IEEE Transactions on Very Large Scale Integration (VLSI) Systems · 2015 · 52 citations · 10 references
ComputingComputer EngineeringComputer ScienceComputer ArchitectureFeature EngineeringTime Series AnalysisDigital Signal ProcessingFrequency-domain AnalysisPattern RecognitionSignal ProcessingSpectral AnalysisSpeech RecognitionBit-width OptimizationCepstral AnalysisCepstral CoefficientsCepstral FeaturesDynamic RangeEnergy ConsumptionEnergy-efficient ComputationFloating-point Arithmetic
This brief presents an energy-efficient architecture to extract mel-frequency cepstrum coefficients (MFCCs) for real-time speech recognition systems. Based on the algorithmic property of MFCC feature extraction, the architecture is designed with floating-point arithmetic units to cover a wide dynamic range with a small bit-width. Moreover, various operations required in the MFCC extraction are examined to optimize operational bit-width and lookup tables needed to compute nonlinear functions, such as trigonometric and logarithmic functions. In addition, the dataflow of MFCC extraction is tailored to minimize the computation time. As a result, the energy consumption is considerably reduced compared with previous MFCC extraction systems.
10
The cepstrum: A guide to processing
D. G. Childers, Doug Skinner, R. C. Kemerait · Proceedings of the IEEE · 1977 · 595 citations
An efficient MFCC extraction method in speech recognition
Wei Han, Cheong-Fat Chan, Chiu‐Sing Choy et al. · 2006 · 290 citations