Gosztolya G, Tóth L.  2018.  A feature selection-based speaker clustering method for paralinguistic tasks. Pattern Analysis and Applications. 21:193–204.

Tóth L, Hoffmann I, Gosztolya G, Vincze V, Szatlóczki G, Bánréti Z, Pákáski M, Kálmán J.  2018.  A Speech Recognition-based Solution for the Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech. Current Alzheimer Research. 15:130–138.

Grósz T, Gosztolya G, Tóth L.  2017.  A Comparative Evaluation of GMM-Free State Tying Methods for ASR. Proceedings of Interspeech. :1626–1630.

Gosztolya G, Busa-Fekete R, Grósz T, Tóth L.  2017.  DNN-Based Feature Extraction and Classifier Combination for Child-Directed Speech, Cold and Snoring Identification. Proceedings of Interspeech. :3522–3526.

Gosztolya G, Tóth L.  2017.  DNN-based Feature Extraction for Conflict Intensity Estimation from Speech. IEEE Signal Processing Letters. 24:1837–1841.

Csapó TGábor, Grósz T, Gosztolya G, Tóth L, Markó A.  2017.  DNN-Based Ultrasound-to-Speech Conversion for a Silent Speech Interface. Proceedings of Interspeech. :3672–3676.

Grósz T, Gosztolya G, Tóth L.  2017.  Training Context-Dependent DNN Acoustic Models Using Probabilistic Sampling. Proceedings of Interspeech. :1621–1625.

Gosztolya G, Grósz T, Tóth L.  2016.  GMM-Free Flat Start Sequence-Discriminative DNN Training. Proceedings of Interspeech. :3409–3413.

Tóth L, Kocsor A.  2003.  Harmonic alternatives to sine-wave speech. INTERSPEECH.

Gosztolya G, Kocsor A, Tóth L, Felföldi L.  2003.  Various Robust Search Methods in a Hungarian Speech Recognition System. Acta Cybernetica. 16:229–240.