Takao Kobayashi focuses on Speech recognition, Hidden Markov model, Speech synthesis, Artificial intelligence and Pattern recognition. His Speech recognition study incorporates themes from Spectral density estimation and Cepstral analysis. His Hidden Markov model study integrates concerns from other disciplines, such as Quality, Probability distribution, State and White noise.
The Speech synthesis study combines topics in areas such as Sentence, Adaptation and Interpolation. His Artificial intelligence research is multidisciplinary, relying on both Algorithm, Adaptive filter, Duration and Natural language processing. His Pattern recognition study combines topics from a wide range of disciplines, such as Estimation theory, Set and Speech processing.
Takao Kobayashi spends much of his time researching Speech recognition, Hidden Markov model, Speech synthesis, Artificial intelligence and Pattern recognition. Takao Kobayashi focuses mostly in the field of Speech recognition, narrowing it down to topics relating to Adaptation and, in certain cases, Voice analysis. His Hidden Markov model study also includes
The concepts of his Speech synthesis study are interwoven with issues in Decision tree, Intelligibility and Voice activity detection, Speech processing. His Artificial intelligence research incorporates themes from Linear regression and Natural language processing. Takao Kobayashi interconnects Estimation theory, Algorithm and Parametric statistics in the investigation of issues within Pattern recognition.
His primary scientific interests are in Speech recognition, Speech synthesis, Hidden Markov model, Artificial intelligence and Pattern recognition. His studies deal with areas such as Kriging and Phrase as well as Speech recognition. His work carried out in the field of Speech synthesis brings together such families of science as Tone, Algorithm, Parametric statistics and Speech processing.
His Hidden Markov model research is multidisciplinary, incorporating perspectives in Fundamental frequency, Quantization, Adaptation, Rule-based machine translation and Prosody. His work focuses on many connections between Artificial intelligence and other disciplines, such as Natural language processing, that overlap with his field of interest in Speaker diarisation. His Pattern recognition research incorporates elements of Regression analysis, Feature and Kernel.
Takao Kobayashi mostly deals with Hidden Markov model, Speech synthesis, Speech recognition, Artificial intelligence and Pattern recognition. His work deals with themes such as Fundamental frequency, Quantization and Speech processing, which intersect with Hidden Markov model. His biological study deals with issues like Parametric statistics, which deal with fields such as Kernel and Overfitting.
Takao Kobayashi integrates many fields, such as Speech recognition and Emotional expression, in his works. His Phrase and Speaker recognition study in the realm of Artificial intelligence interacts with subjects such as Sequence labeling. His Pattern recognition research includes themes of Frame, Feature, Algorithm and Regression analysis.
This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.
Speech parameter generation algorithms for HMM-based speech synthesis
K. Tokuda;T. Yoshimura;T. Masuko;T. Kobayashi.
international conference on acoustics, speech, and signal processing (2000)
Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis
Takayoshi Yoshimura;Keiichi Tokuda;Takashi Masuko;Takao Kobayashi.
conference of the international speech communication association (1999)
An adaptive algorithm for mel-cepstral analysis of speech
T. Fukada;K. Tokuda;T. Kobayashi;S. Imai.
international conference on acoustics, speech, and signal processing (1992)
Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation Algorithm
J. Yamagishi;T. Kobayashi;Y. Nakano;K. Ogata.
IEEE Transactions on Audio, Speech, and Language Processing (2009)
Hidden Markov models based on multi-space probability distribution for pitch pattern modeling
K. Tokuda;T. Masuko;N. Miyazaki;T. Kobayashi.
international conference on acoustics speech and signal processing (1999)
Speech parameter generation from HMM using dynamic features
K. Tokuda;T. Kobayashi;S. Imai.
international conference on acoustics, speech, and signal processing (1995)
Multi-Space Probability Distribution HMM
Keiichi Tokuda;Takashi Masuko;Noboru Miyazaki;Takao Kobayashi.
IEICE Transactions on Information and Systems (2002)
Mel-generalized cepstral analysis - a unified approach to speech spectral estimation.
Keiichi Tokuda;Takao Kobayashi;Takashi Masuko;Satoshi Imai.
conference of the international speech communication association (1994)
Speech synthesis using HMMs with dynamic features
T. Masuko;K. Tokuda;T. Kobayashi;S. Imai.
international conference on acoustics speech and signal processing (1996)
Average-Voice-Based Speech Synthesis Using HSMM-Based Speaker Adaptation and Adaptive Training
Junichi Yamagishi;Takao Kobayashi.
The IEICE transactions on information and systems (2007)
If you think any of the details on this page are incorrect, let us know.
We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below: