Tatsuhiko Saito

  • Citations Per Year
Learn More
We propose a statistical framework for high-level feature extraction that uses SIFT Gaussian mixture models (GMMs) and audio models. SIFT features were extracted from all the image frames and modeled by a GMM. In addition, we used mel-frequency cepstral coefficients and ergodic hidden Markov models to detect high-level features in audio streams. The best(More)
We newly developed a 3 × 3 integrated optical packet and circuit switch-node. Optical buffers and burst-mode erbium-doped fiber amplifiers with the gain flatness are installed in the 3 × 3 switch-node. The optical buffer can prevent packet collisions and decrease packet loss. We constructed a multi-ring optical packet and circuit integrated network testbed(More)
We propose a statistical framework for high-level feature (HLF) extraction, which employs scale-invariant feature transform Gaussian mixture models (SIFT GMMs), acoustic features, and maximal figure-of-merit (MFoM). The MeanInfAP of our best run was 0.1679. Our team placed 11th after all of the runs and 4th among all participating teams. Notably, the InfAPs(More)
[1] High-frequency S wave seismogram envelopes are broadened with increasing travel distance due to diffraction and scattering. The basic mechanism of the broadening has been studied on the basis of the scattering theory with the parabolic approximation for the scalar wave equation in random media. However, conventional models are not realistic enough since(More)
S U M M A R Y The scattering coefficient is one of the most fundamental parameters by which to quantify the scattering intensity for waves as a function of scattering angle and wave frequency. This study presents a derivation of the scattering coefficient for linear long-wave tsunami equations in randomly fluctuating sea-bottom topography using the(More)
This paper describes a performance prediction technique of a speech recognition system using a small amount of target speakers’ data. In the conventional HMM-based technique, a speakerdependent model was used and thus a considerable amount of training data was needed. To reduce the amount of training data, we introduce an average voice model as a prior(More)
To estimate the seismic velocity changes at different depths associated with a large earthquake, we apply passive image interferometry to two types of seismograms: KiK-net vertical pairs of earthquake records and Hi-net continuous borehole data. We compute the surface/borehole deconvolution waveform (DCW) of seismograms recorded by a KiK-net station and the(More)
AHP (Analytic Hierarchy Process) has been widely used in a field of decision making. One extension, an absolute measurement method AHP is effective for bad consistency in case containing too many alternatives and can avoid the rank reversal problem. However using the absolute measurement method, the results often lose reliability because the comparison(More)
  • 1