Search Results for author:
Found 8 papers, 2 papers with code
Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
On CIFAR-10, we obtain a FID of 2. 80 by sampling in 15 steps under one-session training and the new state-of-the-art FID of 3. 37 by sampling in one step with additional training.
HQNAS: Auto CNN deployment framework for joint quantization and architecture search
Deep learning applications are being transferred from the cloud to edge with the rapid development of embedded computing systems.
FAQS: Communication-efficient Federate DNN Architecture and Quantization Co-Search for personalized Hardware-aware Preferences
Due to user privacy and regulatory restrictions, federate learning (FL) is proposed as a distributed learning framework for training deep neural networks (DNN) on decentralized data clients.
Dynamic Multi-scale Convolution for Dialect Identification
To address this issue, we propose a new architecture, named dynamic multi-scale convolution, which consists of dynamic kernel convolution, local multi-scale learning, and global multi-scale pooling.
Transformer with Bidirectional Decoder for Speech Recognition
To demonstrate our proposed speech transformer with a bidirectional decoder(STBD), we conduct extensive experiments on the AISHELL-1 dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Highly Efficient Architecture of NewHope-NIST on FPGA using Low-Complexity NTT/INTT
First, both the pre-processing of NTT and the post-processing of INTT are merged into the fast Fourier transform (FFT) algorithm, which reduces N and 2N modular multiplications for N-point NTT and INTT, respectively.
THUEE system description for NIST 2019 SRE CTS Challenge
This paper describes the systems submitted by the department of electronic engineering, institute of microelectronics of Tsinghua university and TsingMicro Co. Ltd. (THUEE) to the NIST 2019 speaker recognition evaluation CTS challenge.
Small-footprint Keyword Spotting with Graph Convolutional Network
Despite the recent successes of deep neural networks, it remains challenging to achieve high precision keyword spotting task (KWS) on resource-constrained devices.
