i) 2017 - 37 Documents

Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/4009

Browse

Subject: search.filters.subject.Speech recognition

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    DEEP BELIEF NETWORKS FOR PHONEME RECOGNITION IN CONTINUOUS TAMIL SPEECH–AN ANALYSIS
    (International Information and Engineering Technology and Association, 2017) Laxmi Sree, Baskaran Raguram; Vijaya Madhaya, Shanmugam
    . A combination of Gaussian Mixture Model and Hidden Markov Model has been used successfully in building acoustic models for speech recognition. These models have dominated this area for nearly three decades. Re-entry of neural networks in many clustering, classification and pattern recognition problems have triggered current researchers to focus in making use of its power in the area of speech recognition. This article compares the performance of Bernoulli-Bernoulli Deep Belief Networks (BBDBN) and Gaussian-Bernoulli Deep Belief Networks (GBDBN) on phoneme recognition of spoken speech in Tamil. In addition to that the impact of feature representation in the performance of acoustic model is also studied by using three different datasets built using different feature representation for the phoneme samples extracted from the continuous Tamil speech.
  • Thumbnail Image
    Item
    MULTI-LABEL CLASSIFICATION: PROBLEM TRANSFORMATION METHODS IN TAMIL PHONEME CLASSIFICATION
    (Elsevier, 2017) Pushpa, M; Karpagavalli, S
    Most of the supervised learning task has been carried out using single label classification and solved as binary or multiclass classification problems. The hierarchical relationship among the classes leads to Multi- Label (ML) classification which is learning from a set of instances that are associated with a set of labels. In Tamil language, phonemes fall into different categories according to place and manner of articulation. This motivates the application of multi-label classification methods to classify Tamil phonemes. Experiments are carried out using Binary Relevance (BR) and Label Powerset (LP) and BR’s improvement Classifier Chains (CC) methods with different base classifiers and the results are analysed.