Source-Filter based Full-band Adaptive Harmonic Model and Its Application to Speech Prosody Modification

International Conference
2013-08-25 00:21
Authors : JeeSok Lee, Frank Soong, Hong-Goo Kang

Year : 2013

Publisher / Conference : INTERSPEECH

This paper presents a source-filter based adaptive harmonic model (aHM) that can modify prosody of given speech signals. Although the conventional aHM generates a homogeneous replication of the input speech, it is not suitable for prosody modification since temporal and spectral information are interweaved. The proposed method overcomes such limitation by further decomposing the harmonic parameter extracted from aHM into source and filter related components. By applying source-filter structure to aHM, the proposed algorithm can modify pitch of the synthesized speech with introducing only minor degradation. Both objective and subjective test results show that the proposed algorithm can naturally manipulate pitch contour, of which performance is much better than conventional algorithms such as pitch synchronous overlap add (PSOLA) and speech transformation and representation using adaptive interpolation of weighted spectrum (STRAIGHT). Index Terms: Prosody modification, pitch modification, speech analysis, speech synthesis, harmonic model.
전체 327
18 International Conference Soonho Baek, Hong-Goo Kang "Vector Taylor Series based HMM Adaptation for Generalized Cepstrum in Noisy Environment" in ASRU, 2013
17 International Conference Jung-Won Lee, Hong-Goo Kang, Samuel Kim, Yoonjae Lee "Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio" in APSIPA, 2013
16 International Conference Eunwoo Song, Jongyoub Ryu, Hong-Goo Kang "Speech enhancement for pathological voice using time-frequency trajectory excitation modeling" in APSIPA, 2013
15 International Conference Jinkyu Lee, Hyunson Seo, Hong-Goo Kang "Adaptation of HMM dynamic parameters in reverberant environment" in EUSIPCO, 2013
14 International Conference Jae-Mo Yang, Hong-Goo Kang "Adaptive multichannel linear prediction based dereverberation in time-varying room environments" in EUSIPCO, 2013
13 International Conference JeeSok Lee, Frank Soong, Hong-Goo Kang "Source-Filter based Full-band Adaptive Harmonic Model and Its Application to Speech Prosody Modification" in INTERSPEECH, 2013
12 International Conference Young-Sun Joo, Chi-Sang Jung, Hong-Goo Kang "Enhancement of spectral clarity for HMM-based text-to-speech systems" in ICASSP, 2013
11 International Conference Taegyu Lee, Seokjin Lee, Young-cheol Park, Dae Hee Youn "Virtual bass system based on a multiband harmonic generation" in ICCE, 2013
10 International Conference Se-Woon Jeon, Dae Hee Youn, Young-Cheol Park "Blind depth estimation based on primary-to-ambient energy ratio for 3-D acoustic depth rendering" in APSIPA ASC, 2012
9 International Conference Sunwoong Choi, Dong-il Hyun, Young-cheol Park, Seokpil Lee, Dae Hee Youn "Blind Upmixing for Height and Wide Channels Based on an Image Source Method" in 133th Convention of Audio Engineering Society, pp.8752, 2012