Takayuki Arakawa

Model-Basedwiener Filter for Noise Robust Speech Recognition

In this paper, we propose a new approach for noise robust speech recognition, which integrates signal-processing-based spectral enhancement and statistical-model-based compensation. The proposed method, model-based Wiener filter (MBW), takes three steps to estimate clean speech signals from noisy speech signals, which are corrupted by various kinds of additive background noise. The first step is the well-known spectral subtraction (SS). Since the SS averagely subtracts noise components, the estimated speech signals often include distortion. In the second step, the distortion caused by SS is reduced using the minimum mean square error estimation for a Gaussian mixture model representing pre-trained knowledge of speech. In the final step, the Wiener filtering is performed with the decision-directed method. Experiments are conducted using the Aurora2-J (Japanese digit string) database. The results show that the proposed method performs as well as the ETSI advanced front-end in average and the variation range of the recognition accuracy according to the kind of noise is about one third, which demonstrates the robustness of the proposed method

Speaker tracking with spherical microphone arrays

In prior work, we investigated the application of a spherical microphone array to a distant speech recognition task. In that work, the relative positions of a fixed loud speaker and the spherical array required for beamforming were measured with an optical tracking device. In the present work, we investigate how these relative positions can be determined automatically for real, human speakers based solely on acoustic evidence. We first derive an expression for the complex pressure field of a plane wave scattering from a rigid sphere. We then use this theoretical field as the predicted observation in an extended Kalman filter whose state is the speakers current position, the direction of arrival of the plane wave. By minimizing the squared-error between the predicted pressure field and that actually recorded, we are able to infer the position of the speaker.

A noise-robust speech recognition method composed of weak noise suppression and weak Vector Taylor Series Adaptation

This paper proposes a noise-robust speech recognition method composed of weak noise suppression (NS) and weak Vector Taylor Series Adaptation (VTSA). The proposed method compensates defects of NS and VTSA, and gains only the advantages by them. The weak NS reduces distortion by over-suppression that may accompany noise-suppressed speech. The weak VTSA avoids over-adaptation by offsetting a part of acoustic-model adaptation that corresponds to the suppressed noise. Evaluation results with the AURORA2 database show that the proposed method achieves as much as 1.2 points higher word accuracy (87.4%) than a method with VTSA alone (86.2%) that is always better than its counterpart with NS.

Extended Minimum Classification Error Training in Voice Activity Detection

Voice Activity Detection (VAD) is a fundamental part of speech processing. Combination of multiple acoustic features is an effective approach to make VAD more robust against various noise conditions. There have been proposed several feature combination methods, in which weights for feature values are optimized based on Minimum Classification Error (MCE) training. We improve these MCE-based methods by introducing a novel discriminative function for whole frames. The proposed method optimizes combination weights taking into account the ratio between false acceptance and false rejection rates as well as the effect of the use of shaping procedures such as hangover.

Fast and accurate personal authentication using ear acoustics

This paper presents a biometric personal-authentication method that exploits acoustic characteristics of human ears. It transmits a probe signal into the ear and receives its reflection, which contains personal identity information about the shape of the ear canal. Based on a study of effective and efficient acoustic feature representation and the use of audio equipment suitable for acquiring features with low within-individual variability, the proposed method achieves a promising equal error rate of 0.97% with only 12 feature components. A prototype system for Android smartphones is also presented.