We propose a noise suppression method based on multi-model compositions using particle filtering. In real environments, input speech for speech recognition includes many kinds of noise signals. For such noisy speech, we previously proposed Multi-model Noise Suppression (MM-NS) that uses many kinds of noise models and their compositions obtained from training data. However, since MM-NS only uses the static property of noise models, handling unknown noise distributions is difficult. We introduce a particle filter into MM-NS. The distributions of noise models are used as prior distributions of particle filtering to increase the accuracy of the estimation of noise signals for input data. We evaluated this method using the E-Nightingale task, which contains voice memoranda spoken by nurses during actual work at hospitals. The proposed method outperformed the original MM-NS.

This paper presents robust speech recognition using a noise suppression method based on multi-model compositions and multi-pass search. In real environments, many kinds of noise signals exists, and input speech for speech recognition systems include them. Our task in the E-Nightingale project is speech recognition of voice memoranda spoken by nurses during actual work at hospitals. To obtain good recognized candidates, suppressing many kinds of noise signals at once to find target speech is important. First, before noise suppression, to find speech and noise label sequences, we introduce multi-pass search with acoustic models including many kinds of noise models and their compositions, their n-gram models, and their lexicon. Second, noise suppression based on models is performed using the multiple composite models selected by recognized label sequences with time alignments. We evaluated this approach using the E-Nightingale task, and the proposed method outperformed the conventional method.

We present a practical 3D reconstruction method that guarantees robust visual hull construction in real environments where segmentation errors and occlusion exist. The proposed method consists of foreground extraction and reliability-based shape-from-silhouette, and they are connected by the intra-/inter-silhouette reliabilities. In foreground extraction, all regions are classified into four categories based on their intra-reliabilities. Then the reliability-based shape-from-silhouette technique reconstructs a visual hull by carving a 3D space based on the intra-/inter-silhouette reliabilities. The proposed method provides a reliable visual hull in real environments without much increment of the system complexity compared with conventional systems.

This paper addresses the problem of segmenting audio data recorded with embedded devices for the purpose of intelligent sensing in the context of multi-modal interactions. We propose a real-time method for robust speech detection in natural, noisy environments. It is based on a fusion of high order statistics of the LPC residual and autocorrelation, and adopts an on-line version of Expectation Maximization algorithm for the classification. Experimental evaluations show that the proposed method provides better detection performance under different types of natural noises, working robustly against other voices in the context of multi-speaker interactive situations. As the proposed method is based on features which have a low computational cost, and has a small latency, it is suitable for real-time tracking applications.

We have constructed a sensor network in a real hospital environment to develop a system that prevents medical accidents by monitoring nursing activities. The network has been carefully designed to be dependable for practical purposes even in a network-unready environment with considerations of safety and stability as well as the consistency of the obtained sensor data. This paper describes the design and implementation of our sensor network. Through an experiment of about one week, we confirmed that our design performs well in a practical environment and obtains consistent data among the sensors worn by nurses and installed in the environment. Since a hospital has strict limitations on the use of sensor network equipment, the design described in this paper provides a practical solution for the construction of sensor networks in many indoor applications

No abstract available.