A 2.3 nJ/Frame Voice Activity Detector-Based Audio Front-End for Context-Aware System-On-Chip Applications in 32-nm CMOS

Author

Raychowdhury, Arijit ; Tokunaga, Carlos ; Beltman, Willem ; Deisher, Michael ; Tschanz, James W. ; De, Vivek

Author_Institution

Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA

Volume

48

Issue

8

fYear

2013

fDate

Aug. 2013

Firstpage

1963

Lastpage

1969

Abstract

Advanced human-machine interfaces require improved embedded sensors that can seamlessly interact with the user. Voice-based communication has emerged as a promising interface for next generation mobile, automotive and hands-free devices. Presented here is such an audio front-end with Voice Activity Detection (VAD) hardware targeted for low-power embedded SoCs, featuring a 512 pt FFT, programmable filters, noise floor estimator and a decision engine which has been fabricated in 32 nm CMOS. The dual-V_CC, dual-frequency design allows the core datapath to scale to near-threshold voltage (NTV), where power consumption is less than 50 uW. At peak energy efficiency, the core can process audio data at 2.3 nJ/frame - a 9.4X improvement over nominal voltage conditions.

Keywords

CMOS integrated circuits; intelligent sensors; low-power electronics; speech recognition; system-on-chip; voice communication; FFT; NTV; VAD hardware; advanced human-machine interfaces; audio front-end; core datapath; decision engine; embedded sensors; low-power embedded SoC; near-threshold voltage; noise floor estimator; programmable filters; size 32 nm; voice activity detection; voice-based communication; Engines; Hardware; Iron; Noise; Speech; Speech recognition; System-on-chip; Low-power sensor front-end; near $V_{{t}}$ operation; voice activity detection;

fLanguage

English

Journal_Title

Solid-State Circuits, IEEE Journal of

Publisher

ieee

ISSN

0018-9200

Type

jour

DOI

10.1109/JSSC.2013.2258827

Filename

6519946