Research output per year
Research output per year
Personal profile
Research Interests
Trainable lifelike conversational agents, Acoustic models for automatic speech recognition, Handwriting recognition.
Qualifications
1988, PhD, Tohoku University.
Biography
I joined the School of Informatics at the University of Edinburgh in September 2004. Previously I have worked at Japan Advanced Institute of Science and Technology (JAIST). From 1995 to 1996, I was a visiting researcher at CSTR, The University of Edinburgh. I was a visitor at ATR Interpreting Telephony Research Laboratories in the summer of 1990. From 1988 to 1991 I was a Research Associate of Faculty of Information Science, Tohoku University. I received my Ph.D. in 1988 from Tohoku University.
Fingerprint
Dive into the research topics where Hiroshi Shimodaira is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
-
Speech-driven head motion generation from waveforms
Lu, J. & Shimodaira, H., Apr 2024, In: Speech Communication. 159, p. 1-13 13 p., 103056.Research output: Contribution to journal › Article › peer-review
Open AccessFile -
Double-DCCCAE: Estimation of body gestures from speech waveform
Lu, J., Liu, T., Xu, S. & Shimodaira, H., 13 May 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, p. 900-904 5 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
Prediction of Head Motion from Speech Waveforms with a Canonical-Correlation-Constrained Autoencoder
Lu, J. & Shimodaira, H., 25 Oct 2020, INTERSPEECH 2020. International Speech Communication Association, p. 1301-1305 5 p. (Interspeech ).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
Direct F0 Estimation with Neural-Network-based Regression
Xu, S. & Shimodaira, H., 19 Sept 2019, Proc. Interspeech 2019. International Speech Communication Association, p. 1995-1999 5 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile -
Bidirectional LSTM Networks Employing Stacked Bottleneck Features for Expressive Speech-Driven Head Motion Synthesis
Haag, K. & Shimodaira, H., 19 Oct 2016, Intelligent Virtual Agents: 16th International Conference, IVA 2016, Los Angeles, CA, USA, September 20--23, 2016, Proceedings. Traum, D., Swartout, W., Khooshabeh, P., Kopp, S., Scherer, S. & Leuski, A. (eds.). Cham: Springer, p. 198-207 10 p. (Lecture Notes in Computer Science; vol. 10011).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open AccessFile