MSP-MFCC: Energy-Efficient MFCC Feature Extraction Method With Mixed-Signal Processing Architecture for Wearable Speech Recognition Applications

Abstract

Feature extraction is an essential part of automatic speech recognition (ASR) to compress raw speech data and enhance features, where conventional implementation methods based on the digital domain have encountered energy consumption and processing speed bottlenecks. Thus, we propose a Mixed-Signal Processing (MSP) architecture to efficiently extract Mel-Frequency Cepstrum Coefficients (MFCC) features. We design MSP-MFCC to pre-process speech signals in the analog domain, which significantly reduces the cost of the analog-to-digital converter (ADC), as well as the computational complexity of the digital back-end. Moreover, MSP-MFCC eliminates the time-consuming Fourier transform in the conventional digital realization by improving processing flow. We fabricated the analog part based on 180nm CMOS mixed-signal technology, then measured the chip. The measured results show the energy consumption of MSP-MFCC is $0.72~\mu \text{J}$ /frame, and the processing speed is up to $45.79~\mu \text{s}$ /frame. MSP-MFCC achieves 95% energy saving and about $6.4\times $ speedup than state of the art. Further, by using the features extracted by MSP-MFCC, speech recognition simulation reaches the accuracy of 98.2%, which also keeps the leading performance to its current counterparts. The proposed MFCC extractor is competitive for integration in the ultra-low-power always-on wearable speech recognition applications.

Keywords

• Mixed signal processing architecture
• energy-efficient feature extraction
• mel-frequency cepstrum coefficients (MFCC)
• wearable speech recognition application