Some experiences on applying deep learning to speech signal and natural language processing

Yuan Fu Liao, Yih-Ru Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the advent of deep learning there has been a major paradigm shift in how speech signal and text processing techniques work. In this paper, we would like to share our experiences/recent works on applying deep neural networks (DNNs) to adaptive microphone array speech enhancement, sentiment analysis, speech recognition, language recognition and text-to-speech (TTS). In those tasks, many different DNN structures and learning strategies were involved including DNN, convolutional neural network (CNN), recurrent neural network (RNN) and long-short-term memory (LSTM). Experimental results all show DNNs are quite promising.

Original languageEnglish
Title of host publicationDISA 2018 - IEEE World Symposium on Digital Intelligence for Systems and Machines, Proceedings
EditorsPeter Sincak, Jan Paralic, Laszlo Kovacs, XenFu Wang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages83-94
Number of pages12
ISBN (Electronic)9781538651025
DOIs
StatePublished - 11 Oct 2018
Event1st IEEE World Symposium on Digital Intelligence for Systems and Machines, DISA 2018 - Kosice, Slovakia
Duration: 23 Aug 201825 Aug 2018

Publication series

NameDISA 2018 - IEEE World Symposium on Digital Intelligence for Systems and Machines, Proceedings

Conference

Conference1st IEEE World Symposium on Digital Intelligence for Systems and Machines, DISA 2018
CountrySlovakia
CityKosice
Period23/08/1825/08/18

Fingerprint Dive into the research topics of 'Some experiences on applying deep learning to speech signal and natural language processing'. Together they form a unique fingerprint.

Cite this