Sirvi Autor "Alumäe, Tanel" järgi
Nüüd näidatakse 1 - 5 5
- Tulemused lehekülje kohta
- Sorteerimisvalikud
listelement.badge.dso-type Kirje , listelement.badge.access-status Avatud juurdepääs , Automatic Closed Captioning for Estonian Live Broadcasts(University of Tartu Library, 2023-05) Alumäe, Tanel; Kalda, Joonas; Bode, Külliki; Kaitsa, Martinlistelement.badge.dso-type Kirje , listelement.badge.access-status Avatud juurdepääs , Automatic Compound Word Reconstruction for Speech Recognition of Compounding Languages(Tartu, Estonia, University of Tartu, Estonia, pp. 5--12, 2007) Alumäe, Tanel; Nivre, Joakim; Kaalep, Heiki-Jaan; Muischnek, Kadri; Koit, Marelistelement.badge.dso-type Kirje , listelement.badge.access-status Avatud juurdepääs , Automatic Compound Word Reconstruction for Speech Recognitionof Compounding Languages(2007-05-21T09:08:12Z) Alumäe, Tanellistelement.badge.dso-type Kirje , listelement.badge.access-status Avatud juurdepääs , Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs(University of Tartu Library, 2025-03) Fedorchenko, Artem; Alumäe, Tanel; Johansson, Richard; Stymne, SaraThis paper presents an approach for generating high-quality, same-language subtitles for Estonian TV content. We finetune the Whisper model on human-generated Estonian subtitles and enhance it with iterative pseudo-labeling and large language model (LLM) based post-editing. Our experiments demonstrate notable subtitle quality improvement through pseudo-labeling with an unlabeled dataset. We find that applying LLM-based editing at test time enhances subtitle accuracy, while its use during training does not yield further gains. This approach holds promise for creating subtitle quality close to human standard and could be extended to real-time applications.listelement.badge.dso-type Kirje , listelement.badge.access-status Avatud juurdepääs , Summarization ja arvuti poolt assisteeritud orienteerumine suurtes tekstimassiivides(2022-11-01) Alumäe, Tanel