Saved in:
Bibliographic Details
Main Authors: Zolfagharinejad, Mohamadreza, Büchel, Julian, Cassola, Lorenzo, Kinge, Sachin, Syed, Ghazi Sarwat, Sebastian, Abu, van der Wiel, Wilfred G.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.10434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912594948784128
author Zolfagharinejad, Mohamadreza
Büchel, Julian
Cassola, Lorenzo
Kinge, Sachin
Syed, Ghazi Sarwat
Sebastian, Abu
van der Wiel, Wilfred G.
author_facet Zolfagharinejad, Mohamadreza
Büchel, Julian
Cassola, Lorenzo
Kinge, Sachin
Syed, Ghazi Sarwat
Sebastian, Abu
van der Wiel, Wilfred G.
contents With the rise of decentralized computing, as in the Internet of Things, autonomous driving, and personalized healthcare, it is increasingly important to process time-dependent signals at the edge efficiently: right at the place where the temporal data are collected, avoiding time-consuming, insecure, and costly communication with a centralized computing facility (or cloud). However, modern-day processors often cannot meet the restrained power and time budgets of edge systems because of intrinsic limitations imposed by their architecture (von Neumann bottleneck) or domain conversions (analogue-to-digital and time-to-frequency). Here, we propose an edge temporal-signal processor based on two in-materia computing systems for both feature extraction and classification, reaching a software-level accuracy of 96.2% for the TI-46-Word speech-recognition task. First, a nonlinear, room-temperature dopant-network-processing-unit (DNPU) layer realizes analogue, time-domain feature extraction from the raw audio signals, similar to the human cochlea. Second, an analogue in-memory computing (AIMC) chip, consisting of memristive crossbar arrays, implements a compact neural network trained on the extracted features for classification. With the DNPU feature extraction consuming 100s nW and AIMC-based classification having the potential for less than 10 fJ per multiply-accumulate operation, our findings offer a promising avenue for advancing the compactness, efficiency, and performance of heterogeneous smart edge processors through in-materia computing hardware.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10434
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle In-Materia Speech Recognition
Zolfagharinejad, Mohamadreza
Büchel, Julian
Cassola, Lorenzo
Kinge, Sachin
Syed, Ghazi Sarwat
Sebastian, Abu
van der Wiel, Wilfred G.
Audio and Speech Processing
Sound
With the rise of decentralized computing, as in the Internet of Things, autonomous driving, and personalized healthcare, it is increasingly important to process time-dependent signals at the edge efficiently: right at the place where the temporal data are collected, avoiding time-consuming, insecure, and costly communication with a centralized computing facility (or cloud). However, modern-day processors often cannot meet the restrained power and time budgets of edge systems because of intrinsic limitations imposed by their architecture (von Neumann bottleneck) or domain conversions (analogue-to-digital and time-to-frequency). Here, we propose an edge temporal-signal processor based on two in-materia computing systems for both feature extraction and classification, reaching a software-level accuracy of 96.2% for the TI-46-Word speech-recognition task. First, a nonlinear, room-temperature dopant-network-processing-unit (DNPU) layer realizes analogue, time-domain feature extraction from the raw audio signals, similar to the human cochlea. Second, an analogue in-memory computing (AIMC) chip, consisting of memristive crossbar arrays, implements a compact neural network trained on the extracted features for classification. With the DNPU feature extraction consuming 100s nW and AIMC-based classification having the potential for less than 10 fJ per multiply-accumulate operation, our findings offer a promising avenue for advancing the compactness, efficiency, and performance of heterogeneous smart edge processors through in-materia computing hardware.
title In-Materia Speech Recognition
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2410.10434