Google
×
In this paper we propose to use a modified version of this hierarchical model to generate features for standard hidden Markov models. To obtain these features ...
spectro-temporal, hierarchical processing of the speech improves the robustness of speech recognition, but uses Hidden Markov Models. (HMMs) instead of ...
By taking spectro-temporal aspects into account when extracting features, speech recognition performance has been reported to improve especially under noisy ...
The work presented in this thesis was carried out as I was a research as- sistant at the control theory and robotic lab of the TU Darmstadt. The.
Xavier Domont, "Hierarchical Spectro-Temporal Features for Robust Speech Recognition", 2010. Abstract. Automatic Speech Recognition (ASR) systems are ...
People also ask
Speech recognition robust against interfering noise remains a difficult task. We previously presented a set of spectro- temporal speech features which we ...
PDF | On Sep 22, 2008, Martin Heckmann and others published A closer look on hierarchical spectro-temporal features (HIST) | Find, read and cite all the ...
In this paper we present a hierarchical framework for the extraction of spectro-temporal acoustic features. The design of the features targets higher ...
We propose to exploit this observation and model the harmonic patterns, amplitude envelope, and noisy phonetic components with a smooth representation, and then ...
In this paper we present a hierarchical framework for the extraction of spectro-temporal acoustic features. The design of the features targets higher ...