Speech detection using Real Adaboost in car environments

Abstract

In real noisy environments, a speech detection algorithm plays an especially important role for noise reduction, speech recognition, and so on. In this paper, a speech/nonspeech detection algorithm using Real Adaboost is described, which can achieve extremely high detection rates. Boosting is a technique of combining a set weak classifiers to form one high-performance prediction rule, and Real Adaboost [R. E. Schapire and Y. Singer, Mach Learn. 37, 3, 297–336, (1999)] is an adaptive boosting algorithm in which the rule for combining the weak classifiers adapts to the problem and is able to yield extremely efficient classifiers. The Real Adaboost algorithm is investigated for speech/nonspeech detection problem. The proposed method shows an increasing speech detection rate in car environments, comparable with that of the detector based on GMM (Gaussian mixture model), where the detection accuracy rate was 98% for the proposed method and 92% for GMM in a car at highway speed. The results of the experiments clarified the effectiveness of the proposed method.

Human-Robot Interface Using System Request Utterance Detection Based on Acoustic Features

“…But, in [10], the experimental results clarify the effectiveness of the AdaBoost-based method in a low SNR environment. Therefore, we will research our methods implemented on the mobile robot in noisy real environments, such as a party room.…”

“…As the AdaBoost trains the weight, focusing on "hard" data, we can expect that it will achieve extremely high detection rates in low SNR situations. For example, in [10], the proposed method has been evaluated on car environments, and the experimental results show an improved voice detection rate, compared to that of conventional detectors based on the GMM (Gaussian Mixture Model) in a car moving at highway speed (the SNR of 2 dB).…”

“…By separating the utterance section and calculating acoustic features from each section, the accuracy of discrimination was improved. In adition, a robust voice/non-voice detection algorithm using AdaBoost, which can achieve extremely high detection rates in noisy environments, is described in this paper [10].…”

Audio-Based Video Editing with Two-Channel Microphone

“…As the AdaBoost trains the weight, focusing on "hard" data, we can expect that it will achieve extremely high detection rates in low SNR situations. For example, in [12], the proposed method has been evaluated on car environments, and the experimental results show an improved voice detection rate, compared to that of conventional detectors based on the GMM (Gaussian Mixture Model) in a car moving at highway speed (an SNR of 2 dB).…”

Video Editing Based on Situation Awareness from Voice Information and Face Emotion

“…As the AdaBoost trains the weight, focusing on "hard" data, we can expect that it will achieve extremely high detection rates in low SNR situations. For example, in (Takiguchi et al, 2006), the proposed method has been evaluated on car environments, and the experimental results show an improved voice detection rate, compared to that of conventional detectors based on the GMM (Gaussian Mixture Model) in a car moving at highway speed (an SNR of 2 dB)…”