Result Details

DNN derived filters for processing of modulation spectrum of speech

PEŠÁN, J.; BURGET, L.; HEŘMANSKÝ, H.; VESELÝ, K. DNN derived filters for processing of modulation spectrum of speech. In Proceedings of Interspeech 2015. Proceedings of Interspeech. Dresden: International Speech Communication Association, 2015. no. 09, p. 1908-1911. ISBN: 978-1-5108-1790-6. ISSN: 1990-9772.
Type
conference paper
Language
English
Authors
Pešán Jan, Ing., DCGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Heřmanský Hynek, prof. Ing., Dr. Eng., DCGM (FIT)
Veselý Karel, Ing., Ph.D., DCGM (FIT)
Abstract

In this paper DNN paradigm was successfully used for design of modulation frequency FIR filters. This technique optimized the whole process of deriving posterior probabilities of speech sound classes
(three-state phonemes).

Keywords

deep neural network, convolutive layer, modulationfilters, mammalian auditory processing

URL
Annotation

We propose a novel approach to design modulation frequency filters for the first stage processing of critical band spectrum of speech using deep neural network (DNN). These filters replace conventional modulation frequency filters currently used in state-of-the-art BUT speech recognition system and yield about 10% relative improvement in phoneme recognition accuracy. The resulting filters are consistent with some known temporal properties of higher levels of mammalian auditory processing and suggest more efficient scheme for pre-processing of speech for ASR.

Published
2015
Pages
1908–1911
Journal
Proceedings of Interspeech, vol. 2015, no. 09, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2015
Conference
Interspeech Conference
ISBN
978-1-5108-1790-6
Publisher
International Speech Communication Association
Place
Dresden
UT WoS
000380581600400
EID Scopus
2-s2.0-84959176561
BibTeX 
@inproceedings{BUT119905,
  author="Jan {Pešán} and Lukáš {Burget} and Hynek {Heřmanský} and Karel {Veselý}",
  title="DNN derived filters for processing of modulation spectrum of speech",
  booktitle="Proceedings of Interspeech 2015",
  year="2015",
  journal="Proceedings of Interspeech",
  volume="2015",
  number="09",
  pages="1908--1911",
  publisher="International Speech Communication Association",
  address="Dresden",
  isbn="978-1-5108-1790-6",
  issn="1990-9772",
  url="https://www.fit.vut.cz/research/publication/10969/"
}
Files
Projects
Centrum excelence IT4Innovations, MŠMT, Operační program Výzkum a vývoj pro inovace, ED1.1.00/02.0070, start: 2011-01-01, end: 2015-12-31, completed
DARPA Robust Automatic Transcription of Speech (RATS) - RATS Patrol II, BBN, start: 2015-02-23, end: 2017-03-31, completed
IARPA Building Speech Recognition for Keyword Search in a New Language in a Week with Limited Training Data (BABEL) - Babelon, BBN, start: 2012-03-05, end: 2016-11-04, completed
Meeting Assistant (MINT), TAČR, Program aplikovaného výzkumu a experimentálního vývoje ALFA, TA04011311, start: 2014-10-01, end: 2017-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top