Takashi Sumiyoshi

Learn More
This paper presents our recent attempt to make a super-large scale spoken-term detection system, which can detect any keyword uttered in a 2,000-hour speech database within a few seconds. There are three problems to achieve such a system. The system must be able to detect out-of-vocabulary (OOV) terms (OOV problem). The system has to respond to the user(More)
In this paper, we propose a unified system that incorporates speech source separation and automatic speech recognition for various noise environments. There are three features in the proposed system. The first feature of the proposed method is the LGM (local Gaussian modeling) based source separation with the efficient permutation alignment method that(More)
Radon ((222)Rn) and carbon dioxide were monitored simultaneously in soil air under a cool-temperate deciduous stand on the campus of Hokkaido University, Sapporo, Japan. Both (222)Rn and CO(2) concentrations in soil air varied with atmospheric (soil) temperature in three seasons, except for winter when the temperature in soil air remained constant at 2-3(More)
Continuous (222)Rn monitoring in soil gas since November 22, 2004 has revealed variability in activity concentration with time in the semi-natural woods on the campus of Hokkaido University in Sapporo, Japan. Among various factors affecting soil radon levels and variability, temperature was found to be dominant during three seasons when activity(More)
We propose a new methodology of sound source localization named SPIRE (stepwise phase difference restoration) that is able to localize sources even if they are neighboring in a reverberant environment. Localizing sound sources in reverberant environments is difficult, because the variance of the direction of an estimated sound source increases in(More)
We introduce a new class of speech processing, called Intentional Voice Command Detection (IVCD). It is necessary to reject not only noises but also unintended voices to achieve completely hands-free speech interface. Conventional VAD framework is not sufficient for such purpose, and we discuss how we should define IVCD and how we can realize it. We(More)
In this paper, direction of arrival (DOA) estimation methods (both azimuth and elevation) based on sparseness of human speech, “modified delay-and-sum beamformer based on sparseness (MDSBF)” and “stepwise phase difference restoration (SPIRE)”, are introduced for human symbiotic robots. MDSBF can achieve good DOA estimation, whose(More)
In this paper, we propose a novel multichannel noise reduction method for a mechanical noise with a time-variant impulse response. The mechanical noise source location moves depending on the status of the actuator. In accordance with the move of the noise-source location, a most suitable multichannel beamformer is selected separately at each time-frequency(More)
Red-crowned (or Japanese) cranes Grus japonensis are native to eastern Hokkaido, Japan--the island population, and mainland Asia--the continental population that migrates from breeding grounds along the Amur River Basin to winter in east China and the Korean Peninsula. The island population was reduced to about 50-60 birds in early part of the 20th century.(More)
Depth profiles potassium and its isotope ratio (K/K) were investigated in several forest soils from different geological and climatic backgrounds. The ratio was found not to be constant (0.0117 %) but varied appreciably from 0.0085 to 0.0167 % among different soils. Possible factors affecting variability of K/K values were considered by a multivariate(More)