Towards Two-point Neuron-inspired Energy-efficient Multi-modal Open Master Hearing Aid

被引：0

作者：

Raza, M. ^{[1
]}

Adetomi, A. ^{[1
,2
]}

Ahmed, K. ^{[1
]}

Hussain, A. ^{[2
]}

Arslan, T. ^{[3
]}

Adeel, A. ^{[4
]}

机构：

[1] Univ Wolverhampton, CMI Lab, Wolverhampton, England

[2] Edinburgh Napier Univ, Sch Comp, Edinburgh, Midlothian, Scotland

[3] Univ Edinburgh, Sch Engn, Edinburgh, Midlothian, Scotland

[4] Stirling Univ, Sch Comp, Stirling, Scotland

来源：

INTERSPEECH 2023 | 2023年

关键词：

OpenMHA; energy efficiency; two-point neurons;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Here we demonstrate a two-point neuron-inspired audio-visual (AV) open Master Hearing Aid (OpenMHA) framework for on-chip energy-efficient speech enhancement (SE). The developed system is compared against state-of-the-art cepstrumbased audio-only (A-only) SE and conventional point-neuron inspired deep neural net (DNN) driven multimodal (MM) SE. Pilot experiments demonstrate that the proposed system outperforms audio-only SE in terms of speech quality and intelligibility and performs comparably to point neuron-inspired DNN with significantly reduced energy consumption at any time both during training and inferencing.

引用

页码：688 / 689

页数：2

共 17 条

[1] On the Way to a Multi-Modal Energy-Efficient Route
Prandtstetter, Matthias
Straub, Markus
Puchinger, Jakob
39TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY (IECON 2013), 2013, : 4779 - 4784
[2] Energy-Efficient Motion Planning for Multi-Modal Hybrid Locomotion
Suh, H. J. Terry
Xiong, Xiaobin
Singletary, Andrew
Ames, Aaron D.
Burdick, Joel W.
2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 7027 - 7033
[3] TOWARDS AN FPGA IMPLEMENTATION OF IOT-BASED MULTI-MODAL HEARING AID SYSTEM
Enemali, Godwin
Bishnu, Abhijeet
Ratnarajah, Tharmalingam
Arslan, Tughrul
2023 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW, 2023,
[4] An Energy-Efficient Quality Adaptive Framework for Multi-Modal Sensor Context Recognition
Roy, Nirmalya
Misra, Archan
Julien, Christine
Das, Sajal K.
Biswas, Jit
2011 IEEE INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND COMMUNICATIONS (PERCOM 2011), 2011, : 63 - 73
[5] A rail transit simulation system for multi-modal energy-efficient routing applications
Wang, Jinghui
Ghanem, Ahmed
Rakha, Hesham
Du, Jianhe
INTERNATIONAL JOURNAL OF SUSTAINABLE TRANSPORTATION, 2021, 15 (03) : 187 - 202
[6] A Highly Energy-Efficient Hyperdimensional Computing Processor for Wearable Multi-modal Classification
Menon, Alisha
Sun, Daniel
Sabouri, Sarina
Lee, Kyoungtae
Aristio, Melvin
Liew, Harrison
Rabaey, Jan M.
2021 IEEE BIOMEDICAL CIRCUITS AND SYSTEMS CONFERENCE (IEEE BIOCAS 2021), 2021,
[7] An Energy-Efficient Multi-Modal IoT System Leveraging NB-IoT and BLE
Basu, Subho Shankar
Haxhibeqiri, Jetmir
Baert, Mathias
Moons, Bart
Hoebeke, Jeroen
2020 IEEE INTERNATIONAL CONFERENCE ON INTERNET OF THINGS AND INTELLIGENCE SYSTEM (IOTAIS), 2021, : 30 - 36
[8] MMRL: A Multi-Modal Reinforcement Learning Technique for Energy-efficient Medical IoT Systems
Abo-eleneen, Amr
Mohamed, Amr
IWCMC 2021: 2021 17TH INTERNATIONAL WIRELESS COMMUNICATIONS & MOBILE COMPUTING CONFERENCE (IWCMC), 2021, : 2026 - 2031
[9] CAS: Fusing DNN Optimization & Adaptive Sensing for Energy-Efficient Multi-Modal Inference
Weerakoon, Dulanga
Subbaraju, Vigneshwaran
Lim, Joo Hwee
Misra, Archan
IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (11): : 10057 - 10064
[10] Unlocking the Potential of Two-Point Cells for Energy-Efficient and Resilient Training of Deep Nets
Adeel, Ahsan
Adetomi, Adewale
Ahmed, Khubaib
Hussain, Amir
Arslan, Tughrul
Phillips, W. A.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2023, 7 (03): : 818 - 828

← 1 2 →