Nobuyuki Nishizawa

Publication Activity (10 Years)

Years Active: 2000-2019
Publications (10 Years): 8

Top Topics

Speech Synthesis

Educational Tool

Inter Annotator Agreement

Prosodic Features

Top Venues

Publications

Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
Training Multi-Speaker Neural Text-to-Speech Systems Using Speaker-Imbalanced Speech Corpora. INTERSPEECH (2019)
Nobuyuki Nishizawa, Tomohiro Obara, Gen Hattori
Evaluation of Block-Wise Parameter Generation for Statistical Parametric Speech Synthesis. SSW (2019)
Nobuyuki Nishizawa, Tomohiro Obara, Gen Hattori
Development and Evaluation of Japanese Text-to-speech Middleware for 32-Bit Microcontrollers. ICASSP (2019)
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora. CoRR (2019)
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
Investigating accuracy of pitch-accent annotations in neural network-based speech synthesis and denoising effects. CoRR (2018)
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
Investigating Accuracy of Pitch-accent Annotations in Neural Network-based Speech Synthesis and Denoising Effects. INTERSPEECH (2018)
Nobuyuki Nishizawa, Tomonori Yazaki
Wide Passband Design for Cosine-Modulated Filter Banks in Sinusoidal Speech Synthesis. SSW (2016)
Nobuaki Minematsu, Daisuke Saito, Nobuyuki Nishizawa
Prosodic Reading Tutor of Japanese, Suzuki-kun: The first and only educational tool to teach the formal Japanese. SSW (2016)
Nobuyuki Nishizawa, Tsuneo Kato
Speech synthesis using subband-coded multiband source components and sinusoids. ICASSP (2013)
Nobuyuki Nishizawa, Tsuneo Kato
Speech synthesis using a maximally decimated pseudo QMF bank for embedded devices. SSW (2013)
Nobuyuki Nishizawa, Tsuneo Kato
Speech synthesis using a non-maximally decimated filter bank for embedded systems. INTERSPEECH (2012)
Tsuneo Kato, Makoto Yamada, Nobuyuki Nishizawa, Keiichiro Oura, Keiichi Tokuda
Large-Scale Subjective Evaluations of Speech Rate Control Methods for HMM-Based Speech Synthesizers. INTERSPEECH (2011)
Tsuneo Kato, Kengo Fujita, Nobuyuki Nishizawa
Efficient Beam Pruning for Speech Recognition with a Reward Considering the Potential to Reach Various Words on a Lexical Tree. IEICE Trans. Inf. Syst. (6) (2011)
Nobuyuki Nishizawa, Tsuneo Kato
Accurate parameter generation using fixed-point arithmetic for embedded HMM-based speech synthesizers. ICASSP (2011)
Tsuneo Kato, Kengo Fujita, Nobuyuki Nishizawa
An efficient beam pruning with a reward considering the potential to reach various words on a lexical tree. ICASSP (2010)
Nobuyuki Nishizawa, Tsuneo Kato
Substitution of state distributions to reproduce natural prosody on HMM-based speech synthesizers. SSW (2010)
Nobuyuki Nishizawa, Hisashi Kawai
Unit database pruning based on the cost degradation criterion for concatenative speech synthesis. ICASSP (2008)
Nobuyuki Nishizawa, Hisashi Kawai
A preselection method based on cost degradation from the optimal sequence for concatenative speech synthesis. INTERSPEECH (2007)
Nobuyuki Nishizawa, Hisashi Kawai
A Short-Latency Unit Selection Method with Redundant Search for Concatenative Speech Synthesis. ICASSP (1) (2006)
Toshio Hirai, Hisashi Kawai, Minoru Tsuzaki, Nobuyuki Nishizawa
Analysis of major factors of naturalness degradation in concatenative synthesis. INTERSPEECH (2005)
Nobuyuki Nishizawa, Hisashi Kawai
Using a depth-restricted search to reduce delays in unit selection. INTERSPEECH (2004)
Nobuyuki Nishizawa, Hisashi Kawai
Scaling of waveform segments along the time axis for concatenative speech synthesis. ICASSP (1) (2004)
Nobuyuki Nishizawa, Keikichi Hirose, Nobuaki Minematsu
Estimation of resonant characteristics based on AR-HMM modeling and spectral envelope conversion of vowel sounds. INTERSPEECH (2003)
Nobuyuki Nishizawa, Keikichi Hirose, Nobuaki Minematsu
Separation of voiced source characteristics and vocal tract transfer function characteristics for speech sounds by iterative analysis based on AR-HMM model. INTERSPEECH (2002)
Nobuyuki Nishizawa, Nobuaki Minematsu, Keikichi Hirose
Development of a formant-based analysis-synthesis system and generation of high quality liquid sounds of Japanese. INTERSPEECH (2000)