Presentation 2018-03-20
[Poster Presentation] A Hybrid Approach on Electrolaryngeal Speech Enhancement based on Spectral Differential Features and Noise Suppression
Mohammad Eshghi, Kazuhiro Kobayashi, Tomoki Toda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This work presents a hybrid approach for enhancing the quality of the electrolaryngeal (EL) speech. Current hybrid enhancement systems rely on noise suppression and statistical voice conversion techniques. However, utilizing a vocoder to generate the converted waveform usually degrades the quality of the converted speech. To alleviate the quality degradation caused by the vocoder, we proposed a vocoder-free enhancement method based on direct modification of the waveform using differences in spectral features of the EL and normal speeches. After applying a time-variant filter to the EL speech for enhancing its quality, noise suppression is further applied to the enhanced EL speech to reduce remaining time-varying noise components. To evaluate the effectiveness of our proposed method, subjective evaluations based on an opinion test on intelligibility has been performed. Our experimental results show that the proposed method improves intelligibility of the EL speech.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Electrolaryngeal speech enhancement / spectral subtraction / statistical voice conversion / differential spectral features / time-variant filtering
Paper # EA2017-141,SIP2017-150,SP2017-124
Date of Issue 2018-03-12 (EA, SIP, SP)

Conference Information
Committee SIP / EA / SP / MI
Conference Date 2018/3/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English) Speech, Engineering/Electro Acoustics, Signal Processing, and Related Topics [SIP, EA, SP]/ Medical Image Engineering, Analysis, Recognition, etc. [MI]
Chair Masahiro Okuda(Univ. of Kitakyushu) / Suehiro Shimauchi(NTT) / Yoichi Yamashita(Ritsumeikan Univ.) / Kensaku Mori(Nagoya Univ.)
Vice Chair Shogo Muramatsu(Niigata Univ.) / Naoyuki Aikawa(TUS) / Mitsunori Mizumachi(Kyutech) / Hiroki Mori(Utsunomiya Univ.) / Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.)
Secretary Shogo Muramatsu(Chiba Inst. of Tech.) / Naoyuki Aikawa(Takushoku Univ.) / Mitsunori Mizumachi(Akita Pref. Univ.) / Hiroki Mori(Shizuoka Inst. of Science and Tech.) / Yoshiki Kawata(Shizuoka Univ.) / Yuichi Kimura(Meijo Univ.)
Assistant Masayoshi Nakamoto(Hiroshima Univ.ひろ) / TREVINO Jorge(Tohoku Univ.) / Nobutaka Ito(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Satoshi Kobashikawa(NTT) / Ryo Haraguchi(Univ. of Hyogo) / Yasushi Hirano(Yamaguchi Univ.)

Paper Information
Registration To Technical Committee on Signal Processing / Technical Committee on Engineering Acoustics / Technical Committee on Speech / Technical Committee on Medical Imaging
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Poster Presentation] A Hybrid Approach on Electrolaryngeal Speech Enhancement based on Spectral Differential Features and Noise Suppression
Sub Title (in English)
Keyword(1) Electrolaryngeal speech enhancement
Keyword(2) spectral subtraction
Keyword(3) statistical voice conversion
Keyword(4) differential spectral features
Keyword(5) time-variant filtering
1st Author's Name Mohammad Eshghi
1st Author's Affiliation Nagoya University, Graduate School of Information Science(Nagoya Univ.)
2nd Author's Name Kazuhiro Kobayashi
2nd Author's Affiliation Information Technology Center(Nagoya Univ.)
3rd Author's Name Tomoki Toda
3rd Author's Affiliation Information Technology Center(Nagoya Univ.)
Date 2018-03-20
Paper # EA2017-141,SIP2017-150,SP2017-124
Volume (vol) vol.117
Number (no) EA-515,SIP-516,SP-517
Page pp.pp.221-226(EA), pp.221-226(SIP), pp.221-226(SP),
#Pages 6
Date of Issue 2018-03-12 (EA, SIP, SP)