Showing papers on "Generalised Hough transform published in 2014"
04 May 2014
TL;DR: This paper proposes an alternative to conventional MFCC or filterbank features, using an approach based on the Generalised Hough Transform (GHT), a common approach used in the field of image processing for the task of object detection.
Abstract: Despite recent advances in the use of Artificial Neural Network (ANN) architectures for automatic speech recognition (ASR), relatively little attention has been given to using feature inputs beyond MFCCs in such systems. In this paper, we propose an alternative to conventional MFCC or filterbank features, using an approach based on the Generalised Hough Transform (GHT). The GHT is a common approach used in the field of image processing for the task of object detection, where the idea is to learn the spatial distribution of a codebook of feature information relative to the location of the target class. During recognition, a simple weighted summation of the codebook activations is commonly used to detect the presence of the target classes. Here we propose to learn the weighting discriminatively in an ANN, where the aim is to optimise the static phone classification error at the output of the network. As such an ANN is common to hybrid ASR architectures, the output activations from the GHT can be considered as a novel feature for ASR. Experimental results on the TIMIT phoneme recognition task demonstrate the state-of-the-art performance of the approach.
2 citations
01 Dec 2014
TL;DR: A feature-based approach to address the challenging task of recognising overlapping sound events from single channel audio by taking the output from the GHT and using it as a feature for classification, and demonstrating that such an approach can improve upon the previous knowledge-based scoring system.
Abstract: In this paper, we propose a feature-based approach to address the challenging task of recognising overlapping sound events from single channel audio. Our approach is based on our previous work on Local Spectrogram Features (LSFs), where we combined a local spectral representation of the spectrogram with the Generalised Hough Transform (GHT) voting system for recognition. Here we propose to take the output from the GHT and use it as a feature for classification, and demonstrate that such an approach can improve upon the previous knowledge-based scoring system. Experiments are carried out on a challenging set of five overlapping sound events, with the addition of non-stationary background noise and volume change. The results show that the proposed system can achieve a detection rate of 99% and 91% in clean and 0dB noise conditions respectively, which is a strong improvement over our previous work.
1 citations