International Journal of Advanced Research in Electrical Electronics and Instrumentation Engineering · 2013 · 75 citations · 1 references
ComputingLinguisticsAcousticsNatural Language ProcessingTime Series AnalysisDynamic Time WarpingPattern RecognitionSpeech AcousticsSpeech RecognitionTime Series Feature ExtractionTime-frequency AnalysisCepstral AnalysisCepstral CoefficientsSpeech Pattern RecognitionSpeech Signal AnalysisSpeech Signal ProcessingTime Series Pattern RecognitionTime-frequency Feature Extraction
This paper describes an approach of isolated speech recognition by using the Mel-Scale Frequency Cepstral Coefficients (MFCC) and Dynamic Time Warping (DTW). Several features are extracted from speech signal of spoken words. An experimental database of total five speakers, speaking 10 digits each is collected under acoustically controlled room is taken. MFCC are extracted from speech signal of spoken words. To cope with different speaking speeds in speech recognition Dynamic Time Warping (DTW) is used. DTW is an algorithm, which is used for measuring similarity between two sequences, which may vary in time or speed.
1
Real-time speaker identification
Pasi Frati, Evgeny Karpov, Tomi Kinnunen · 2004 · 44 citations