Noise robust exemplar-based connected digit recognition

This paper proposes a noise robust exemplar-based speech recognition system where noisy speech is modeled as a linear combination of a set of speech and noise exemplars. The method works by finding a small number of labeled exemplars in a very large collection of speech and noise exemplars that jointly approximate the observed speech signal. We represent the exemplars using melenergies, which allows modeling the summation of speech and noise, and estimate the activations of the exemplars by minimizing the generalized Kullback-Leibler divergence between the observations and the model. The activations of the speech exemplars are directly being used for recognition. This approach proves to be promising, achieving up to 55.8% accuracy at signal-to-noise ratio −5 dB on the AURORA-2 connected digit recognition task.

• Type: Conference
• Year: 2010
• Where: ICASSP
• Authors: Jort F. Gemmeke, Tuomas Virtanen
• Keywords: Exemplar-based Speech Recognition, Exemplars, ICASSP 2010, Noise Exemplars, Signal Processing