关键词:
Informatics
signal processing
Speech recognition
Mel frequency cepstral coefficient
frequency scale
engineering computing
Language Development
Biomedical Engineering
Biological techniques
摘要:
The field of biomedical engineering and informatics has been advancing rapidly in this information age. Signal processing and information technology progress continually to provide new methodologies to enable researchers and scientists to address challenges and problems in biology, medicine and healthcare. This special issue, following two others on the related topic published in January 2012 and January 2013, includes eleven papers focusing on the new development of signal processing and informatics approaches to address the challenges and problems in biomedical engineering and bioinformatics. It is hoped that this special issue will benefit researchers from multiple disciplines including engineering, computing, and informatics. The papers are organized as follows. Automatic speech recognition (ASR) technology has been providing important functionality in computer assisted language learning applications. In the paper 'Improving Mispronunciation Detection using Adaptive Frequency Scale', Ge et al. present a Hidden Markov Model (HMM)-based method for the detection of mispronunciations. Exploiting the specific dialog scripting employed in language learning software, HMMs are trained for different pronunciations. New adaptive features have been developed and obtained through an adaptive warping of the frequency scale prior to computing the cepstral coefficients. Experimental results show that the adaptive frequency scale yields a better coefficient representation leading to higher classification rates in comparison with conventional HMMs using Mel-frequency cepstral coefficients.