Using Quantized Neural Network for Speaker Recognition on Edge Computing Devices

Dai, Tongwei

doi:10.1088/1742-6596/1992/2/022177

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data collected by sensors can be processed locally or transferred to the cloud after the local preprocessing. An artificial neural network (ANN) has been deployed on IoT devices to perform special tasks such as voice recognition and verification [ 2 ]. However, the intensive memory and processing requirements of conventional ANNs have made it difficult to deploy deep networks to resource-constrained and power-constrained IoT devices.…”

Section: Introductionmentioning

confidence: 99%

Optimal Mapping of Spiking Neural Network to Neuromorphic Hardware for Edge-AI

Xiao

Chen

Wang

2022

Sensors

View full text Add to dashboard Cite

Neuromorphic hardware, the new generation of non-von Neumann computing system, implements spiking neurons and synapses to spiking neural network (SNN)-based applications. The energy-efficient property makes the neuromorphic hardware suitable for power-constrained environments where sensors and edge nodes of the internet of things (IoT) work. The mapping of SNNs onto neuromorphic hardware is challenging because a non-optimized mapping may result in a high network-on-chip (NoC) latency and energy consumption. In this paper, we propose NeuMap, a simple and fast toolchain, to map SNNs onto the multicore neuromorphic hardware. NeuMap first obtains the communication patterns of an SNN by calculation that simplifies the mapping process. Then, NeuMap exploits localized connections, divides the adjacent layers into a sub-network, and partitions each sub-network into multiple clusters while meeting the hardware resource constraints. Finally, we employ a meta-heuristics algorithm to search for the best cluster-to-core mapping scheme in the reduced searching space. We conduct experiments using six realistic SNN-based applications to evaluate NeuMap and two prior works (SpiNeMap and SNEAP). The experimental results show that, compared to SpiNeMap and SNEAP, NeuMap reduces the average energy consumption by 84% and 17% and has 55% and 12% lower spike latency, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimal Mapping of Spiking Neural Network to Neuromorphic Hardware for Edge-AI

Xiao

Chen

Wang

2022

Sensors

View full text Add to dashboard Cite

show abstract

Speaker Recognition Using Constrained Convolutional Neural Networks in Emotional Speech

Simic

Suzic

Nosek

et al. 2022

Entropy

View full text Add to dashboard Cite

Speaker recognition is an important classification task, which can be solved using several approaches. Although building a speaker recognition model on a closed set of speakers under neutral speaking conditions is a well-researched task and there are solutions that provide excellent performance, the classification accuracy of developed models significantly decreases when applying them to emotional speech or in the presence of interference. Furthermore, deep models may require a large number of parameters, so constrained solutions are desirable in order to implement them on edge devices in the Internet of Things systems for real-time detection. The aim of this paper is to propose a simple and constrained convolutional neural network for speaker recognition tasks and to examine its robustness for recognition in emotional speech conditions. We examine three quantization methods for developing a constrained network: floating-point eight format, ternary scalar quantization, and binary scalar quantization. The results are demonstrated on the recently recorded SEAC dataset.

show abstract

Using Quantized Neural Network for Speaker Recognition on Edge Computing Devices

Cited by 2 publications

References 0 publications

Optimal Mapping of Spiking Neural Network to Neuromorphic Hardware for Edge-AI

Optimal Mapping of Spiking Neural Network to Neuromorphic Hardware for Edge-AI

Speaker Recognition Using Constrained Convolutional Neural Networks in Emotional Speech

Contact Info

Product

Resources

About