Mitsuru Nakai

According to our database, Mitsuru Nakai authored at least 25 papers between 1992 and 2003.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2003

On-line Overlaid-Handwriting Recognition Based on Substroke HMMs.

Hiroshi Shimodaira, Takashi Sudo, Mitsuru Nakai, Shigeki Sagayama

Proceedings of the 7th International Conference on Document Analysis and Recognition (ICDAR 2003), 2003

Generation of Hierarchical Dictionary for Stroke-order Free Kanji Handwriting Recognition Based on Substroke HMM.

Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama

Proceedings of the 7th International Conference on Document Analysis and Recognition (ICDAR 2003), 2003

2002

Pen Pressure Features for Writer-Independent On-Line Handwriting Recognition Based on Substroke HMM.

Mitsuru Nakai, Takashi Sudo, Hiroshi Shimodaira, Shigeki Sagayama

Proceedings of the 16th International Conference on Pattern Recognition, 2002

Context-dependent substroke model for HMM-based on-line handwriting recognition.

Junko Tokuno, Nobuhito Inami, Shigeki Matsuda, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama

Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition, 2002

Jacobian joint adaptation to noise, channel and vocal tract length.

Hiroshi Shimodaira, Nobuyoshi Sakai, Mitsuru Nakai, Shigeki Sagayama

Proceedings of the IEEE International Conference on Acoustics, 2002

Hidden Markov model for automatic transcription of MIDI signals.

Haruto Takeda, Naoki Saito, Tomoshi Otsuki, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama

Proceedings of the IEEE 5th Workshop on Multimedia Signal Processing, 2002

2001

Dynamic Time-Alignment Kernel in Support Vector Machine.

Hiroshi Shimodaira, Ken-ichi Noma, Mitsuru Nakai, Shigeki Sagayama

Proceedings of the Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, 2001

Support vector machine with dynamic time-alignment kernel for speech recognition.

Hiroshi Shimodaira, Ken-ichi Noma, Mitsuru Nakai, Shigeki Sagayama

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Substroke Approach to HMM-Based On-line Kanji Handwriting Recognition.

Mitsuru Nakai, Naoto Akira, Hiroshi Shimodaira, Shigeki Sagayama

Proceedings of the 6th International Conference on Document Analysis and Recognition (ICDAR 2001), 2001

Multiple-regression hidden Markov model.

Katsuhisa Fujinaga, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama

Proceedings of the IEEE International Conference on Acoustics, 2001

2000

Jacobian adaptation of HMM with initial model selection for noisy speech recognition.

Hiroshi Shimodaira, Yutaka Kato, Toshihiko Akae, Mitsuru Nakai, Shigeki Sagayama

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Feature-dependent allophone clustering.

Shigeki Matsuda, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Asynchronous-transition HMM.

Shigeki Matsuda, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama

Proceedings of the IEEE International Conference on Acoustics, 2000

1998

Modified Minimum Classification Error Learning and Its Application to Neural Networks.

Hiroshi Shimodaira, Jun Rokui, Mitsuru Nakai

Proceedings of the Advances in Pattern Recognition, 1998

Improving the generalization performance of the MCE/GPD learning.

Hiroshi Shimodaira, Jun Rokui, Mitsuru Nakai

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

The use of F0 reliability function for prosodic command analysis on F0 contour generation model.

Mitsuru Nakai, Hiroshi Shimodaira

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

1997

Restoration of pitch pattern of speech based on a pitch generation model.

Hiroshi Shimodaira, Mitsuru Nakai, Akihiro Kumata

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

On representation of fundamental frequency of speech for prosody analysis using reliability function.

Mitsuru Nakai, Hiroshi Shimodaira

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Accent Phrase Segmentation by F₀ Clustering Using Superpositional Modelling.

Mitsuru Nakai, Harald Singer, Yoshinori Sagisaka, Hiroshi Shimodaira

Proceedings of the Computing Prosody, 1997

1995

Automatic prosodic segmentation by F₀ clustering using superpositional modeling.

Mitsuru Nakai, Harald Singer, Yoshinori Sagisaka, Hiroshi Shimodaira

Proceedings of the 1995 International Conference on Acoustics, 1995

1994

Accent phrase segmentation by finding n-best sequences of pitch pattern templates.

Mitsuru Nakai, Hiroshi Shimodaira

Proceedings of the 3rd International Conference on Spoken Language Processing, 1994

Prosodic phrase segmentation by pitch pattern clustering.

Hiroshi Shimodaira, Mitsuru Nakai

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

1993

Accent phrase segmentation using transition probabilities between pitch pattern templates.

Hiroshi Shimodaira, Mitsuru Nakai

Proceedings of the Third European Conference on Speech Communication and Technology, 1993

1992

Robust pitch detection by narrow band spectrum analysis.

Hiroshi Shimodaira, Mitsuru Nakai

Proceedings of the Second International Conference on Spoken Language Processing, 1992

A fast VQ codebook design algorithm for a large number of data.

Mitsuru Nakai, Hiroshi Shimodaira, Masayuki Kimura

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992