Search
Now showing items 21-30 of 1192
Multi-objective optimisation of wavelet features for phoneme recognition
(Institution of Engineering and Technology, 2016-03)
State-of-the-art speech representations provide acceptable recognition results under optimal conditions, though their performance in adverse conditions still needs to be improved. In this direction, many advances involving ...
On Including Temporal Constraints In Viterbi Alignment For Speech Recognition In Noise
(IEEE, Piscataway, NJ, United States, 2001)
Spoken emotion recognition through optimum-path forest classification using glottal features
(Academic Press Ltd- Elsevier Science LtdLondonInglaterra, 2010)
Uncertainty Weighting And Propagation In Dnn-Hmm-Based Speech Recognition
(2018)
In this paper an uncertainty weighting scheme for DNNHMM-based speech recognition is proposed to increase discriminability in the decoding process. To this end, the DNN pseudo-log-likelihoods are weighted according to the ...
Soft indexing of speech content for search in spoken documents
(2007)
The paper presents the Position Specific Posterior Lattice (PSPL), a novel lossy representation of automatic speech recognition lattices that naturally tends itself to efficient indexing and subsequent relevance ranking ...
Objective quality evaluation in blind source separation for speech recognition in a real room
(Elsevier Science, 2007-12)
The determination of quality of the signals obtained by blind source separation is a very important subject fordevelopment and evaluation of such algorithms. When this approach is used as a pre-processing stage for automatic ...
Autoregressive decomposition and pole tracking applied to vocal fold nodule signals
(2007-08-01)
This letter describes a novel algorithm that is based on autoregressive decomposition and pole tracking used to recognize two patterns of speech data: normal voice and disphonic voice caused by nodules. The presented method ...
Autoregressive decomposition and pole tracking applied to vocal fold nodule signals
(2007-08-01)
This letter describes a novel algorithm that is based on autoregressive decomposition and pole tracking used to recognize two patterns of speech data: normal voice and disphonic voice caused by nodules. The presented method ...
A tutorial review on entropy-based handcrafted feature extraction for information fusion
(2018-05-01)
Entropy (H) is the main subject of this article, concisely written to serve as a tutorial introducing two feature extraction (FE) methods for usage in digital signal processing (DSP) and pattern recognition (PR). The theory, ...