Conference paper

PEŠÁN Jan, BURGET Lukáš, HEŘMANSKÝ Hynek and VESELÝ Karel. DNN derived filters for processing of modulation spectrum of speech. In: Proceedings of Interspeech 2015. Dresden: International Speech Communication Association, 2015, pp. 1908-1911. ISBN 978-1-5108-1790-6. ISSN 1990-9772.
Publication language:english
Original title:DNN derived filters for processing of modulation spectrum of speech
Title (cs):Filtry získané pomocí DNN pro zpracování modulačního spektra řeči
Proceedings:Proceedings of Interspeech 2015
Conference:INTERSPEECH 2015
Place:Dresden, DE
Journal:Proceedings of Interspeech, Vol. 2015, No. 09, FR
Publisher:International Speech Communication Association
deep neural network, convolutive layer, modulation filters, mammalian auditory processing
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).
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.
   author = {Jan Pe{\v{s}}{\'{a}}n and Luk{\'{a}}{\v{s}} Burget
	and Hynek He{\v{r}}mansk{\'{y}} and Karel
   title = {DNN derived filters for processing of modulation
	spectrum of speech},
   pages = {1908--1911},
   booktitle = {Proceedings of Interspeech 2015},
   journal = {Proceedings of Interspeech},
   volume = 2015,
 number = 09,
   year = 2015,
   location = {Dresden, DE},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-5108-1790-6},
   ISSN = {1990-9772},
   language = {english},
   url = {}

Your IPv4 address:
Switch to https