Speech Recognition On Timit

評価指標

Percentage error

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	Percentage error	Paper Title	Repository
Li-GRU	16.3	The PyTorch-Kaldi Speech Recognition Toolkit
LSNN	33.2	Long short-term memory and learning-to-learn in networks of spiking neurons
wav2vec	14.7	wav2vec: Unsupervised Pre-training for Speech Recognition
wav2vec 2.0	8.3	wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
LSTM + Dropout + BatchNorm + Monophone Reg	14.5	The PyTorch-Kaldi Speech Recognition Toolkit
LiGRU + Dropout + BatchNorm + Monophone Reg	14.2	The PyTorch-Kaldi Speech Recognition Toolkit
QCNN-10L-256FM	19.64	Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition
LSTM	16.0	The PyTorch-Kaldi Speech Recognition Toolkit
Bi-LSTM + skip connections w/ CTC	17.7	Speech Recognition with Deep Recurrent Neural Networks
GRU + Dropout + BatchNorm + Monophone Reg	14.9	The PyTorch-Kaldi Speech Recognition Toolkit
LAS multitask with indicators sampling	20.4	Attention model for articulatory features detection
Light Gated Recurrent Units	16.7	Light Gated Recurrent Units for Speech Recognition
Hierarchical maxout CNN + Dropout	16.5	-	-
RNN + Dropout + BatchNorm + Monophone Reg	15.9	The PyTorch-Kaldi Speech Recognition Toolkit
GRU	16.6	The PyTorch-Kaldi Speech Recognition Toolkit
RNN-CRF on 24(x3) MFSC	17.3	Segmental Recurrent Neural Networks for End-to-end Speech Recognition	-
RNN	16.5	The PyTorch-Kaldi Speech Recognition Toolkit
Bi-RNN + Attention	17.6	Attention-Based Models for Speech Recognition
CNN in time and frequency + dropout, 17.6% w/o dropout	16.7	-	-
vq-wav2vec	11.6	vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations

0 of 22 row(s) selected.