Understanding Speech and Scene with Ears and Eyes

Kurimo, Mikko (Principal investigator)
Virkkunen, Anja (Project Member)
Sarvas, Marek (Project Member)
Grósz, Tamás (Project Member)

Acronym	USSEE
Status	Finished
Effective start/end date	01/01/2022 → 31/12/2024

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

SDG 5 Gender Equality

Is your model big enough? Training and interpreting large-scale monolingual speech foundation models
Getman, Y., Grósz, T., Lehtonen, T. & Kurimo, M., 2025, Proceedings of the Interspeech. International Speech Communication Association (ISCA), p. 231-235 5 p. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).
Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Open Access
Leveraging Uncertainty for Finnish L2 Speech Scoring with LLMs
Voskoboinik, E., Phan, N., Grósz, T. & Kurimo, M., 2025, The Workshop on Automatic Assessment of Atypical Speech (AAAS-2025). Proceedings of the Workshop. University of Tartu Library, 9 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Open Access
File
98 Downloads (Pure)
Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition
Bijoy, M. H., Porjazovski, D., Grósz, T. & Kurimo, M., 2025, Proceedings of the Interspeech. International Speech Communication Association (ISCA), p. 146-150 5 p. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).
Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Open Access

Lahjoita puhetta semisupervised baseline Kaldi ASR model
Grósz, T. (Creator), Zenodo, 13 May 2022
DOI: 10.5281/zenodo.6545289
Dataset: Software or code

Understanding Speech and Scene with Ears and Eyes

Project Details

UN Sustainable Development Goals

Fingerprint

Is your model big enough? Training and interpreting large-scale monolingual speech foundation models

Leveraging Uncertainty for Finnish L2 Speech Scoring with LLMs

Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition

Lahjoita puhetta semisupervised baseline Kaldi ASR model

Understanding Speech and Scene with Ears and Eyes

Project Details

UN Sustainable Development Goals

Fingerprint

Research output

Is your model big enough? Training and interpreting large-scale monolingual speech foundation models

Leveraging Uncertainty for Finnish L2 Speech Scoring with LLMs

Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition

Datasets

Lahjoita puhetta semisupervised baseline Kaldi ASR model