Speech Synthesis Based on Hidden Markov Models von Tokuda, Keiichi, Nankaku, Yoshihiko, Toda, Tomoki, Zen, Heiga, Yamagishi, Junichi, Oura, Keiichiro

Volltext

Statistical Voice Conversion Techniques for Body-Conducted Unvoiced Speech Enhancement von Toda, Tomoki, Nakagiri, Mikihiro, Shikano, Kiyohiro

Volltext

An Investigation of Fundamental Frequency Pattern Prediction for Japanese Electrolaryngeal Speech Enhancement Based on Frame-Wise Phoneme Representations von Eshghi, Mohammad, Toda, Tomoki

Volltext

Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory von Toda, T., Black, A.W., Tokuda, K.

Volltext

A Comparative Study of Self-Supervised Speech Representation Based Voice Conversion von Huang, Wen-Chin, Yang, Shu-Wen, Hayashi, Tomoki, Toda, Tomoki

Volltext

Duration-Controlled LSTM for Polyphonic Sound Event Detection von Hayashi, Tomoki, Watanabe, Shinji, Toda, Tomoki, Hori, Takaaki, Le Roux, Jonathan, Takeda, Kazuya

Volltext

Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model von Toda, Tomoki, Black, Alan W., Tokuda, Keiichi

Volltext

Comparison of real-time multi-speaker neural vocoders on CPUs von Matsubara, Keisuke, Okamoto, Takuma, Takashima, Ryoichi, Takiguchi, Tetsuya, Toda, Tomoki, Kawai, Hisashi

Volltext

Underdetermined Source Separation Based on Generalized Multichannel Variational Autoencoder von Seki, Shogo, Kameoka, Hirokazu, Li, Li, Toda, Tomoki, Takeda, Kazuya

Volltext

A review on subjective and objective evaluation of synthetic speech von Cooper, Erica, Huang, Wen-Chin, Tsao, Yu, Wang, Hsin-Min, Toda, Tomoki, Yamagishi, Junichi

Volltext

Daily Activity Recognition with Large-Scaled Real-Life Recording Datasets Based on Deep Neural Network Using Multi-Modal Signals von HAYASHI, Tomoki, NISHIDA, Masafumi, KITAOKA, Norihide, TODA, Tomoki, TAKEDA, Kazuya

Volltext

High-Fidelity and Pitch-Controllable Neural Vocoder Based on Unified Source-Filter Networks von Yoneyama, Reo, Wu, Yi-Chiao, Toda, Tomoki

Volltext

Environmental sound processing and its applications von Miyazaki, Koichi, Toda, Tomoki, Hayashi, Tomoki, Takeda, Kazuya

Volltext

Anti-Spoofing for Text-Independent Speaker Verification: An Initial Database, Comparison of Countermeasures, and Human Performance von Zhizheng Wu, De Leon, Phillip L., Demiroglu, Cenk, Khodabakhsh, Ali, King, Simon, Zhen-Hua Ling, Saito, Daisuke, Stewart, Bryan, Toda, Tomoki, Wester, Mirjam, Yamagishi, Junichi

Volltext

Fast Neural Speech Waveform Generative Models With Fully-Connected Layer-Based Upsampling von Yamashita, Haruki, Okamoto, Takuma, Takashima, Ryoichi, Ohtani, Yamato, Takiguchi, Tetsuya, Toda, Tomoki, Kawai, Hisashi

Volltext

Postfilters to Modify the Modulation Spectrum for Statistical Parametric Speech Synthesis von Takamichi, Shinnosuke, Toda, Tomoki, Black, Alan W., Neubig, Graham, Sakti, Sakriani, Nakamura, Satoshi

Volltext

Stereophonic Music Separation Based on Non-Negative Tensor Factorization with Cepstral Distance Regularization von SEKI, Shogo, TODA, Tomoki, TAKEDA, Kazuya

Volltext

Non-Parallel Voice Conversion System With WaveNet Vocoder and Collapsed Speech Suppression von Wu, Yi-Chiao, Tobing, Patrick Lumban, Kobayashi, Kazuhiro, Hayashi, Tomoki, Toda, Tomoki

Volltext

Investigation of Japanese PnG BERT Language Model in Text-to-Speech Synthesis for Pitch Accent Language von Yasuda, Yusuke, Toda, Tomoki

Volltext

Full-Band LPCNet: A Real-Time Neural Vocoder for 48 kHz Audio With a CPU von Matsubara, Keisuke, Okamoto, Takuma, Takashima, Ryoichi, Takiguchi, Tetsuya, Toda, Tomoki, Shiga, Yoshinori, Kawai, Hisashi

Volltext