- CSB - MetaPress - Google - Bing - Yahoo
 | 2011 | |
|---|---|---|
| c17 |      | László Tóth: A hierarchical, context-dependent neural network architecture for improved phone recognition. ICASSP 2011: 5040-5043 |
| 2010 | ||
| j9 | | László Tóth, Balázs Tarján, Gellért Sárosi, Péter Mihajlik: Speech Recognition Experiments with Audiobooks. Acta Cybern. 19(4): 695-713 (2010) |
| 2009 | ||
| c16 | | Gábor Gosztolya, András Bánhalmi, László Tóth: Using One-Class Classification Techniques in the Anti-phoneme Problem. IbPRIA 2009: 433-440 |
| 2008 | ||
| c15 | | Gábor Gosztolya, László Tóth: Detection of Phoneme Boundaries Using Spiking Neurons. ICAISC 2008: 782-793 |
| c14 | | László Tóth, Joe Frankel, Gábor Gosztolya, Simon King: Cross-lingual portability of MLP-based tandem features - a case study for English and Hungarian. INTERSPEECH 2008: 2695-2698 |
| 2007 | ||
| j8 | | László Tóth, András Kocsor: A segment-based interpretation of HMM/ANN hybrids. Computer Speech & Language 21(3): 562-578 (2007) |
| j7 | | András Bánhalmi, Dénes Paczolay, László Tóth, András Kocsor: Development of a Hungarian Medical Dictation System. Informatica (Slovenia) 31(2): 241-246 (2007) |
| c13 | | László Tóth: Benchmarking human performance on the acoustic and linguistic subtasks of ASR systems. INTERSPEECH 2007: 382-385 |
| 2006 | ||
| c12 | | Istvan Marosi, László Tóth: OCR Voting Methods for Recognizing Low Contrast Printed Documents. DIAL 2006: 108-115 |
| 2005 | ||
| c11 | | László Tóth, András Kocsor: Training HMM/ANN Hybrid Speech Recognizers by Probabilistic Sampling. ICANN (1) 2005: 597-603 |
| c10 | | András Bánhalmi, Kornél Kovács, András Kocsor, László Tóth: Fundamental frequency estimation by least-squares harmonic model fitting. INTERSPEECH 2005: 305-308 |
| c9 | | |
| 2004 | ||
| j6 | | László Tóth, András Kocsor, Gábor Gosztolya: Telephone Speech Recognition via the Combination of Knowledge Sources in a Segmental Speech Model. Acta Cybern. 16(4): 643-657 (2004) |
| j5 | | Gyula Zsigri, András Kocsor, László Tóth, Györgyi Sejtes: Phonetic Level Annotation and Segmentation of Hungarian Speech Databases. Acta Cybern. 16(4): 659-673 (2004) |
| j4 | | András Kocsor, László Tóth: Application of Kernel-Based Feature Space Transformations and Learning Methods to Phoneme Classification. Appl. Intell. 21(2): 129-142 (2004) |
| j3 | | András Kocsor, László Tóth: Kernel-based feature extraction with a speech technology application. IEEE Transactions on Signal Processing 52(8): 2250-2263 (2004) |
| c8 | | László Tóth, Gábor Gosztolya: Replicator Neural Networks for Outlier Modeling in Segmental Speech Recognition. ISNN (1) 2004: 996-1001 |
| 2003 | ||
| j2 | | Gábor Gosztolya, András Kocsor, László Tóth: Various Robust Search Methods in a Hungarian Speech Recognition System. Acta Cybern. 16(2): 229-240 (2003) |
| c7 | | |
| c6 | | Dénes Paczolay, András Kocsor, László Tóth: Real-Time Vocal Tract Length Normalization. TSD 2003: 309-314 |
| 2002 | ||
| c5 | | Kornél Kovács, András Kocsor, László Tóth: Hungarian Speech Synthesis Using a Phase Exact HNM Approach. SOFSEM 2002: 181-185 |
| 2001 | ||
| c4 | | András Kocsor, László Tóth, László Felföldi: Application of Feature Transformation and Learning Methods in Phoneme Classification. IEA/AIE 2001: 502-512 |
| c3 | | András Kocsor, László Tóth, Dénes Paczolay: A Nonlinearized Discriminant Analysis and Its Application to Speech Impediment Therapy. TSD 2001: 249-257 |
| 2000 | ||
| c2 | | László Tóth, András Kocsor, Kornél Kovács: A Discriminative Segmental Speech Model and Its Application to Hungarian Number Recognition. TSD 2000: 307-313 |
| 1999 | ||
| j1 | | András Kocsor, László Tóth, I. Bálint: Optimal Parameters of a Sinusoidal Representation of Signals. Acta Cybern. 14(2): 315-330 (1999) |
| 1997 | ||
| c1 | | Zoltán Alexin, János Csirik, Tibor Gyimóthy, Márk Jelasity, László Tóth: Learning Phonetic Rules in a Speech Recognition System. ILP 1997: 37-44 |
Colors in the list of coauthors
Last update Sat May 18 07:50:23 2013 CET by the DBLP Team —
Data released under the ODC-BY 1.0 license — See also our legal information page