Improved Epoch Extraction From Speech Signals Using Wavelet Synchrosqueezed Transform

Govind, D.; Priya, S. Lakshmi; Akarsh, S.; Gowri, B.

doi:10.1109/ncc.2019.8732259

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, synchrosqueezing can be used as a substitute to empirical mode decomposition techniques [64]. The concept of WSST has been used for epoch extraction from the emotional speech because of its sharpness in instantaneous frequency representation [65]. In addition, synchrosqueezing successfully represents the rapidly varying pitch in emotional speech, which forms the basis of this study.…”

Section: A Wavelet Synchrosqueezed Transformmentioning

confidence: 99%

Emotional Voice Conversion Using a Hybrid Framework With Speaker-Adaptive DNN and Particle-Swarm-Optimized Neural Network

et al. 2020

View full text Add to dashboard Cite

We propose a hybrid network-based learning framework for speaker-adaptive vocal emotion conversion, tested on three different datasets (languages), namely, EmoDB (German), IITKGP (Telugu), and SAVEE (English). The optimized learning model introduced is unique because of its ability to synthesize emotional speech with an acceptable perceptive quality while preserving speaker characteristics. The multilingual model is extremely beneficial in scenarios wherein emotional training data from a specific target speaker are sparsely available. The proposed model uses speaker-normalized mel-generalized cepstral coefficients for spectral training with data adaptation using the seed data from the target speaker. The fundamental frequency (F0) is transformed using a wavelet synchrosqueezed transform prior to mapping to obtain a sharpened time-frequency representation. Moreover, a feedforward artificial neural network, together with particle swarm optimization, was used for F0 training. Additionally, static-intensity modification was also performed for each test utterance. Using the framework, we were able to capture the spectral and pitch contour variabilities of emotional expression better than with other state-of-the-art methods used in this study. Considering the overall performance scores across datasets, an average melcepstral distortion (MCD) of 4.98 and root mean square error (RMSE-F0) of 10.67 were obtained in objective evaluations, and an average comparative mean opinion score (CMOS) of 3.57 and speaker similarity score of 3.70 were obtained for the proposed framework. Particularly, the best MCD of 4.09 (EmoDB-happiness) and RMSE-F0 of 9.00 (EmoDB-anger) were obtained, along with the maximum CMOS of 3.7 and speaker similarity of 4.6, thereby highlighting the effectiveness of the hybrid network model.

show abstract

Section: A Wavelet Synchrosqueezed Transformmentioning

confidence: 99%