On Batching Variable Size Inputs for Training End-to-End Speech
Enhancement Systems

v1v2 (latest)

On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems

25 January 2023

Philippe Gonzalez

ArXiv (abs)PDF HTML

Papers citing "On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems"

14 / 14 papers shown

Title
TPARN: Triple-path Attentive Recurrent Network for Time-domain Multichannel Speech Enhancement Ashutosh Pandey Buye Xu Anurag Kumar Jacob Donley P. Calamia DeLiang Wang KELM 79 42 0 20 Oct 2021
DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement Shubo Lv Yanxin Hu Shimin Zhang Lei Xie 48 93 0 16 Jun 2021
Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks Yuichiro Koyama Tyler Vuong Stefan Uhlich Bhiksha Raj 60 41 0 23 May 2020
SDR - half-baked or well done? F. Sánchez-Martínez M. Esplà-Gomis Hakan Erdogan J. Hershey 148 1,202 0 06 Nov 2018
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Yi Luo N. Mesgarani 159 1,794 0 20 Sep 2018
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions Jonathan Shen Ruoming Pang Ron J. Weiss M. Schuster Navdeep Jaitly ... Yuxuan Wang RJ Skerry-Ryan Rif A. Saurous Yannis Agiomyrgiannakis Yonghui Wu 79 2,701 0 16 Dec 2017
Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling Qi Meng Wei-neng Chen Yue Wang Zhi-Ming Ma Tie-Yan Liu FedML 47 102 0 29 Sep 2017
Supervised Speech Separation Based on Deep Learning: An Overview DeLiang Wang Jitong Chen SSL 77 1,373 0 24 Aug 2017
Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization Viacheslav Khomenko Oleg Shyshkov Olga Radyvonenko Kostiantyn Bokhan 47 65 0 18 Aug 2017
An Empirical Study of Mini-Batch Creation Strategies for Neural Machine Translation Makoto Morishita Yusuke Oda Graham Neubig Koichiro Yoshino Katsuhito Sudoh Satoshi Nakamura MoE 51 26 0 19 Jun 2017
A comprehensive study of batch construction strategies for recurrent neural networks in MXNet P. Doetsch Pavel Golik Hermann Ney 57 17 0 05 May 2017
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 427 2,945 0 15 Sep 2016
Adam: A Method for Stochastic Optimization Diederik P. Kingma Jimmy Ba ODL 1.9K 150,260 0 22 Dec 2014
Practical recommendations for gradient-based training of deep architectures Yoshua Bengio 3DH ODL 193 2,201 0 24 Jun 2012