|
LSNN
|
Long short-term memory and learning-to-learn in n…
|
33.20
|
2018-03-26
|
|
|
LAS multitask with indicators sampling
|
Attention model for articulatory features detecti…
|
20.40
|
2019-07-02
|
|
|
Soft Monotonic Attention (ours, offline)
|
Online and Linear-Time Attention by Enforcing Mon…
|
20.10
|
2017-04-03
|
|
|
QCNN-10L-256FM
|
Quaternion Convolutional Neural Networks for End-…
|
19.64
|
2018-06-20
|
|
|
Bi-LSTM + skip connections w/ CTC
|
Speech Recognition with Deep Recurrent Neural Net…
|
17.70
|
2013-03-22
|
|
|
Bi-RNN + Attention
|
Attention-Based Models for Speech Recognition
|
17.60
|
2015-06-24
|
|
|
RNN-CRF on 24(x3) MFSC
|
Segmental Recurrent Neural Networks for End-to-en…
|
17.30
|
2016-03-01
|
|
|
Light Gated Recurrent Units
|
Light Gated Recurrent Units for Speech Recognition
|
16.70
|
2018-03-26
|
|
|
GRU
|
The PyTorch-Kaldi Speech Recognition Toolkit
|
16.60
|
2018-11-19
|
|
|
RNN
|
The PyTorch-Kaldi Speech Recognition Toolkit
|
16.50
|
2018-11-19
|
|
|
Li-GRU
|
The PyTorch-Kaldi Speech Recognition Toolkit
|
16.30
|
2018-11-19
|
|
|
LSTM
|
The PyTorch-Kaldi Speech Recognition Toolkit
|
16.00
|
2018-11-19
|
|
|
RNN + Dropout + BatchNorm + Monophone Reg
|
The PyTorch-Kaldi Speech Recognition Toolkit
|
15.90
|
2018-11-19
|
|
|
GRU + Dropout + BatchNorm + Monophone Reg
|
The PyTorch-Kaldi Speech Recognition Toolkit
|
14.90
|
2018-11-19
|
|
|
Li-GRU + fMLLR features
|
Light Gated Recurrent Units for Speech Recognition
|
14.90
|
2018-03-26
|
|
|
wav2vec
|
wav2vec: Unsupervised Pre-training for Speech Rec…
|
14.70
|
2019-04-11
|
|
|
LSTM + Dropout + BatchNorm + Monophone Reg
|
The PyTorch-Kaldi Speech Recognition Toolkit
|
14.50
|
2018-11-19
|
|
|
LiGRU + Dropout + BatchNorm + Monophone Reg
|
The PyTorch-Kaldi Speech Recognition Toolkit
|
14.20
|
2018-11-19
|
|
|
vq-wav2vec
|
vq-wav2vec: Self-Supervised Learning of Discrete …
|
11.60
|
2019-10-12
|
|
|
wav2vec 2.0
|
wav2vec 2.0: A Framework for Self-Supervised Lear…
|
8.30
|
2020-06-20
|
|