p10tr/speech-recognition

Speech recognition related articles

Speech recognition

Speech recognition related articles

The acoustic & language modeling

• Sequence Modeling with CTC
• Facebook wav2letter
  • Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
  • Letter-Based Speech Recognition with Gated ConvNets
  • wav2letter github repo
• Google Listen-Attend-n-Spell
  • Listen, Attend and Spell
  • State-of-the-art Speech Recognition With Sequence-to-Sequence Models
• A time delay neural network architecture for efficient modeling of long temporal contexts
• Recent Progresses in Deep Learning Based Acoustic Models
• Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition
• Residual Convolutional CTC Networks for Automatic Speech Recognition
• Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling
• Exploring Neural Transducers for End-to-End Speech Recognition

Key word spotting

• Hello Edge: Keyword Spotting on Microcontrollers
• Convolutional Neural Networks for Small-footprint Keyword Spotting

Data augmentation

• Vocal Tract Length Perturbation (VTLP) improves speech recognition
• Vocal Tract Length Perturbation (VTLP) presentation
• Improving LSTM-CTC based ASR performance in domains with limited training data

Far-field speech recognition

• Acoustic Modeling for Google Home

State-of-art

• List of state-of-art LVCSR systems and reported WERs

Toolkits

• Kaldi

Hardware corner

• Neural networks on silicon

Corporas

• Open Speech and Language Resources

Uncategorized but useful links