Satoshi Imai

1983–1994

A researcher in the Science corpus: 4 papers; trusts 0 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Who trusts Satoshi Imai overall

1. Heiga Zen
2. Keiichi Tokuda
3. Kishore Prahallad
4. Xu Tan
5. Junichi Yamagishi
6. Alan W. Black
7. Seyed Hamidreza Mohammadi
8. Yoshihiko Nankaku
9. Yi Luo
10. Yedid Hoshen

Papers from Satoshi Imai's perspective

Ordered by how strongly the researchers Satoshi Imai trusts endorse each paper. Same corpus, a different order for every researcher.

1. Mel Log Spectrum Approximation (MLSA) filter for speech synthesis
2. A statistical method for estimation of speech spectral density and formant frequencies
3. Cepstral analysis synthesis on the mel frequency scale
4. Fundamentals of speech recognition
5. Robust text-independent speaker identification using Gaussian mixture speaker models
6. Dropout: a simple way to prevent neural networks from overfitting
7. Auto-Encoding Variational Bayes (International Conference on Learning Representations)
8. A Fast Learning Algorithm for Deep Belief Nets
9. A tutorial on hidden Markov models and selected applications in speech recognition
10. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper

Their papers

• Mel-generalized cepstral analysis - a unified approach to speech spectral estimation (1994)
• An adaptive algorithm for mel-cepstral analysis of speech (1992)
• Mel Log Spectrum Approximation (MLSA) filter for speech synthesis (1983)
• Cepstral analysis synthesis on the mel frequency scale (1983)