paper-with-me

홈 › Papers

End-to-end Keyword Spotting using Neural Architecture Search and Quantization

2021-04-14 · David Peter, Wolfgang Roth, Franz Pernkopf

This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models in limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) operating on raw audio waveforms. After a suitable KWS model is found with NAS, we conduct quantization of weights and activations to reduce the memory footprint. We conduct extensive experiments on the Google speech commands dataset. In particular, we compare our end-to-end approach to mel-frequency cepstral coefficient (MFCC) based systems. For quantization, we compare fixed bit-width quantization and trained bit-width quantization. Using NAS only, we were able to obtain a highly efficient model with an accuracy of 95.55% using 75.7k parameters and 13.6M operations. Using trained bit-width quantization, the same model achieves a test accuracy of 93.76% while using on average only 2.91 bits per activation and 2.51 bits per weight.

📄 PDF Abstract BibTeX arXiv:2104.06666

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword SpottingNeural Architecture SearchQuantization

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Neural Architecture Search Neural Architecture Search (NAS) learns a modular architecture which can be transferred from a small dataset to a large dataset. The method does this by reducing the problem…
Differentiable NAS 설명 없음

Similar Papers 제목 키워드 기반

Low-bit quantization and quantization-aware training for small-footprint keyword spotting

2018-10-19 · Yuriy Mishchenko, Yusuf Goren, Ming Sun, Chris Beauchene 외

We investigate low-bit quantization to reduce computational cost of deep neural network (DNN) based keyword spotting (KWS). We propose approaches to further reduce quantization bits via integrating quantization into keyw…

Keyword SpottingQuantizationSmall-Footprint Keyword Spotting

Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization

2020-12-18 · David Peter, Wolfgang Roth, Franz Pernkopf

This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differentiable NAS approach to optimize the stru…

Keyword SpottingNeural Architecture SearchQuantization

Encoder-Decoder Neural Architecture Optimization for Keyword Spotting

2021-06-04 · Tong Mo, Bang Liu

Keyword spotting aims to identify specific keyword audio utterances. In recent years, deep convolutional neural networks have been widely utilized in keyword spotting systems. However, their model architectures are mainl…

DecoderKeyword SpottingNeural Architecture Search

Neural Architecture Search For Keyword Spotting

2020-09-01 · Tong Mo, Yakun Yu, Mohammad Salameh, Di Niu 외

Deep neural networks have recently become a popular solution to keyword spotting systems, which enable the control of smart devices via voice. In this paper, we apply neural architecture search to search for convolutiona…

Keyword SpottingNeural Architecture Search

Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization

2021-08-03 · Jonathan Macoskey, Grant P. Strimel, Ariya Rastrow

We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks. The architecture enables a dynamic pivot f…

Inference OptimizationKeyword SpottingQuantizationspeech-recognition+1