Sparse coding based features for speech units classification. (January 2018)

• Record Type: Journal Article
• Authors: Sharma, Pulkit; Abrol, Vinayak; Dileep, A.D.; Sao, Anil Kumar
• Is Part Of: Computer speech & language. Volume 47(2018)
• Page Start: 333
• Page End: 350
• Publication Date: 2018-01
• Subjects: Sparse representation -- Dictionary learning -- Speech recognition; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2017.08.004
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Sparse representation (SR) based features for speech units classification. PCA-based multiple dictionaries to extract SR based feature from speech signals. Emphasizing discriminative information using a dictionary based on weighted decomposition of principal components. Proposed sparse features perform well even in noisy conditions. Abstract: In this work, we propose sparse representation based features for speech units classification tasks. In order to effectively capture the variations in a speech unit, the proposed method employs multiple class specific dictionaries. Here, the training data belonging to each class is clustered into multiple clusters, and a principal component analysis (PCA) based dictionary is learnt for each cluster. It has been observed that coefficients corresponding to middle principal components can effectively discriminate among different speech units. Exploiting this observation, we propose to use a transformation function known as weighted decomposition (WD) of principal components, which is used to emphasize the discriminative information present in the PCA-based dictionary. In this paper, both raw speech samples and mel frequency cepstral coefficients (MFCC) are used as an initial representation for feature extraction. For comparison, various popular dictionary learning techniques such as K-singular value decomposition (KSVD), simultaneous codeword optimization (SimCO) and greedy adaptive dictionary (GAD) are also employed in the proposed framework. The effectiveness of the proposed features is demonstrated using continuous density hidden Markov model (CDHMM) based classifiers for (i) classification of isolated utterances of E-set of English alphabet, (ii) classification of consonant-vowel (CV) segments in Hindi language and (iii) classification of phoneme from TIMIT phonetic corpus.