Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for reliable speech recognition, particularly when the audio is corrupted by noise. However, cautious selection of sensory features is crucial for attaining high recognition performance. In the machine-learning community, deep learning approaches have recently attracted increasing attention because deep neural networks can effectively extract robust latent features that enable various recognition algorithms to demonstrate revolutionary generalization capabilities under diverse application conditions. This study introduces a connectionist-hidden Markov model (HMM) system for noise-robust AVSR. First, a deep denoising autoencoder is utilized for acquiring noise-robust audio features. By preparing the training data for the network with pairs of consecutive multiple steps of deteriorated audio features and the corresponding clean features, the network is trained to output denoised audio features from the corresponding features deteriorated by noise. Second, a convolutional neural network (CNN) is utilized to extract visual features from raw mouth area images. By preparing the training data for the CNN as pairs of raw images and the corresponding phoneme label outputs, the network is trained to predict phoneme labels from the corresponding mouth area input images. Finally, a multi-stream HMM (MSHMM) is applied for integrating the acquired audio and visual HMMs independently trained with the respective features. By comparing the cases when normal and denoised mel-frequency cepstral coefficients (MFCCs) are utilized as audio features to the HMM, our unimodal isolated word recognition results demonstrate that approximately 65 % word recognition rate gain is attained with denoised MFCCs under 10 dB signalto-noise-ratio (SNR) for the audio signal input. Moreover, our multimodal isolated word recognition results utilizing MSHMM with denoised MFCCs and acquired visual features demonstrate that an additional word recognition rate gain is attained for the SNR conditions below 10 dB.

[abstFig src='/00290001/04.jpg' width='300' text='Using a deep learning model, the robot locate the sound source from a multiple channel audio stream input' ] This study proposes the use of a deep neural network to localize a sound source using an array of microphones in a reverberant environment. During the last few years, applications based on deep neural networks have performed various tasks such as image classification or speech recognition to levels that exceed even human capabilities. In our study, we employ deep residual networks, which have recently shown remarkable performance in image classification tasks even when the training period is shorter than that of other models. Deep residual networks are used to process audio input similar to multiple signal classification (MUSIC) methods. We show that with end-to-end training and generic preprocessing, the performance of deep residual networks not only surpasses the block level accuracy of linear models on nearly clean environments but also shows robustness to challenging conditions by exploiting the time delay on power information.

No abstract

In search and rescue activities, unmanned aerial vehicles (UAV) should exploit sound information to compensate for poor visual information. This paper describes the design and implementation of a UAV-embedded microphone array system for sound source localization in outdoor environments. Four critical development problems included water-resistance of the microphone array, efficiency in assembling, reliability of wireless communication, and sufficiency of visualization tools for operators. To solve these problems, we developed a spherical microphone array system (SMAS) consisting of a microphone array, a stable wireless network communication system, and intuitive visualization tools. The performance of SMAS was evaluated with simulated data and a demonstration in the field. Results confirmed that the SMAS provides highly accurate localization, water resistance, prompt assembly, stable wireless communication, and intuitive information for observers and operators.