Robust Speech Recognition
14 papers with code • 0 benchmarks • 1 datasets
Benchmarks
These leaderboards are used to track progress in Robust Speech Recognition
Google Speech Commands - Musan
Most implemented papers
Very Deep Convolutional Neural Networks for Robust Speech Recognition
Anustup900/Tensorflow-Speech-Recognition
•
•
On the Aurora 4 task, the very deep CNN achieves a WER of 8. 81%, further 7. 99% with auxiliary feature joint training, and 7. 09% with LSTM-RNN joint decoding.
Scalable Factorized Hierarchical Variational Autoencoder Training
Deep generative models have achieved great success in unsupervised learning with the ability to capture complex nonlinear relationships between latent generating factors and observations.
Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition
wangkenpu/rsrgan
•
•
First, we study the effectiveness of different dereverberation networks (the generator in GAN) and find that LSTM leads a significant improvement as compared with feed-forward DNN and CNN in our dataset.
Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition
vivivic/speech-domain-adaptation-DRL
•
•
The latent variables allow us to convert the domain of speech according to its context and domain representation.
Learning Waveform-Based Acoustic Models using Deep Variational Convolutional Neural Networks
doglic/asr
•
•
We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models.
Multi-task self-supervised learning for Robust Speech Recognition
santi-pdp/pase
•
•
We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks.
Domain Adaptation Using Class Similarity for Robust Speech Recognition
zhu-han/ASR-Adaption-Class-Similarity
•
•
Then, for each class, probabilities of this class are used to compute a mean vector, which we refer to as mean soft labels.
An Investigation of End-to-End Models for Robust Speech Recognition
A systematic comparison of these two approaches for end-to-end robust ASR has not been attempted before.
Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition
Speech enhancement (SE) aims to suppress the additive noise from a noisy speech signal to improve the speech's perceptual quality and intelligibility.
Sequential Randomized Smoothing for Adversarially Robust Speech Recognition
raphaelolivier/smoothingasr
•
•
EMNLP 2021
We apply adaptive versions of state-of-the-art attacks, such as the Imperceptible ASR attack, to our model, and show that our strongest defense is robust to all attacks that use inaudible noise, and can only be broken with very high distortion.
