完整後設資料紀錄
DC 欄位語言
dc.contributor.authorLo, Yu-Wenen_US
dc.contributor.authorShen, Yih-Liangen_US
dc.contributor.authorLiao, Yuan-Fuen_US
dc.contributor.authorChi, Tai-Shihen_US
dc.date.accessioned2019-04-02T06:04:14Z-
dc.date.available2019-04-02T06:04:14Z-
dc.date.issued2018-01-01en_US
dc.identifier.urihttp://hdl.handle.net/11536/150765-
dc.description.abstractBefore the era of the neural network (NN), features extracted from auditory models have been applied to various speech applications and been demonstrated more robust against noise than conventional speech-processing features. What's the role of auditory models in the current NN era? Are they obsolete? To answer this question, we construct a NN with a generative auditory model embedded to process speech signals. The generative auditory model consists of two stages, the stage of spectrum estimation in the logarithmic-frequency axis by the cochlea and the stage of spectral-temporal analysis in the modulation domain by the auditory cortex. The NN is evaluated in a simple speaker identification task. Experiment results show that the auditory model embedded NN is still more robust against noise, especially in low SNR conditions, than the randomly-initialized NN in speaker identification.en_US
dc.language.isoen_USen_US
dc.subjectgenerative auditory modelen_US
dc.subjectconvolutional neural networken_US
dc.subjectmulti-resolutionen_US
dc.subjectspeaker identificationen_US
dc.titleA GENERATIVE AUDITORY MODEL EMBEDDED NEURAL NETWORK FOR SPEECH PROCESSINGen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)en_US
dc.citation.spage5179en_US
dc.citation.epage5183en_US
dc.contributor.department電機工程學系zh_TW
dc.contributor.departmentDepartment of Electrical and Computer Engineeringen_US
dc.identifier.wosnumberWOS:000446384605070en_US
dc.citation.woscount0en_US
顯示於類別:會議論文