Search Results for author: Martin Kocour

Found 10 papers, 3 papers with code

Hystoc: Obtaining word confidences for fusion of end-to-end ASR systems

no code implementations21 May 2023 Karel Beneš, Martin Kocour, Lukáš Burget

Furthermore, we show that utilizing Hystoc in fusion of multiple e2e ASR systems increases the gains from the fusion by up to 1\,\% WER absolute on Spanish RTVE2020 dataset.

Automatic Speech Recognition speech-recognition +1

Analysis of impact of emotions on target speech extraction and speech separation

1 code implementation15 Aug 2022 Ján Švec, Kateřina Žmolíková, Martin Kocour, Marc Delcroix, Tsubasa Ochiai, Ladislav Mošner, Jan Černocký

One of the factors causing such degradation may be intrinsic speaker variability, such as emotions, occurring commonly in realistic speech.

Speaker Verification Speech Extraction

Call-sign recognition and understanding for noisy air-traffic transcripts using surveillance information

no code implementations13 Apr 2022 Alexander Blatt, Martin Kocour, Karel Veselý, Igor Szöke, Dietrich Klakow

The introduced data augmentation adds additional performance on high WER transcripts and allows the adaptation of the model to unseen airspaces.

Data Augmentation

Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model

1 code implementation31 Oct 2021 Martin Kocour, Kateřina Žmolíková, Lucas Ondel, Ján Švec, Marc Delcroix, Tsubasa Ochiai, Lukáš Burget, Jan Černocký

We modify the acoustic model to predict joint state posteriors for all speakers, enabling the network to express uncertainty about the attribution of parts of the speech signal to the speakers.

speech-recognition Speech Recognition

GPU-Accelerated Forward-Backward algorithm with Application to Lattice-Free MMI

no code implementations22 Oct 2021 Lucas Ondel, Léa-Marie Lam-Yee-Mui, Martin Kocour, Caio Filippo Corro, Lukáš Burget

We propose to express the forward-backward algorithm in terms of operations between sparse matrices in a specific semiring.

Detecting English Speech in the Air Traffic Control Voice Communication

no code implementations6 Apr 2021 Igor Szoke, Santosh Kesiraju, Ondrej Novotny, Martin Kocour, Karel Vesely, Jan "Honza" Cernocky

The proposed English Language Detection (ELD) system is based on the embeddings from Bayesian subspace multinomial model.

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