BCN2BRNO Automatic speech recognition system for Albayzin 2022 Speech to Text Challenge
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APR37717" target="_blank" >RIV/00216305:26230/22:PR37717 - isvavai.cz</a>
Result on the web
<a href="https://www.fit.vut.cz/research/product/797/" target="_blank" >https://www.fit.vut.cz/research/product/797/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
BCN2BRNO Automatic speech recognition system for Albayzin 2022 Speech to Text Challenge
Original language description
The software is based on the development of Automatic Speech Recognition systems for the Albayzin 2022 Challenge. We trained and evaluated both hybrid systems and those based on end-to-end models. We also investigated the use of self-supervised learning speech representations from pre-trained models and their impact on ASR performance (as opposed to training models directly from scratch). Additionally, we also applied the Whisper model in a zero-shot fashion, postprocessing its output to fit the required transcription format. On top of tuning the model architectures and overall training schemes, we improved the robustness of our models by augmenting the training data with noises extracted from the target domain. Moreover, we applied rescoring with an external LM on top of N-best hypotheses to adjust each sentence score and pick the single best hypothesis. All these efforts lead to a significant WER reduction. Our single best system and the fusion of selected systems achieved 16.3% and 13.7% WER respectively on RTVE2020 test partition, i.e. the official evaluation partition from the previous Albayzin challenge
Czech name
—
Czech description
—
Classification
Type
R - Software
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/LTAIN19087" target="_blank" >LTAIN19087: Multi-linguality in speech technologies</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Internal product ID
R1-LTAIN19087
Technical parameters
Pro stažení kontaktujte: Vysoké učení technické v Brně, IČ: 00216305, Ing. Martin Kocour, Fakulta Informační technologií, Božetěchova 2/1 612 00 Brno, tel.: 541141283, ikocour@fit.vut.cz, https://www.fit.vut.cz/person/ikocour/
Economical parameters
Produkt vznikl v rámci vývojově-výzkumné činnosti na FIT VUT v Brně, zejména díky česko-indické spolupráci financované z projektu: LTAIN19087 - Multi-lingualita v řečových technologiích.
Owner IČO
00216305
Owner name
Vysoké učení technické v Brně