Acoustic model combinations for continuous speech recognition system. Issue 2 (1st January 2012)

• Record Type: Journal Article
• Authors: Aggarwal, R.K.; Dave, Mayank
• Is Part Of: International journal of computational systems engineering. Volume 1:Issue 2(2012)
• Page Start: 79
• Page End: 90
• Publication Date: 2012-01-01
• Subjects: automatic speech recognition -- ASR -- acoustic models -- confusion network combination -- CNC -- Hindi -- system combination -- Mel-frequency cepstrum coefficient -- MFCC -- perceptual linear prediction -- PLP -- discriminative training -- large margin estimation; Computer science -- Periodicals; Electronic data processing -- Periodicals; System analysis -- Periodicals; 003.3
• Languages: English
• ISSNs: 2046-3391

Abstract

System combination is a promising way to obtain a significant improvement in performance as compared to the conventional form of single system model. In the field of automatic speech recognition (ASR), various approaches have been studied focusing on different aspects of feature extraction and acoustic modelling. These approaches can be combined to utilise their complementary information and to cope with the limitations of individual technique. In this paper we have proposed a novel approach in which three acoustic models based on maximum likelihood, discriminative and margin-based estimation are combined using a technique called as confusion network combination. Further, each acoustic model is associated with a different type of feature extractor to derive observation vectors for training and testing. Experimental results show 2%–5% reduction in error rate for Hindi ASR.