Vassilios Digalakis

64 papers A 8B 1Misc 12Journal 19Unranked 24

Year	Rank	Type	Title / Venue / Authors
2017	A	`conf`	ClockWork-RNN Based Architectures for Slot Filling. INTERSPEECH Despoina Georgiadou, Vassilios Diakoloukas, Vassilios Tsiaras, Vassilios Digalakis
2016	J	`jnl`	Global Variance in Speech Synthesis With Linear Dynamical Models. IEEE Signal Process. Lett. Vassilis Tsiaras, Ranniery Maia, Vassilios Diakoloukas, Yannis Stylianou, Vassilios Digalakis
2015	A	`conf`	Towards a linear dynamical model based speech synthesizer. INTERSPEECH Vassilios Tsiaras, Ranniery Maia, Vassilios Diakoloukas, Yannis Stylianou, Vassilios Digalakis
2014	—	`conf`	Joint estimation of multiple undirected graphical models. MLSP Alexandros Georgogiannis, Vassilios Digalakis
2014	Misc	`conf`	Linear dynamical models in speech synthesis. ICASSP Vassilios Tsiaras, Ranniery Maia, Vassilios Diakoloukas, Yannis Stylianou, Vassilios Digalakis
2010	Misc	`conf`	Identification of linear systems in canonical form through an EM framework. ICASSP Pavlos Papadopoulos, Vassilios Digalakis
2008	B	`ed.`	Proceedings of the 10th International Conference on Multimodal Interfaces, ICMI 2008, Chania, Crete, Greece, October 20-22, 2008 ICMI Vassilios Digalakis, Alexandros Potamianos, Matthew Turk, Roberto Pieraccini, Yuri Ivanov
2007	A	`conf`	A generic methodology of converting transliterated text to phonetic strings case study: greeklish. INTERSPEECH Nikos Tsourakis, Vassilios Digalakis
2007	A	`conf`	A sub-optimal viterbi-like search for linear dynamic models classification. INTERSPEECH Dimitris Oikonomidis, Vassilios Diakoloukas, Vassilios Digalakis
2007	J	`jnl`	Automatic pronunciation evaluation of foreign speakers using unknown text. Comput. Speech Lang. N. Moustroufas, Vassilios Digalakis
2007	—	`conf`	Degradation of speech recognition performance over lossy data networks. WMuNeP Dimitris Pratsolis, Nikos Tsourakis, Vassilios Digalakis
2007	—	`conf`	Estimation of General Identifiable Linear Dynamic Models with an Application in Speech Recognition. ICASSP (4) Georgios Tsontzos, Vassilios Diakoloukas, Christos Koniaris, Vassilios Digalakis
2007	J	`jnl`	Gaussian Mixture Clustering and Language Adaptation for the Development of a New Language Speech Recognition System. IEEE Trans. Speech Audio Process. Nikos Chatzichrisafis, Vassilios Diakoloukas, Vassilios Digalakis, Costas Harizakis
2004	A	`conf`	Rapid acoustic model development using Gaussian mixture clustering and language adaptation. INTERSPEECH Nikos Chatzichrisafis, Vassilios Digalakis, Vassilios Diakoloukas, Costas Harizakis
2003	A	`conf`	Large vocabulary continuous speech recognition in greek: corpus and an automatic dictation system. INTERSPEECH Vassilios Digalakis, Dimitris Oikonomidis, Dimitris Pratsolis, Nikos Tsourakis, Christos Vosnidis, Nikos Chatzichrisafis, Vassilios Diakoloukas
2003	A	`conf`	Stem-based maximum entropy language models for inflectional languages. INTERSPEECH Dimitris Oikonomidis, Vassilios Digalakis
2001	J	`jnl`	Maximum likelihood stochastic transformation adaptation for medium and small data sets. Comput. Speech Lang. Constantinos Boulis, Vassilios Diakoloukas, Vassilios Digalakis
2001	A	`conf`	Use of clustering information for coarticulation compensation in speech synthesis by word concatenation. INTERSPEECH Christos Vosnidis, Vassilios Digalakis
2000	J	`jnl`	A Configurable Logic Based Architecture for Real-Time Continuous Speech Recognition Using Hidden Markov Models. J. VLSI Signal Process. Panagiotis Stogiannos, Apostolos Dollas, Vassilios Digalakis
2000	J	`jnl`	Automatic scoring of pronunciation quality. Speech Commun. Leonardo Neumeyer, Horacio Franco, Vassilios Digalakis, Mitch Weintraub
2000	J	`jnl`	Combination of machine scores for automatic grading of pronunciation quality. Speech Commun. Horacio Franco, Leonardo Neumeyer, Vassilios Digalakis, Orith Ronen
2000	J	`jnl`	Efficient speech recognition using subvector quantization and discrete-mixture HMMS. Comput. Speech Lang. Vassilios Digalakis, Stavros Tsakalidis, Costas Harizakis, Leonardo Neumeyer
2000	Misc	`conf`	Fast speaker adaptation of large vocabulary continuous density HMM speech recognizer using a basis transform approach. ICASSP Constantinos Boulis, Vassilios Digalakis
1999	Misc	`conf`	Correlation modeling of MLLR transform biases for rapid HMM adaptation to new speakers. ICASSP Enrico Bocchieri, Vassilios Digalakis, Adrian Corduneanu, Constantinos Boulis
1999	Misc	`conf`	Efficient speech recognition using subvector quantization and discrete-mixture HMMs. ICASSP Stavros Tsakalidis, Vassilios Digalakis, Leonardo Neumeyer
1999	J	`jnl`	Maximum-likelihood stochastic-transformation adaptation of hidden Markov models. IEEE Trans. Speech Audio Process. Vassilios Diakoloukas, Vassilios Digalakis
1999	J	`jnl`	Online adaptation of hidden Markov models using incremental estimation algorithms. IEEE Trans. Speech Audio Process. Vassilios Digalakis
1999	J	`jnl`	Quantization of cepstral parameters for speech recognition over the World Wide Web. IEEE J. Sel. Areas Commun. Vassilios Digalakis, Leonardo Neumeyer, Manolis Perakakis
1999	Misc	`conf`	Rapid speech recognizer adaptation to new speakers. ICASSP Vassilios Digalakis, Heather Collier, Sid Berkowitz, Adrian Corduneanu, Enrico Bocchieri, Ashvin Kannan, Constantinos Boulis, Sanjeev Khudanpur, William Byrne, Ananth Sankar
1999	—	`conf`	Reviving discrete HMMs: the myth about the superiority of continuous HMMs. EUROSPEECH Vassilios Digalakis, Stavros Tsakalidis, Leonardo Neumeyer
1998	Misc	`conf`	Design and implementation of auto-attendant system for the TUC campus using speech recognition. ICASSP Konstantinos Koumpis, Vassilios Digalakis, Hy Murveit
1998	—	`conf`	On the integration of dialect and speaker adaptation in a multi-dialect speech recognition system. EUSIPCO Vassilios Digalakis, Vlasios Doumpiotis, Stavros Tsakalidis
1998	—	`conf`	Product-code vector quantization of cepstral parameters for speech recognition over the WWW. ICSLP Vassilios Digalakis, Leonardo Neumeyer, Manolis Perakakis
1998	Misc	`conf`	Quantization of cepstral parameters for speech recognition over the World Wide Web. ICASSP Vassilios Digalakis, Leonardo Neumeyer, Manolis Perakakis
1998	Misc	`conf`	Robust speech recognition for multiple topological scenarios of the GSM mobile phone system. ICASSP Theodoros Salonidis, Vassilios Digalakis
1997	—	`conf`	Adaptation of hidden Markov models using multiple stochastic transformations. EUROSPEECH Vassilios Diakoloukas, Vassilios Digalakis
1997	Misc	`conf`	Development of dialect-specific speech recognizers using adaptation methods. ICASSP Vassilios Diakoloukas, Vassilios Digalakis, Leonardo Neumeyer, Jaan Kaja
1997	—	`conf`	On-line adaptation of hidden Markov models using incremental estimation algorithms. EUROSPEECH Vassilios Digalakis
1996	J	`jnl`	From HMM's to segment models: a unified view of stochastic modeling for speech recognition. IEEE Trans. Speech Audio Process. Mari Ostendorf, Vassilios Digalakis, Owen Kimball
1996	J	`jnl`	Genones: generalized mixture tying in continuous hidden Markov model-based speech recognizers. IEEE Trans. Speech Audio Process. Vassilios Digalakis, Peter Monaco, Hy Murveit
1996	J	`jnl`	Speaker adaptation using combined transformation and Bayesian methods. IEEE Trans. Speech Audio Process. Vassilios Digalakis, Leonardo Neumeyer
1995	—	`conf`	A comparative study of speaker adaptation techniques. EUROSPEECH Leonardo Neumeyer, Ananth Sankar, Vassilios Digalakis
1995	Misc	`conf`	Speaker adaptation using combined transformation and Bayesian methods. ICASSP Vassilios Digalakis, Leonardo Neumeyer
1995	J	`jnl`	Speaker adaptation using constrained estimation of Gaussian mixtures. IEEE Trans. Speech Audio Process. Vassilios Digalakis, Dimitry Rtischev, Leonardo Neumeyer
1995	—	`conf`	Temporal correlation modeling in a hybrid neural network/hidden Markov model speech recognizer. EUROSPEECH Horacio Franco, Vassilios Digalakis
1995	—	`conf`	Training data clustering for improved speech recognition. EUROSPEECH Ananth Sankar, Françoise Beaufays, Vassilios Digalakis
1994	—	`conf`	Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists. HLT Manny Rayner, David M. Carter, Vassilios Digalakis, Patti Price
1994	J	`jnl`	Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists. CoRR Manny Rayner, David M. Carter, Vassilios Digalakis, Patti Price
1994	—	`conf`	Consistency Modeling. HLT Hy Murveit, Vassilios Digalakis, Peter Monaco, Mitch Weintraub
1994	—	`conf`	Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer. ICASSP (1) Vassilios Digalakis, Hy Murveit
1994	—	`conf`	High-Accuracy Large-Vocabulary Speech Recognition Using Mixture Tying and Consistency Modeling. HLT Vassilios Digalakis, Hy Murveit
1994	—	`conf`	Techniques to Achieve an Accurate Real-Time Large-Vocabulary Speech Recognition System. HLT Hy Murveit, Peter Monaco, Vassilios Digalakis, John Butzberger
1994	J	`jnl`	Training issues and channel equalization techniques for the construction of telephone acoustic models using a high-quality speech corpus. IEEE Trans. Speech Audio Process. Leonardo Neumeyer, Vassilios Digalakis, Mitchel Weintraub
1993	—	`conf`	A Speech To Speech Translation System Built From Standard Components. HLT 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
1993	—	`conf`	High Performance Speech Recognition Using Consistency Modeling. HLT Vassilios Digalakis, Hy Murveit, Mitch Weintraub
1993	—	`conf`	Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniques. ICASSP (2) Hy Murveit, John Butzberger, Vassilios Digalakis, Mitch Weintraub
1993	J	`jnl`	ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition. IEEE Trans. Speech Audio Process. Vassilios Digalakis, Jan Robin Rohlicek, Mari Ostendorf
1993	—	`conf`	Progressive-Search Algorithms For Large-Vocabulary Speech Recognition. HLT Hy Murveit, John Butzberger, Vassilios Digalakis, Mitch Weintraub
1993	—	`conf`	Spoken language translation with MID-90's technology: a case study. EUROSPEECH 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
1992	J	`jnl`	Fast algorithms for phone classification and recognition using segment-based models. IEEE Trans. Signal Process. Vassilios Digalakis, Mari Ostendorf, Jan Robin Rohlicek
1991	—	`conf`	A Dynamical System Approach to Continuous Speech Recognition. HLT Vassilios Digalakis, Jan Robin Rohlicek, Mari Ostendorf
1991	Misc	`conf`	A dynamical system approach to continuous speech recognition. ICASSP Vassilios Digalakis, Jan Robin Rohlicek, Mari Ostendorf
1990	—	`conf`	Fast Search Algorithms for Connected Phone Recognition Using the Stochastic Segment Model. HLT Vassilios Digalakis, Mari Ostendorf, Jan Robin Rohlicek
1989	—	`conf`	Improvements in the Stochastic Segment Model for Phoneme Recognition. HLT (2) Vassilios Digalakis, Mari Ostendorf, Jan Robin Rohlicek