paper-with-me

홈 › Papers

EdgeCRNN: an edgecomputing oriented model of acoustic feature enhancement for keyword spotting

2021-03-14 · Yungen Wei, Zheng Gong, Shunzhi Yang, Kai Ye, Yamin Wen

Keyword Spotting (KWS) is a significant branch of Automatic Speech Recognition (ASR) and has been widely used in edge computing devices. The goal of KWS is to provide high accuracy with a low False Alarm Rate (FAR), while reducing the costs of memory, computation, and latency. However, limited resources are challenging for KWS applications on edge computing devices. Lightweight models and structures for deep learning have achieved good results in the KWS branch while maintaining efficient performances. In this paper, we present a new Convolutional Recurrent Neural Network (CRNN) architecture named EdgeCRNN for edge computing devices. EdgeCRNN, which is based on depthwise separable convolution and residual structure, uses a feature enhanced method. On the Google Speech Commands Dataset, the experimental results depict that EdgeCRNN can test 11.1 audio data per second on Raspberry Pi 3B+, which is 2.2 times than that of Tpool2. Compared with Tpool2, the accuracy of EdgeCRNN reaches 98.05% whilst its performance is also competitive.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Edge-computingKeyword Spottingspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling

2026-05-07 · Guanrou Yang, Tian Tan, Qian Chen, Zhikang Niu 외 arxiv

Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks currently pose significant compatibility challe…

Self-Supervised LearningSpeech EnhancementVoice Conversion

BioSEN: A Bio-acoustic Signal Enhancement Network for Animal Vocalizations

2026-05-02 · Tianyu Song, Ton Viet Ta, Ngamta Thamwattana, Hisako Nomura 외 arxiv

Most work in audio enhancement targets human speech, while bioacoustics is less studied due to noisy recordings and the distinct traits of animal sounds. To fill this gap, we adapt speech enhancement methods and build Bi…

Speech Enhancement

TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement

2023-02-16 · Yunyang Zeng, Joseph Konan, Shuo Han, David Bick 외

Speech enhancement models have greatly progressed in recent years, but still show limits in perceptual quality of their speech outputs. We propose an objective for perceptual quality based on temporal acoustic parameters…

Speaker RecognitionSpeech Enhancement

SagnacAssisted Enhanced OTDR for Distributed Acoustic Sensing: A Standardized Benchmark and Engineering Evaluation Framework

2026-06-04 · Weiguang Wang, Fugen Wu, Hailing Wang, Xuechen Liang 외 arxiv

Phase-sensitive optical time-domain reflectometry ($φ$-OTDR) is widely used in large-scale distributed acoustic sensing (DAS) because it provides distributed spatiotemporal monitoring over long sensing distances. Its fie…

PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement

2023-02-16 · Muqiao Yang, Joseph Konan, David Bick, Yunyang Zeng 외

Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning objective that formalizes differences in …

Speech EnhancementTime SeriesTime Series Analysis