Publications

Found 14 results
Author Keyword Title Type [ Year(Asc)]
Filters: Author is Gosztolya, Gábor  [Clear All Filters]
2019
Gosztolya G, Pintér Á, Tóth L, Grósz T, Markó A, Csapó TGábor.  2019.  Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces. Proceedings of IJCNN.
Gosztolya G, Busa-Fekete R.  2019.  Calibrating AdaBoost for Phoneme Classification. Soft Computing. 23:115–128.
Gosztolya G, Tóth L.  2019.  Calibrating DNN Posterior Probability Estimates of HMM/DNN Models to Improve Social Signal Detection From Audio Data. Proceedings of Interspeech. :515–519.
Gosztolya G, Vincze V, Tóth L, Pákáski M, Kálmán J, Hoffmann I.  2019.  Identifying Mild Cognitive Impairment and mild Alzheimer’s disease based on spontaneous speech using ASR and linguistic features. Computer, Speech & Language. 53:181–197.
Gosztolya G.  2019.  Posterior-Thresholding Feature Extraction for Paralinguistic Speech Classification. Knowledge-Based Systems. 186
Tóth L, Gosztolya G.  2019.  Reducing the Inter-speaker Variance of CNN Acoustic Models Using Unsupervised Adversarial Multi-task Training. Proceedings of SPECOM. :481–490.
Csapó TGábor, Al-Radhi MSalah, Németh G, Gosztolya G, Grósz T, Tóth L, Markó A.  2019.  Ultrasound-based Silent Speech Interface Built on a Continuous Vocoder. Proceedings of Interspeech. :894–898.
Gosztolya G.  2019.  Using Fisher Vector and Bag-of-Audio-Words Representations to Identify Styrian Dialects, Sleepiness, Baby & Orca Sounds. Proceedings of Interspeech. :2413–2417.
Gosztolya G.  2019.  Using the Bag-of-Audio-Word Feature Representation of ASR DNN Posteriors for Paralinguistic Classification. Proceedings of Interspeech. :2413–2417.
2003
Gosztolya G, Kocsor A.  2003.  Improving the Multi-stack Decoding Algorithm in a Segment-based Speech Recognizer. Proceedings of the 16th International Conference on Developments in Applied Artificial Intelligence. :744–749.
Gosztolya G, Kocsor A, Tóth L, Felföldi L.  2003.  Various Robust Search Methods in a Hungarian Speech Recognition System. Acta Cybernetica. 16:229-240.