Tamás Grósz

Postdoc, Aalto University

Joined

June 2022

Names

Tamás Grósz (Preferred)

Emails

****@aalto.fi (Confirmed)

Personal Links

Career & Education History

Postdoc

Aalto University (aalto.fi)

2019 – Present

Advisors, Relations & Conflicts

Postdoc Advisor

2019 – Present

PhD Advisor

2013 – 2018

Expertise

Deep learning

Present

Automatic Speech Recognition

Present

Paralinguistics

Present

Publications

From Raw Speech to Fixed Representations: A Comprehensive Evaluation of Speech Embedding Techniques
Dejan Porjazovski, Tamás Grósz, Mikko Kurimo
- IEEE ACM Trans. Audio Speech Lang. Process. 2024
- Readers: Everyone
Comparison and analysis of new curriculum criteria for end-to-end ASR
Georgios Karakasidis, Mikko Kurimo, Peter Bell, Tamás Grósz
- Speech Commun. 2024
- Readers: Everyone
Investigating the Clusters Discovered By Pre-Trained AV-HuBERT
Anja Virkkunen, Marek Sarvas, Guangpu Huang, Tamás Grósz, Mikko Kurimo
- ICASSP 2024
- Readers: Everyone
Lahjoita puhetta: a large-scale corpus of spoken Finnish with some benchmarks
Anssi Moisio, Dejan Porjazovski, Aku Rouhe, Yaroslav Getman, Anja Virkkunen, Ragheb Al-Ghezi, Mietta Lennes, Tamás Grósz, Krister Lindén, Mikko Kurimo
- Lang. Resour. Evaluation 2023
- Readers: Everyone
CaptainA - A mobile app for practising Finnish pronunciation
Nhan Phan, Tamás Grósz, Mikko Kurimo
- Published: 20 Mar 2023, Last Modified: 17 Apr 2023
- NoDaLiDa 2023
- Readers: Everyone
Investigating wav2vec2 context representations and the effects of fine-tuning, a case-study of a Finnish model
Tamás Grósz, Yaroslav Getman, Ragheb Al-Ghezi, Aku Rouhe, Mikko Kurimo
- INTERSPEECH 2023
- Readers: Everyone
Advancing Audio Emotion and Intent Recognition with Large Pre-Trained Models and Bayesian Inference
Dejan Porjazovski, Yaroslav Getman, Tamás Grósz, Mikko Kurimo
- ACM Multimedia 2023
- Readers: Everyone
Topic Identification for Spontaneous Speech: Enriching Audio Features with Embedded Linguistic Information
Dejan Porjazovski, Tamás Grósz, Mikko Kurimo
- EUSIPCO 2023
- Readers: Everyone
Discovering Relevant Sub-spaces of BERT, Wav2Vec 2.0, ELECTRA and ViT Embeddings for Humor and Mimicked Emotion Recognition with Integrated Gradients
Tamás Grósz, Anja Virkkunen, Dejan Porjazovski, Mikko Kurimo
- MuSe@ACM Multimedia 2023
- Readers: Everyone
Multi-task wav2vec2 Serving as a Pronunciation Training System for Children
Yaroslav Getman, Ragheb Al-Ghezi, Tamás Grósz, Mikko Kurimo
- SLaTE 2023
- Readers: Everyone

View all 12 publications

Co-Authors