Ihmiset

Dejan Porjazovski

Doctoral Researcher

T412 Department of Information and Communications Engineering

Full researcher profile

https://research.aalto.fi/...

Sähköposti

[email protected]

Puhelinnumero

+358503394605

Osaamisalueet

spoken language understanding, 113 Computer and information sciences

Palkinnot

The ACM Multimedia 2023 Computational Paralinguistics Challenge Prize

We have received the prize for winning the Emotion Share sub-challenge. More info at http://www.compare.openaudio.eu/winners/

Invitation or ranking in competition Speech Recognition Jan 2023

Tutkimusryhmät

Speech Recognition, Doctoral Researcher

Julkaisut

Multimodal Humor Detection and Social Perception Prediction

Mehedi Hasan Bijoy, Dejan Porjazovski, Nhan Phan, Guangpu Huang, Tamás Grósz, Mikko Kurimo 2024 MuSe 2024 - Proceedings of the 5th Multimodal Sentiment Analysis Challenge and Workshop

From Raw Speech to Fixed Representations: A Comprehensive Evaluation of Speech Embedding Techniques

Dejan Porjazovski, Tamas Grosz, Mikko Kurimo 2024 IEEE/ACM Transactions on Audio Speech and Language Processing

Improved Spoken Emotion Recognition With Combined Segment-Based Processing And Triplet Loss

Dejan Porjazovski, Tamás Grósz, Mikko Kurimo 2024 Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024)

Out-of-distribution generalisation in spoken language understanding

Dejan Porjazovski, Anssi Moisio, Mikko Kurimo 2024 Interspeech 2024

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 2023 MuSe '23: Proceedings of the 4th on Multimodal Sentiment Analysis Challenge and Workshop: Mimicked Emotions, Humour and Personalisation

Dejan Porjazovski

Osaamisalueet

Palkinnot

The ACM Multimedia 2023 Computational Paralinguistics Challenge Prize

Tutkimusryhmät

Julkaisut

Multimodal Humor Detection and Social Perception Prediction

From Raw Speech to Fixed Representations: A Comprehensive Evaluation of Speech Embedding Techniques

Improved Spoken Emotion Recognition With Combined Segment-Based Processing And Triplet Loss

Out-of-distribution generalisation in spoken language understanding

Discovering Relevant Sub-spaces of BERT, Wav2Vec 2.0, ELECTRA and ViT Embeddings for Humor and Mimicked Emotion Recognition with Integrated Gradients

Lahjoita puhetta: a large-scale corpus of spoken Finnish with some benchmarks

Advancing Audio Emotion and Intent Recognition with Large Pre-Trained Models and Bayesian Inference

Topic Identification for Spontaneous Speech: Enriching Audio Features with Embedded Linguistic Information

Wav2vec2-based Paralinguistic Systems to Recognise Vocalised Emotions and Stuttering

Attention-Based End-To-End Named Entity Recognition From Speech