@techreport{oai:ipsj.ixsq.nii.ac.jp:00216633,
 author = {Detai, Xin and Shinnosuke, Takamichi and Takuma, Okamoto and Hisashi, Kawai and Hiroshi, Saruwatari and Detai, Xin and Shinnosuke, Takamichi and Takuma, Okamoto and Hisashi, Kawai and Hiroshi, Saruwatari},
 issue = {32},
 month = {Feb},
 note = {We investigate the possibility of controlling speaking rate by using the HiFi-GAN neural vocoder. Although traditional time-scale modification (TSM) algorithms have been widely applied in real-world applications, their performance and efficiency are relatively low. Recent work of neural vocoder has shown the possibility of synthesizing speech with high fidelity and efficiency. The proposed method inserts an interpolation layer into the HiFi-GAN to control the speaking rate. A signal resampling method and an image scaling method are implemented in the proposed method to warp the mel-spectrogram or hidden features of the neural vocoder. We also design a Japanese speech corpus to evaluate the proposed speaking rate control method. Experimental results of comprehensive objective and subjective evaluations demonstrate that the proposed method can control speaking rate with higher quality and efficiency than a baseline TSM algorithm. We open-source the corpus and give future directions of speaking rate control by a neural vocoder., We investigate the possibility of controlling speaking rate by using the HiFi-GAN neural vocoder. Although traditional time-scale modification (TSM) algorithms have been widely applied in real-world applications, their performance and efficiency are relatively low. Recent work of neural vocoder has shown the possibility of synthesizing speech with high fidelity and efficiency. The proposed method inserts an interpolation layer into the HiFi-GAN to control the speaking rate. A signal resampling method and an image scaling method are implemented in the proposed method to warp the mel-spectrogram or hidden features of the neural vocoder. We also design a Japanese speech corpus to evaluate the proposed speaking rate control method. Experimental results of comprehensive objective and subjective evaluations demonstrate that the proposed method can control speaking rate with higher quality and efficiency than a baseline TSM algorithm. We open-source the corpus and give future directions of speaking rate control by a neural vocoder.},
 title = {Speaking Rate Control by HiFi-GAN using Feature Interpolation},
 year = {2022}
}