IEEE ICASSP 2018 || Calgary, Alberta, Canada || 15-20 April 2018

Technical Program

SP-P14: Speech Synthesis, Generation and Coding

Session Type: Poster
Time: Thursday, April 19, 16:00 - 18:00
Location: Poster Area B
Session Chair: Tim Fingscheidt, Technische Universit├Ąt Braunschweig
 
SP-P14.1: B-SPLINE PDF: A GENERALIZATION OF HISTOGRAMS TO CONTINUOUS DENSITY MODELS FOR GENERATIVE AUDIO NETWORKS
         Ioannis Agiomyrgiannakis; Google Inc.
 
SP-P14.2: AN INVESTIGATION OF SUBBAND WAVENET VOCODER COVERING ENTIRE AUDIBLE FREQUENCY RANGE WITH LIMITED ACOUSTIC FEATURES
         Takuma Okamoto; National Institute of Information and Communications Technology
         Kentaro Tachibana; National Institute of Information and Communications Technology
         Tomoki Toda; Nagoya University
         Yoshinori Shiga; National Institute of Information and Communications Technology
         Hisashi Kawai; National Institute of Information and Communications Technology
 
SP-P14.3: SAMPLERNN-BASED NEURAL VOCODER FOR STATISTICAL PARAMETRIC SPEECH SYNTHESIS
         Yang Ai; University of Science and Technology of China
         Hong-Chuan Wu; University of Science and Technology of China
         Zhen-Hua Ling; University of Science and Technology of China
 
SP-P14.4: AN INVESTIGATION OF NOISE SHAPING WITH PERCEPTUAL WEIGHTING FOR WAVENET-BASED SPEECH GENERATION
         Kentaro Tachibana; National Institute of Information and Communications Technology
         Tomoki Toda; Nagoya University
         Yoshinori Shiga; National Institute of Information and Communications Technology
         Hisashi Kawai; National Institute of Information and Communications Technology
 
SP-P14.5: MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM
         Min-Jae Hwang; Yonsei University
         Eunwoo Song; Naver Corp.
         Kyungguen Byun; Yonsei University
         Hong-Goo Kang; Yonsei University
 
SP-P14.6: ON THE USE OF WAVENET AS A STATISTICAL VOCODER
         Nagaraj Adiga; University of Crete
         Vassilis Tsiaras; University of Crete
         Yannis Stylianou; University of Crete
 
SP-P14.7: SPEECH WAVEFORM SYNTHESIS FROM MFCC SEQUENCES WITH GENERATIVE ADVERSARIAL NETWORKS
         Lauri Juvela; Aalto University
         Bajibabu Bollepalli; Aalto University
         Xin Wang; National Institute of Informatics
         Hirokazu Kameoka; NTT Corporation
         Manu Airaksinen; Aalto University
         Junichi Yamagishi; National Institute of Informatics
         Paavo Alku; Aalto University
 
SP-P14.8: ON THE ANALYSIS OF TRAINING DATA FOR WAVENET-BASED SPEECH SYNTHESIS
         Jakub Vit; University of West Bohemia
         Zdenek Hanzlicek; University of West Bohemia
         Jindrich Matousek; University of West Bohemia
 
SP-P14.9: GMM-BASED ITERATIVE ENTROPY CODING FOR SPECTRAL ENVELOPES OF SPEECH AND AUDIO
         Srikanth Korse; Fraunhofer IIS
         Guillaume Fuchs; International Audio Laboratories, Friedrich-Alexander University (FAU), Erlangen, Germany, Fraunhofer IIS, Erlangen, Germany
         Tom Baeckstroem; Aalto University, Helsinki
 
SP-P14.10: PERSONALIZED SPONTANEOUS SPEECH SYNTHESIS USING A SMALL-SIZED UNSEGMENTED SEMISPONTANEOUS SPEECH
         Yi-Chin Huang; Feng Chia University
         Chung-Hsien Wu; National Cheng Kung University
         Yan-You Chen; National Cheng Kung University
         Ming-Ge Shie; National Cheng Kung University
         Jhing-Fa Wang; National Cheng Kung University