Department of Signal Processing and Acoustics

Speech recognition

Our goal is to generally improve the speech recognition methodology with the help of the new algorithms developed in Aalto University. Speech recognition offers challenging benchmarking tasks for efficient algorithms that can process and learn to represent large quantities of data. In addition to improving the acoustic models of phonemes we aim at developing new learning statistical language models for difficult large vocabulary continuous speech recognition tasks.
srdemo_small.jpg

 

Research Overview

We currently specialize in the following research areas in speech recognition:

  • Sub-word units and deep learning in language modeling
  • Speaker adaptation and pronunciation rating in acoustic modeling
  • Unlimited vocabulary continuous speech recognition
  • Speech recognition and language modeling methods for under-resourced languages
  • Methods for describing and translating audiovisual
  • Speaker and language recognition and diarization

We are part of Finnish Center of Artificial Intelligence (FCAI, https://fcai.fi/).

Group members

Mikko Kurimo

Professori (Associate professor)
[email protected]
+358503476221

Katri Leino

Tohtorikoulutettava
[email protected]

Aku Rouhe

Doctoral Candidate
[email protected]

Anja Virkkunen

Tohtorikoulutettava
[email protected]

Juho Leinonen

Doctoral Candidate
[email protected]

Tamás Grósz

Postdoctoral Researcher
[email protected]
+358417044324

Yaroslav Getman

Research Assistant
[email protected]

Software & Demonstrations

Software produced as part of our research is available on our GitHub

Demonstration videos of our research work can be watched on our YouTube Channel

Latest publications

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

Tamás Grósz, Mikko Kurimo 2021 Text, Speech, and Dialogue - 24th International Conference, TSD 2021, Proceedings

An Equal Data Setting for Attention-Based Encoder-Decoder and HMM/DNN Models: A Case Study in Finnish ASR

Aku Rouhe, Astrid Van Camp, Mittul Singh, Hugo Van Hamme, Mikko Kurimo 2021 Speech and Computer - 23rd International Conference, SPECOM 2021, Proceedings

Synthesis Speech Based Data Augmentation for Low Resource Children ASR

Virender Kadyan, Hemant Kathania, Prajjval Govil, Mikko Kurimo 2021 Speech and Computer - 23rd International Conference, SPECOM 2021, Proceedings

Morphologically motivated word classes for very large vocabulary speech recognition of Finnish and Estonian

Matti Varjokallio, Sami Virpioja, Mikko Kurimo 2021 Computer Speech and Language

Advances in subword-based HMM-DNN speech recognition across languages

Peter Smit, Sami Virpioja, Mikko Kurimo 2021 Computer Speech and Language

The Effects of a Digital Articulatory Game on the Ability to Perceive Speech-Sound Contrasts in Another Language

Sari Ylinen, Anna Riikka Smolander, Reima Karhila, Sofoklis Kakouros, Jari Lipsanen, Minna Huotilainen, Mikko Kurimo 2021 Frontiers in Education

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

Dejan Porjazovski, Juho Leinonen, Mikko Kurimo 2021 Text, Speech, and Dialogue - 24th International Conference, TSD 2021, Proceedings

Vowel non-vowel based spectral warping and time scale modification for improvement in children’s ASR

Hemant Kathania, Avinash Kumar, Mikko Kurimo 2021 IEEE International Conference on Acoustics, Speech and Signal Processing

Using data augmentation and time-scale modification to improve ASR of children’s speech in noisy environments

Hemant Kathania, Sudarsana Kadiri, Paavo Alku, Mikko Kurimo 2021 APPLIED SCIENCES

Spectral modification for recognition of children’s speech under mismatched conditions

Hemant Kathania, Sudarsana Kadiri, Paavo Alku, Mikko Kurimo 2021 Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
More information on our research in the Research database.
Research database
  • Published:
  • Updated:
Share
URL copied!