Shape in Telephone-Based Recognition Module Using PLP Parameterization. TSD (2001)
Josef Psutka, Vlasta Radová, Ludek Müller, Jindrich Matousek, Pavel Ircing, David Graff
Large broadcast news and read speech corpora of spoken czech. INTERSPEECH (2001)
Ludek Müller, Filip Jurcícek, Lubos Smídl
Rejection and key-phrase spottin techniques using a mumble model in a czech telephone dialog system. INTERSPEECH (2000)
Ludek Müller, Josef Psutka, Lubos Smídl
Design of Speech Recognition Engine. TSD (2000)
Petr Becvár, Ludek Müller
Various approaches in classification of technical processes. Advanced Network Enterprises (2000)
Ludek Müller, Josef Psutka
Using various language model smoothing techniques for the transcription of a weather forecast broadcasted by the czech radio. EUROSPEECH (1999)
Josef Psutka, Jirí Kepka, Ludek Müller, Zbynek Tychtl
Modelling man-computer oral dialogue in noisy environment. EUSIPCO (1996)