HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Speech Recognition On Timit

Metrics

Percentage error

Results

Performance results of various models on this benchmark

Paper TitleRepository
LSNN33.2Long short-term memory and learning-to-learn in networks of spiking neurons
LAS multitask with indicators sampling20.4Attention model for articulatory features detection
Soft Monotonic Attention (ours, offline)20.1Online and Linear-Time Attention by Enforcing Monotonic Alignments
QCNN-10L-256FM19.64Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition
Bi-LSTM + skip connections w/ CTC17.7Speech Recognition with Deep Recurrent Neural Networks
Bi-RNN + Attention17.6Attention-Based Models for Speech Recognition
RNN-CRF on 24(x3) MFSC17.3Segmental Recurrent Neural Networks for End-to-end Speech Recognition-
Light Gated Recurrent Units16.7Light Gated Recurrent Units for Speech Recognition
CNN in time and frequency + dropout, 17.6% w/o dropout16.7--
GRU16.6The PyTorch-Kaldi Speech Recognition Toolkit
Hierarchical maxout CNN + Dropout16.5--
RNN16.5The PyTorch-Kaldi Speech Recognition Toolkit
Li-GRU16.3The PyTorch-Kaldi Speech Recognition Toolkit
LSTM16.0The PyTorch-Kaldi Speech Recognition Toolkit
RNN + Dropout + BatchNorm + Monophone Reg15.9The PyTorch-Kaldi Speech Recognition Toolkit
GRU + Dropout + BatchNorm + Monophone Reg14.9The PyTorch-Kaldi Speech Recognition Toolkit
Li-GRU + fMLLR features14.9Light Gated Recurrent Units for Speech Recognition
wav2vec14.7wav2vec: Unsupervised Pre-training for Speech Recognition
LSTM + Dropout + BatchNorm + Monophone Reg14.5The PyTorch-Kaldi Speech Recognition Toolkit
LiGRU + Dropout + BatchNorm + Monophone Reg14.2The PyTorch-Kaldi Speech Recognition Toolkit
0 of 22 row(s) selected.
Speech Recognition On Timit | SOTA | HyperAI