loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Jiri Malek ; Petr Cerva ; Ladislav Seps and Jan Nouza

Affiliation: Technical University of Liberec, Czech Republic

Keyword(s): Deep Neural Networks, Bottleneck Features, Real-world Nonlinear Distortion, Robust Speech Recognition.

Related Ontology Subjects/Areas/Topics: Design and Implementation of Signal Processing Systems ; Multimedia ; Multimedia Signal Processing ; Multimedia Systems and Applications ; Neural Networks, Spiking Systems, Genetic Algorithms and Fuzzy Logic ; Telecommunications

Abstract: This paper focuses on the robust recognition of nonlinearly distorted speech. We have reported (Seps et al., 2014) that hybrid acoustic models based on a combination of Hidden Markov Models and Deep Neural Networks (HMM-DNNs) are better suited to this task than conventional HMMs utilizing Gaussian Mixture Models (HMM-GMMs). To further improve recognition accuracy, this paper investigates the possibility of combining the modeling power of deep neural networks with the adaptation to given acoustic conditions. For this purpose, the deep neural networks are utilized to produce bottleneck coefficients / features (BNC). The BNCs are subsequently used for training of HMM-GMM based acoustic models and then adapted using Constrained Maximum Likelihood Linear Regression (CMLLR). Our results obtained for three types of nonlinear distortions and three types of input features show that the adapted BNC-based system (a) outperforms HMM-DNN acoustic models in the case of strong compression and (b) y ields comparable performance for speech affected by nonlinear amplification in the analog domain. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.203.221.104

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Malek, J.; Cerva, P.; Seps, L. and Nouza, J. (2016). Study on the Use and Adaptation of Bottleneck Features for Robust Speech Recognition of Nonlinearly Distorted Speech. In Proceedings of the 13th International Joint Conference on e-Business and Telecommunications (ICETE 2016) - SIGMAP; ISBN 978-989-758-196-0; ISSN 2184-3236, SciTePress, pages 65-71. DOI: 10.5220/0005955500650071

@conference{sigmap16,
author={Jiri Malek. and Petr Cerva. and Ladislav Seps. and Jan Nouza.},
title={Study on the Use and Adaptation of Bottleneck Features for Robust Speech Recognition of Nonlinearly Distorted Speech},
booktitle={Proceedings of the 13th International Joint Conference on e-Business and Telecommunications (ICETE 2016) - SIGMAP},
year={2016},
pages={65-71},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005955500650071},
isbn={978-989-758-196-0},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on e-Business and Telecommunications (ICETE 2016) - SIGMAP
TI - Study on the Use and Adaptation of Bottleneck Features for Robust Speech Recognition of Nonlinearly Distorted Speech
SN - 978-989-758-196-0
IS - 2184-3236
AU - Malek, J.
AU - Cerva, P.
AU - Seps, L.
AU - Nouza, J.
PY - 2016
SP - 65
EP - 71
DO - 10.5220/0005955500650071
PB - SciTePress