Speaker Identification using a Novel Prosody with Fuzzy based Hierarchical Decision Tree Approach

Objectives: The proposed speaker identification using a novel prosody with fuzzy based hierarchical decision tree approach and is used to modifying the limitations of existing traditional methods. It improves the performance of speaker identification in given population under noisy environments. Methods/Statistics: The key idea of this approach is to achieve an enhanced efficiency speaker cluster group using prosody features with fuzzy clustering at each level to construct the hierarchical decision tree. At each level, a speaker at belong to same groups are constructed. The proposed method has novelty of prosody as pitch and loudness with fuzzy clustering are used. Findings: An experimental result shows that the proposed model using prosody features outperforms the efficiency of speaker accuracy rate of 93.75 when compare to vocal source accuracy rate of 81.25 under noisy environments. Applications: Gender and age identification, banking and smart voice based technology operation.