Satoru Hayamizu

Research output

Research output per year 1982 2021

• 723 Citations
• 12 h-Index
• 45 Conference contribution
• 41 Article
• 8 Paper
• 7 Conference article

Research output per year

Research output per year

Search results

• 2021

  Multi-angle lipreading with angle classification-based feature extraction and its application to audio-visual speech recognition

  Isobe, S., Tamura, S., Hayamizu, S., Gotoh, Y. & Nose, M., 2021 Jul, In: Future Internet. 13, 7, 182.

  Research output: Contribution to journal › Article › peer-review

  Open Access

  • Audiovisual 100%
  • Speech recognition 81%
  • Feature extraction 66%
  • Deep learning 5%
  • Fusion reactions 5%
• 2016

  Investigation of DNN-based audio-visual speech recognition

  Tamura, S., Ninomiya, H., Kitaoka, N., Osuga, S., Iribe, Y., Takeda, K. & Hayamizu, S., 2016 Oct, In: IEICE Transactions on Information and Systems. E99D, 10, p. 2444-2451 8 p.

  Research output: Contribution to journal › Article › peer-review

  Open Access

  • Audiovisual 100%
  • Deep neural networks 84%
  • Speech recognition 81%
  • Bottles 26%
  • Hidden Markov models 10%
  3 Citations (Scopus)
• 2014

  Multistream sparse representation features for noise robust audio-visual speech recognition

  Shen, P., Tamura, S. & Hayamizu, S., 2014, In: Acoustical Science and Technology. 35, 1, p. 17-27 11 p.

  Research output: Contribution to journal › Article › peer-review

  Open Access

  • speech recognition 100%
  • noise reduction 67%
  • fusion 38%
  4 Citations (Scopus)
• 2013

  Probabilistic expression of Polynomial Semantic Indexing and its application for classification

  Minoura, K., Tamura, S. & Hayamizu, S., 2013, In: Pattern Recognition Letters. 34, 13, p. 1485-1489 5 p.

  Research output: Contribution to journal › Article › peer-review

  • Polynomials 100%
  • Semantics 88%
  • Classifiers 52%
  • Feature extraction 14%
  • Experiments 13%
• 2012

  Visual analysis of health checkup data using multidimensional scaling

  Yamamoto, K., Tamura, S., Hayamizu, S. & Kinosada, Y., 2012 Jan, In: Journal of Advanced Computational Intelligence and Intelligent Informatics. 16, 1, p. 26-32 7 p.

  Research output: Contribution to journal › Article › peer-review

  • Health 100%
  • Visualization 9%
  • Display devices 9%
  • Inspection 9%
  1 Citation (Scopus)
• 2003

  Gesture recognition using HLAC features of PARCOR images

  Kurita, T. & Hayamizu, S., 2003 Apr, In: IEICE Transactions on Information and Systems. E86-D, 4, p. 719-726 8 p.

  Research output: Contribution to journal › Article › peer-review

  • Gesture recognition 100%
  • Autocorrelation 89%
  • Pixels 42%
  • Invariance 30%
  • Hidden Markov models 28%
  7 Citations (Scopus)
• 2002

  Speech Completion: Introducing New Modality into Speech Input Interface

  Goto, M., Itou, K., Akiba, T. & Hayamizu, S., 2002 Jan, In: Computer Software. 19, 4, p. 254-265 12 p.

  Research output: Contribution to journal › Article › peer-review
• 2001

  Jijo 2: An office robot that communicates and learns

  Asoh, H., Motomura, Y., Asano, F., Hara, I., Hayamizu, S., Itou, K., Kurita, T., Matsui, T., Vlassis, N., Bunschoten, R. & Kröse, B., 2001 Sep, In: IEEE Intelligent Systems and Their Applications. 16, 5, p. 46-54 9 p.

  Research output: Contribution to journal › Article › peer-review

  • Robots 100%
  • Microphones 81%
  • Intelligent systems 80%
  • Testbeds 75%
  • Speech recognition 73%
  87 Citations (Scopus)

• Jijo-2: An Office Robot That Communicates and Learns

  Asoh, H., Motomura, Y., Asano, F., Hara, I., Hayamizu, S., Itou, K., Kurita, T., Matsui, T., Vlassis, N., Bunschoten, R. & Kröse, B., 2001, In: IEEE Intelligent Systems. 16, 5, p. 46-55 10 p.

  Research output: Contribution to journal › Article › peer-review
  9 Citations (Scopus)
• 2000

  Interactive learning and management of visual information via human-like software robot

  Hasegawa, O., Sakaue, K. & Hayamizu, S., 2000, New Generation Computing, 18, 2, p. 103-116 14 p.

  Research output: Contribution to specialist publication › Article

  • Robot 100%
  • Vision 83%
  • Learning 74%
  • Software 73%
  • Human 73%
  1 Citation (Scopus)

• Multimodal interaction system that integrates speech and visual information

  Hayamizu, S., Hasegawa, O., Itou, K., Yoshimura, T., Akiba, T., Asoh, H., Akaho, S., Kurita, T. & Sakaue, K., 2000, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 64, 4-5, p. 37-44 8 p.

  Research output: Contribution to journal › Article › peer-review

  • speech recognition 100%
  • learning 71%
  • Speech recognition 61%
  • phonetics 48%
  • communicating 45%

• Speech enhancement based on the subspace method

  Asano, F., Hayamizu, S., Yamada, T. & Nakamura, S., 2000 Sep, In: IEEE Transactions on Speech and Audio Processing. 8, 5, p. 497-507 11 p.

  Research output: Contribution to journal › Article › peer-review

  • Speech enhancement 100%
  • Microphones 84%
  • Signal processing 65%
  • eigenvalues 51%
  • augmentation 49%
  93 Citations (Scopus)
• 1999

  Japanese spontaneous speech corpus collected using automatically inferencing Wizard of Oz system

  Itou, K., Akiba, T., Hasegawa, O., Hayamizu, S. & Tanaka, K., 1999, In: Journal of the Acoustical Society of Japan (E) (English translation of Nippon Onkyo Gakkaishi). 20, 3, p. 207-214 8 p.

  Research output: Contribution to journal › Article › peer-review

  Open Access

  • interruption 100%
  • semantics 53%
  • recovery 33%
  • interactions 16%
  4 Citations (Scopus)
• 1997

  Speech enhancement using array signal processing based on the coherent-subspace method

  Asano, F. & Hayamizu, S., 1997, In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. E80-A, 11, p. 2276-2285 10 p.

  Research output: Contribution to journal › Article › peer-review

  • Speech Enhancement 100%
  • Array Signal Processing 98%
  • Subspace Methods 70%
  • Speech enhancement 65%
  • Microphones 55%
  5 Citations (Scopus)
• 1995

  Detection of unknown words in large vocabulary speech recognition

  Hayamizu, S., Itou, K. & Tanaka, K., 1995, In: Journal of the Acoustical Society of Japan (E) (English translation of Nippon Onkyo Gakkaishi). 16, 3, p. 165-171 7 p.

  Research output: Contribution to journal › Article › peer-review

  Open Access

  • speech recognition 100%
  • dictionaries 23%
  • word processing 15%
  • entry 8%
  • tendencies 7%
  2 Citations (Scopus)
• 1993

  Design and creation of speech and text corpora of dialogue

  Hayamizu, S., Itahashi, S., Kobayashi, T. & Takezawa, T., 1993 Jan 1, In: IEICE Transactions on Information and Systems. E76-D, 1, p. 17-22 6 p.

  Research output: Contribution to journal › Article › peer-review

  • Transcription 100%
  • Syntactics 87%
  • Semantics 58%
  8 Citations (Scopus)

• Prediction of protein secondary structure by the hidden Markov model

  Asai, K., Hayamizu, S. & Handa, K., 1993 Apr, In: Bioinformatics. 9, 2, p. 141-146 6 p.

  Research output: Contribution to journal › Article › peer-review

  • Secondary Protein Structure 100%
  • Secondary Structure 96%
  • Protein Structure 95%
  • Protein Secondary Structure 89%
  • Amino acids 80%
  111 Citations (Scopus)

• Speech database and acoustic-phonetic knowledge base for speech recognition

  Tanaka, K. & Hayamizu, S., 1993, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 57, 2, p. 48-62 15 p.

  Research output: Contribution to journal › Article › peer-review

  • speech recognition 100%
  • phonetics 97%
  • Speech analysis 77%
  • Speech recognition 61%
  • Acoustics 53%

• System design, data collection and evaluation of a speech dialogue system

  Itou, K., Hayamizu, S., Tanaka, K. & Tanaka, H., 1993 Jan, In: IEICE Transactions on Information and Systems. E76-D, 1, p. 121-127 7 p.

  Research output: Contribution to journal › Article › peer-review

  • Systems analysis 100%
  • Statistics 16%
  8 Citations (Scopus)
• 1990

  CVC-based network representation of phoneme sequences with applications to spoken word recognition

  Tanaka, K., Hayamizu, S. & Ohta, K., 1990, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 54, 7, p. 56-62 7 p.

  Research output: Contribution to journal › Article › peer-review

  • phonemes 100%
  • Speech analysis 75%
  • Acoustics 52%
  • phonetics 47%
  • Speech recognition 30%

• Hierarchical representation of speech in symbolic domain and fine phonetic labeling

  Tanaka, K., Hayamizu, S. & Ohta, K., 1990, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 54, 7, p. 13-19 7 p.

  Research output: Contribution to journal › Article › peer-review

  • phonetics 100%
  • Speech analysis 79%
  • marking 69%
  • Labeling 66%
  • Acoustics 55%

• Phonetic network representation of phoneme sequences based on CVC-unit concatenation

  Tanaka, K., Hayamizu, S. & Ohta, K., 1990, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 54, 7, p. 38-45 8 p.

  Research output: Contribution to journal › Article › peer-review

  • phonemes 100%
  • phonetics 94%
  • Speech analysis 75%
  • arcs 26%
  • Acoustics 26%

• Word recognition system using network representation of acoustic phonetic segments

  Hayamizu, S., Tanaka, K. & Ohta, K., 1990, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 54, 7, p. 1-7 7 p.

  Research output: Contribution to journal › Article › peer-review

  • phonetics 100%
  • Speech analysis 79%
  • Acoustics 55%
  • acoustics 39%
  • cepstra 33%
• 1988

  AUTOMATIC LABELING OF KNOWN SPEECH SAMPLES USING A RULE-BASED NETWORK REPRESENTATION AND SEGMENTATION TECHNIQUE.

  Tanaka, K., Hayamizu, S. & Ohta, K., 1988, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 52, 3, p. 30-37 8 p.

  Research output: Contribution to journal › Article › peer-review

  • phonetics 100%
  • Speech analysis 79%
  • marking 69%
  • Labeling 66%
  • sentences 62%

• ON THE DISTANCE MEASURES USING DYNAMIC FEATURES OF SPEECH PARAMETERS.

  Hayamizu, S., Tanaka, K. & Ohta, K., 1988, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 52, 3, p. 75-81 7 p.

  Research output: Contribution to journal › Article › peer-review

  • phonetics 100%
  • Speech analysis 99%
  • vowels 67%
  • Acoustics 52%
  • data bases 42%

• PHONETIC LABEL (APSEG) SEQUENCE SEARCH SYSTEM AND ACOUSTIC-PHONETIC VARIATION CLUSTERING BASED ON A NETWORK REPRESENTATION.

  Tanaka, K., Hayamizu, S. & Ohta, K., 1988, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 52, 3, p. 68-74 7 p.

  Research output: Contribution to journal › Article › peer-review

  • phonetics 100%
  • Speech analysis 79%
  • Labels 57%
  • Acoustics 55%
  • phonemes 52%

• SEMIAUTOMATIC LABELING FOR CONSTRUCTING A PHONEME DATA BASE SYSTEM.

  Tanaka, K., Hayamizu, S. & Ohta, K., 1988, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 52, 3, p. 1-6 6 p.

  Research output: Contribution to journal › Article › peer-review

  • phonemes 100%
  • phonetics 94%
  • data bases 79%
  • Speech analysis 75%
  • marking 66%

• SOME FEATURES OF ACOUSTIC-PHONETIC SEGMENTS OF VOICELESS PLOSIVES AND THEIR RELATION TO SPEECH CONTEXT.

  Hayamizu, S., Tanaka, K. & Ohta, K., 1988, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 52, 3, p. 38-42 5 p.

  Research output: Contribution to journal › Article › peer-review

  • phonetics 100%
  • Speech analysis 79%
  • syllables 66%
  • Acoustics 55%
  • acoustics 39%

• SOME FEATURES OF VOICELESS PLOSIVES IN PHONETICALLY BALANCED WORD SETS.

  Hayamizu, S., Tanaka, K. & Ohta, K., 1988, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 52, 3, p. 12-16 5 p.

  Research output: Contribution to journal › Article › peer-review

  • Speech analysis 100%
  • phonetics 94%
  • Acoustics 34%
  • dictionaries 30%
  • Glossaries 27%
• 1986

  DEMIPHONEMIC REPRESENTATION OF SPEECH AND SEMIAUTOMATIC LABELING SYSTEM.

  Tanaka, K., Hayamizu, S. & Ohta, K., 1986, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 50, 2-3, p. 246-251 6 p.

  Research output: Contribution to journal › Article › peer-review

  • sentences 100%
  • marking 74%
  • Labeling 70%
  • phonetics 53%
  • Speech analysis 42%

• FEATURE EXPRESSION FOR TIME PATTERN OF SPECTRAL ENVELOPES BY QUADRATIC SURFACE APPROXIMATION.

  Hayamizu, S., 1986, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 50, 2-3, p. 227-231 5 p.

  Research output: Contribution to journal › Article › peer-review

  • parabolic bodies 100%
  • envelopes 63%
  • approximation 38%
  • coefficients 19%

• RELATION BETWEEN THE DETERIORATION OF THE RECOGNITION RATE IN CONTINUOUS WORDS RECOGNITION AND THE SPECTRAL MATCHING MEASURES.

  Hayamizu, S. & Oka, R. I., 1986, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 50, 2-3, p. 197-200 4 p.

  Research output: Contribution to journal › Article › peer-review

  • deterioration 100%
  • Deterioration 85%
  • likelihood ratio 34%
  • intervals 17%

• SPEAKER-INDEPENDENT CONNECTED WORDS RECOGNITION USING VECTOR QUANTIZATION OF THE TIME-SPACE PATTERN.

  Hayamizu, S. & Oka, R. I., 1986, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 50, 2-3, p. 160-163 4 p.

  Research output: Contribution to journal › Article › peer-review

  • vector quantization 100%
  • Vector quantization 65%
  • phonemes 61%
  • matrices 32%
  • dynamic programming 31%

• TRIAL OF SENTENCE RECOGNITION OF CONTINUOUS SPEECH USING VECTOR CONTINUOUS DYNAMIC PROGRAMMING.

  Oka, R. I. & Hayamizu, S., 1986, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 50, 2-3, p. 164-167 4 p.

  Research output: Contribution to journal › Article › peer-review

  • dynamic programming 100%
  • sentences 87%
  • Dynamic programming 61%
• 1985

  GENERATION OF VCV/CVC BALANCED WORD SETS FOR SPEECH DATA BASE.

  Hayamizu, S., Tanaka, K., Yokoyama, S. & Ohta, K., 1985, In: Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory. 49, 10, p. 803-834 32 p.

  Research output: Contribution to journal › Article › peer-review

  • data bases 100%
  • Glossaries 78%
  • Speech analysis 47%
  • Entropy 34%
  • dictionaries 28%
  14 Citations (Scopus)
• 1984

  COLLECTING AND EDITING SYSTEM OF SPEECH DATA FOR RESEARCH.

  Hayamizu, S., Mikuni, I., Tanaka, K., Ohmura, H. & Itahashi, S., 1984, In: Bulletin of the Electrotechnical Laboratory, Tokyo. 48, 1-2, p. 98-101 4 p.

  Research output: Contribution to journal › Article › peer-review

  • Labeling 100%
  • Sampling 71%

• COMPARISON OF THE PARAMETERS UTILIZED IN RECOGNIZING CONTINUOUS SPEECH BY USING CONTINUOUS DYNAMIC PROGRAMMING.

  Hayamizu, S. & Oka, R. I., 1984, In: Bulletin of the Electrotechnical Laboratory, Tokyo. 48, 1-2, p. 90-93 4 p.

  Research output: Contribution to journal › Article › peer-review

  • Dynamic programming 100%
  • Field effect transistors 54%
  • Experiments 18%

• EXPERIMENTAL STUDIES ON THE CONNECTED-WORDS RECOGNITION USING CONTINUOUS DYNAMIC PROGRAMMING.

  Hayamizu, S. & Oka, R. I., 1984 Jul, In: Systems, computers, controls. 15, 4, p. 80-88 9 p.

  Research output: Contribution to journal › Article › peer-review

  • Dynamic programming 100%
  • Experiments 24%

• METHODS FOR RECOGNIZING CONTINUOUS SPEECH BY USING CONTINUOUS DYNAMIC PROGRAMMING, AND THEIR APPLICATION.

  Hayamizu, S. & Oka, R. I., 1984, In: Bulletin of the Electrotechnical Laboratory, Tokyo. 48, 1-2, p. 86-89 4 p.

  Research output: Contribution to journal › Article › peer-review

  • Syntactics 100%
  • Dynamic programming 94%
  • Continuous speech recognition 65%
  • Experiments 17%

• ON THE COMPOSITION OF A SPEECH DATABASE - AN EXAMINATION OF SAMPLING RATE CONVERSION METHODS.

  Itahashi, S., Ohmura, H., Mikuni, I. & Hayamizu, S., 1984, In: Bulletin of the Electrotechnical Laboratory, Tokyo. 48, 1-2, p. 34-37 4 p.

  Research output: Contribution to journal › Article › peer-review

  • Sampling 100%
  • Chemical analysis 92%
• 1982

  Detection and Discrimination of Adventitious Frames of Respiratory Sounds*

  Hayamizu, S., Konno, K. & Yoshino, K., 1982, In: Japanese journal of medical electronics and biological engineering. 20, 5, p. 327-330 4 p.

  Research output: Contribution to journal › Article › peer-review

  • Acoustic waves 100%
  • Autocorrelation 22%
  • Tapes 21%
  • Experiments 7%