[PDF][PDF] Finnish ASR with deep transformer models

A Jain, A Rouhe, SA Grönroos… - Interspeech 2020, 2020 - researchportal.helsinki.fi
Finnish ASR with Deep Transformer Models Page 1 Finnish ASR with Deep Transformer Models
Abhilash Jain, Aku Rouhe, Stig-Arne Grönroos, Mikko Kurimo Department of Signal Processing …

[PDF][PDF] Language Modeling for Speech Analytics in Under-Resourced Languages.

S Wills, P Uys, CJ van Heerden, E Barnard - INTERSPEECH, 2020 - isca-archive.org
Different language modeling approaches are evaluated on two under-resourced,
agglutinative, South African languages; Sesotho and isiZulu. The two languages present …

Attention-based End-to-End Models in Language Technology

A Rouhe - 2024 - aaltodoc.aalto.fi
Speech recognition specifically, and language technology more generally, have started to
find everyday use. Challenging language tasks have become feasible through a continued …

LSTM-XL: Attention Enhanced Long-Term Memory for LSTM Cells

T Grósz, M Kurimo - International Conference on Text, Speech, and …, 2021 - Springer
Abstract Long Short-Term Memory (LSTM) cells, frequently used in state-of-the-art language
models, struggle with long sequences of inputs. One major problem in their design is that …

Finnish Language Modeling with Deep Transformer Models

A Jain, A Ruohe, SA Grönroos, M Kurimo - arXiv preprint arXiv …, 2020 - arxiv.org
Transformers have recently taken the center stage in language modeling after LSTM's were
considered the dominant model architecture for a long time. In this project, we investigate …

[PDF][PDF] Puheohjaus web-sovelluksissa

M Kosola - 2020 - theseus.fi
Tämän opinnäytetyön tarkoituksena oli perehtyä puheentunnistuksen teknologiaan,
sekä selvittää, miten web-sovelluksia voidaan ohjata puheella. Työn taustalla oli oma …