4 accepted papers
This paper proposes a novel method for estimating which microphone belongs to the same group in a situation where there are multiple discussion groups in one room, using only audio information. The assumption is that each member wears one close-talk microphone, and that the audio is recorded on thei…
Neural Network (NN) based acoustic frontends, such as denoising autoencoders, are actively being investigated to improve the robustness of NN based acoustic models to various noise conditions. In recent work the joint training of such frontends with backend NNs has been shown to significantly improv…
Acoustic modeling with deep learning has drastically improved the performance of automatic speech recognition (ASR) where the main stream of the acoustic feature is still log-Mel filtered one. While the log-Mel filtered features lose harmonic-structure information, they still include useful informat…
Recently, the hybrid architecture of a neural network (NN) and a hidden Markov model (HMM) has shown significant improvement on automatic speech recognition (ASR) over the conventional Gaussian mixture model (GMM)-based system. The convolutional neural network (CNN), a successful NN-based system, ca…