Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Porjazovski, Dejan"'
Test data is said to be out-of-distribution (OOD) when it unexpectedly differs from the training data, a common challenge in real-world use cases of machine learning. Although OOD generalisation has gained interest in recent years, few works have foc
Externí odkaz:
http://arxiv.org/abs/2407.07425
Large pre-trained models are essential in paralinguistic systems, demonstrating effectiveness in tasks like emotion recognition and stuttering detection. In this paper, we employ large pre-trained models for the ACM Multimedia Computational Paralingu
Externí odkaz:
http://arxiv.org/abs/2310.10179
Traditional topic identification solutions from audio rely on an automatic speech recognition system (ASR) to produce transcripts used as input to a text-based model. These approaches work well in high-resource scenarios, where there are sufficient d
Externí odkaz:
http://arxiv.org/abs/2307.11450
Autor:
Moisio, Anssi, Porjazovski, Dejan, Rouhe, Aku, Getman, Yaroslav, Virkkunen, Anja, Grósz, Tamás, Lindén, Krister, Kurimo, Mikko
The Donate Speech campaign has so far succeeded in gathering approximately 3600 hours of ordinary, colloquial Finnish speech into the Lahjoita puhetta (Donate Speech) corpus. The corpus includes over twenty thousand speakers from all the regions of F
Externí odkaz:
http://arxiv.org/abs/2203.12906
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Porjazovski, Dejan
This repository contains the English trained Wav2vec2 models, used in the paper:Improved Automatic Emotion Recognition from Speech with Segmented Processing and Contrastive Loss
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27ce5a1d022c6bab1d0d5f803e8af9aa
Autor:
Moisio, Anssi, Porjazovski, Dejan, Rouhe, Aku, Getman, Yaroslav, Virkkunen, Anja, AlGhezi, Ragheb, Lennes, Mietta, Grósz, Tamás, Lindén, Krister, Kurimo, Mikko
Publikováno v:
Language Resources & Evaluation; Sep2023, Vol. 57 Issue 3, p1295-1327, 33p
Autor:
Porjazovski, Dejan
Baseline X-vector models for age, gender, dialect, and topic classification. The models are trained and evaluated on the Lahjoita puhetta data, described in "Donate Speech -- a large scale Corpus of spoken Finnish with some benchmarks". For details a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2659::bb38a453fb1f10cca43e666db304900d
https://zenodo.org/record/6545342
https://zenodo.org/record/6545342
openaire: EC/H2020/780069/EU//MeMAD Named entities are heavily used in the field of spoken language understanding, which uses speech as an input. The standard way of doing named entity recognition from speech involves a pipeline of two systems, where
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______661::d1e10e34e29af463b650ae569668f0eb
https://aaltodoc.aalto.fi/handle/123456789/110197
https://aaltodoc.aalto.fi/handle/123456789/110197
Autor:
Moisio A; Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland., Porjazovski D; Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland., Rouhe A; Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland., Getman Y; Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland., Virkkunen A; Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland., AlGhezi R; Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland., Lennes M; Department of Digital Humanities, University of Helsinki, Helsinki, Finland., Grósz T; Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland., Lindén K; Department of Digital Humanities, University of Helsinki, Helsinki, Finland., Kurimo M; Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland.
Publikováno v:
Language resources and evaluation [Lang Resour Eval] 2022 Aug 09, pp. 1-33. Date of Electronic Publication: 2022 Aug 09.