Search Results for author: Hari Krishna Vydana

Found 6 papers, 1 papers with code

A Technical Report: BUT Speech Translation Systems

no code implementations22 Oct 2020 Hari Krishna Vydana, Lukas Burget, Jan Cernocky

To reduce this performance degradation, we have jointly-trained ASR and MT modules with ASR objective as an auxiliary loss.

Translation

Jointly Trained Transformers models for Spoken Language Translation

no code implementations25 Apr 2020 Hari Krishna Vydana, Martin Karafi'at, Katerina Zmolikova, Luk'as Burget, Honza Cernocky

Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to translate source text to text in target language.

automatic-speech-recognition Language Modelling +3

BUT Opensat 2019 Speech Recognition System

no code implementations30 Jan 2020 Martin Karafiát, Murali Karthick Baskar, Igor Szöke, Hari Krishna Vydana, Karel Veselý, Jan "Honza'' Černocký

The paper describes the BUT Automatic Speech Recognition (ASR) systems submitted for OpenSAT evaluations under two domain categories such as low resourced languages and public safety communications.

automatic-speech-recognition Data Augmentation +1

Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

1 code implementation8 Apr 2019 Lucas Ondel, Hari Krishna Vydana, Lukáš Burget, Jan Černocký

This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages.

Acoustic Unit Discovery

Cannot find the paper you are looking for? You can Submit a new open access paper.