Vassilios Digalakis

According to our database, Vassilios Digalakis authored at least 66 papers between 1989 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2023

Frequency Estimation in Data Streams: Learning the Optimal Hashing Scheme.

Dimitris Bertsimas, Vassilis Digalakis

IEEE Trans. Knowl. Data Eng., 2023

2022

The backbone method for ultra-high dimensional sparse machine learning.

Dimitris Bertsimas, Vassilis Digalakis

Mach. Learn., 2022

Frequency Estimation in Data Streams: Learning the Optimal Hashing Scheme (Extended Abstract).

Dimitris Bertsimas, Vassilis Digalakis

Proceedings of the 38th IEEE International Conference on Data Engineering, 2022

2017

ClockWork-RNN Based Architectures for Slot Filling.

Despoina Georgiadou, Vassilios Diakoloukas, Vassilios Tsiaras, Vassilios Digalakis

Proceedings of the Interspeech 2017, 2017

2016

Global Variance in Speech Synthesis With Linear Dynamical Models.

Vassilis Tsiaras, Ranniery Maia, Vassilios Diakoloukas, Yannis Stylianou, Vassilios Digalakis

IEEE Signal Process. Lett., 2016

2015

Towards a linear dynamical model based speech synthesizer.

Vassilios Tsiaras, Ranniery Maia, Vassilios Diakoloukas, Yannis Stylianou, Vassilios Digalakis

Proceedings of the INTERSPEECH 2015, 2015

2014

Joint estimation of multiple undirected graphical models.

Alexandros Georgogiannis, Vassilios Digalakis

Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing, 2014

Linear dynamical models in speech synthesis.

Vassilios Tsiaras, Ranniery Maia, Vassilios Diakoloukas, Yannis Stylianou, Vassilios Digalakis

Proceedings of the IEEE International Conference on Acoustics, 2014

2012

Speech Emotion Recognition using non-linear Teager energy based features in noisy environments.

Alexandros Georgogiannis, Vassilis Digalakis

Proceedings of the 20th European Signal Processing Conference, 2012

2010

Identification of linear systems in canonical form through an EM framework.

Pavlos Papadopoulos, Vassilios Digalakis

Proceedings of the IEEE International Conference on Acoustics, 2010

2007

Gaussian Mixture Clustering and Language Adaptation for the Development of a New Language Speech Recognition System.

Nikos Chatzichrisafis, Vassilios Diakoloukas, Vassilios Digalakis, Costas Harizakis

IEEE Trans. Speech Audio Process., 2007

Automatic pronunciation evaluation of foreign speakers using unknown text.

N. Moustroufas, Vassilios Digalakis

Comput. Speech Lang., 2007

Degradation of speech recognition performance over lossy data networks.

Dimitris Pratsolis, Nikos Tsourakis, Vassilios Digalakis

Proceedings of the WMuNeP'07, 2007

A generic methodology of converting transliterated text to phonetic strings case study: greeklish.

Nikos Tsourakis, Vassilios Digalakis

Proceedings of the INTERSPEECH 2007, 2007

A sub-optimal viterbi-like search for linear dynamic models classification.

Dimitris Oikonomidis, Vassilios Diakoloukas, Vassilios Digalakis

Proceedings of the INTERSPEECH 2007, 2007

Estimation of General Identifiable Linear Dynamic Models with an Application in Speech Recognition.

Georgios Tsontzos, Vassilios Diakoloukas, Christos Koniaris, Vassilios Digalakis

Proceedings of the IEEE International Conference on Acoustics, 2007

2004

Rapid acoustic model development using Gaussian mixture clustering and language adaptation.

Nikos Chatzichrisafis, Vassilios Digalakis, Vassilios Diakoloukas, Costas Harizakis

Proceedings of the INTERSPEECH 2004, 2004

2003

Stem-based maximum entropy language models for inflectional languages.

Dimitris Oikonomidis, Vassilios Digalakis

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Large vocabulary continuous speech recognition in greek: corpus and an automatic dictation system.

Vassilios Digalakis, Dimitris Oikonomidis, Dimitris Pratsolis, Nikos Tsourakis, Christos Vosnidis, Nikos Chatzichrisafis, Vassilios Diakoloukas

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

2001

Maximum likelihood stochastic transformation adaptation for medium and small data sets.

Constantinos Boulis, Vassilios Diakoloukas, Vassilios Digalakis

Comput. Speech Lang., 2001

Use of clustering information for coarticulation compensation in speech synthesis by word concatenation.

Christos Vosnidis, Vassilios Digalakis

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

2000

A Configurable Logic Based Architecture for Real-Time Continuous Speech Recognition Using Hidden Markov Models.

Panagiotis Stogiannos, Apostolos Dollas, Vassilios Digalakis

J. VLSI Signal Process., 2000

Automatic scoring of pronunciation quality.

Leonardo Neumeyer, Horacio Franco, Vassilios Digalakis, Mitch Weintraub

Speech Commun., 2000

Combination of machine scores for automatic grading of pronunciation quality.

Horacio Franco, Leonardo Neumeyer, Vassilios Digalakis, Orith Ronen

Speech Commun., 2000

Efficient speech recognition using subvector quantization and discrete-mixture HMMS.

Vassilios Digalakis, Stavros Tsakalidis, Costas Harizakis, Leonardo Neumeyer

Comput. Speech Lang., 2000

Fast speaker adaptation of large vocabulary continuous density HMM speech recognizer using a basis transform approach.

Constantinos Boulis, Vassilios Digalakis

Proceedings of the IEEE International Conference on Acoustics, 2000

1999

Online adaptation of hidden Markov models using incremental estimation algorithms.

Vassilios Digalakis

IEEE Trans. Speech Audio Process., 1999

Maximum-likelihood stochastic-transformation adaptation of hidden Markov models.

Vassilios Diakoloukas, Vassilios Digalakis

IEEE Trans. Speech Audio Process., 1999

Quantization of cepstral parameters for speech recognition over the World Wide Web.

Vassilios Digalakis, Leonardo Neumeyer, Manolis Perakakis

IEEE J. Sel. Areas Commun., 1999

Reviving discrete HMMs: the myth about the superiority of continuous HMMs.

Vassilios Digalakis, Stavros Tsakalidis, Leonardo Neumeyer

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Efficient speech recognition using subvector quantization and discrete-mixture HMMs.

Stavros Tsakalidis, Vassilios Digalakis, Leonardo Neumeyer

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

Rapid speech recognizer adaptation to new speakers.

Vassilios Digalakis, Heather Collier, Sid Berkowitz, Adrian Corduneanu, Enrico Bocchieri, Ashvin Kannan, Constantinos Boulis, Sanjeev Khudanpur, William Byrne, Ananth Sankar

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

Correlation modeling of MLLR transform biases for rapid HMM adaptation to new speakers.

Enrico Bocchieri, Vassilios Digalakis, Adrian Corduneanu, Constantinos Boulis

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

1998

Product-code vector quantization of cepstral parameters for speech recognition over the WWW.

Vassilios Digalakis, Leonardo Neumeyer, Manolis Perakakis

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Robust speech recognition for multiple topological scenarios of the GSM mobile phone system.

Theodoros Salonidis, Vassilios Digalakis

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

Design and implementation of auto-attendant system for the TUC campus using speech recognition.

Konstantinos Koumpis, Vassilios Digalakis, Hy Murveit

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

On the integration of dialect and speaker adaptation in a multi-dialect speech recognition system.

Vassilios Digalakis, Vlasios Doumpiotis, Stavros Tsakalidis

Proceedings of the 9th European Signal Processing Conference, 1998

1997

On-line adaptation of hidden Markov models using incremental estimation algorithms.

Vassilios Digalakis

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Adaptation of hidden Markov models using multiple stochastic transformations.

Vassilios Diakoloukas, Vassilios Digalakis

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Development of dialect-specific speech recognizers using adaptation methods.

Vassilios Diakoloukas, Vassilios Digalakis, Leonardo Neumeyer, Jaan Kaja

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

1996

From HMM's to segment models: a unified view of stochastic modeling for speech recognition.

Mari Ostendorf, Vassilios Digalakis, Owen Kimball

IEEE Trans. Speech Audio Process., 1996

Speaker adaptation using combined transformation and Bayesian methods.

Vassilios Digalakis, Leonardo Neumeyer

IEEE Trans. Speech Audio Process., 1996

Genones: generalized mixture tying in continuous hidden Markov model-based speech recognizers.

Vassilios Digalakis, Peter Monaco, Hy Murveit

IEEE Trans. Speech Audio Process., 1996

1995

Speaker adaptation using constrained estimation of Gaussian mixtures.

Vassilios Digalakis, Dimitry Rtischev, Leonardo Neumeyer

IEEE Trans. Speech Audio Process., 1995

Training data clustering for improved speech recognition.

Ananth Sankar, Françoise Beaufays, Vassilios Digalakis

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

A comparative study of speaker adaptation techniques.

Leonardo Neumeyer, Ananth Sankar, Vassilios Digalakis

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

Temporal correlation modeling in a hybrid neural network/hidden Markov model speech recognizer.

Horacio Franco, Vassilios Digalakis

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

1994

Training issues and channel equalization techniques for the construction of telephone acoustic models using a high-quality speech corpus.

Leonardo Neumeyer, Vassilios Digalakis, Mitchel Weintraub

IEEE Trans. Speech Audio Process., 1994

Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists.

Manny Rayner, David M. Carter, Vassilios Digalakis, Patti Price

Proceedings of the Human Language Technology, 1994

Techniques to Achieve an Accurate Real-Time Large-Vocabulary Speech Recognition System.

Hy Murveit, Peter Monaco, Vassilios Digalakis, John Butzberger

Proceedings of the Human Language Technology, 1994

Consistency Modeling.

Hy Murveit, Vassilios Digalakis, Peter Monaco, Mitch Weintraub

Proceedings of the Human Language Technology, 1994

High-Accuracy Large-Vocabulary Speech Recognition Using Mixture Tying and Consistency Modeling.

Vassilios Digalakis, Hy Murveit

Proceedings of the Human Language Technology, 1994

Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer.

Vassilios Digalakis, Hy Murveit

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

1993

ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition.

Vassilios Digalakis, Jan Robin Rohlicek, Mari Ostendorf

IEEE Trans. Speech Audio Process., 1993

Three-dimensional linear prediction and its application to digital angiography.

Vassilios V. Digalakis, Vinay K. Ingle, Dimitris G. Manolakis

Multidimens. Syst. Signal Process., 1993

A Speech To Speech Translation System Built From Standard Components.

Manny Rayner, Hiyan Alshawi, Ivan Bretan, David M. Carter, Vassilios Digalakis, Björn Gambäck, Jaan Kaja, Jussi Karlgren, Bertil Lyberg, Stephen G. Pulman, Patti Price, Christer Samuelsson

Proceedings of the Human Language Technology: Proceedings of a Workshop Held at Plainsboro, 1993

Progressive-Search Algorithms For Large-Vocabulary Speech Recognition.

Hy Murveit, John Butzberger, Vassilios Digalakis, Mitch Weintraub

Proceedings of the Human Language Technology: Proceedings of a Workshop Held at Plainsboro, 1993

High Performance Speech Recognition Using Consistency Modeling.

Vassilios Digalakis, Hy Murveit, Mitch Weintraub

Proceedings of the Human Language Technology: Proceedings of a Workshop Held at Plainsboro, 1993

Automatic adaptive constrast enhancement for radiological imaging.

Vassilis Digalakis, Dimitris G. Manolakis, Vinay K. Ingle, A. K. Kok

Proceedings of the 1993 IEEE International Symposium on Circuits and Systems, 1993

Spoken language translation with MID-90's technology: a case study.

Manny Rayner, Ivan Bretan, David M. Carter, Michael Collins, Vassilios Digalakis, Björn Gambäck, Jaan Kaja, Jussi Karlgren, Bertil Lyberg, Stephen G. Pulman, Patti Price, Christer Samuelsson

Proceedings of the Third European Conference on Speech Communication and Technology, 1993

Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniques.

Hy Murveit, John Butzberger, Vassilios Digalakis, Mitch Weintraub

Proceedings of the IEEE International Conference on Acoustics, 1993

Maximum likelihood identification of multiscale stochastic models using the wavelet transform and the EM algorithm.

Vassilios V. Digalakis, Kenneth C. Chou

Proceedings of the IEEE International Conference on Acoustics, 1993

1992

Fast algorithms for phone classification and recognition using segment-based models.

Vassilios Digalakis, Mari Ostendorf, Jan Robin Rohlicek

IEEE Trans. Signal Process., 1992

1991

A dynamical system approach to continuous speech recognition.

Vassilios Digalakis, Jan Robin Rohlicek, Mari Ostendorf

Proceedings of the 1991 International Conference on Acoustics, 1991

1990

Fast Search Algorithms for Connected Phone Recognition Using the Stochastic Segment Model.

Vassilios Digalakis, Mari Ostendorf, Jan Robin Rohlicek

Proceedings of the Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, 1990

1989

Improvements in the Stochastic Segment Model for Phoneme Recognition.

Vassilios Digalakis, Mari Ostendorf, Jan Robin Rohlicek

Proceedings of the Speech and Natural Language: Proceedings of a Workshop Held at Cape Cod, 1989