speech-3

Robust Speech Recognition

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in robust-speech-recognition-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find robust-speech-recognition-3 models and implementations

Datasets

Google Speech Commands - Musan

FSC-P2

Subtasks

No subtasks available.

Most implemented papers

Very deep convolutional neural networks for robust speech recognition

Y. Qian, P. Woodland•Sat Oct 01 2016

The extension and optimisation of previous work on very deep convolutional neural networks for effective recognition of noisy speech in the Aurora 4 task are described and it is shown that state-level weighted log likelihood score combination in a joint acoustic model decoding scheme is very effective.

82

Content

0

Paper Graph

Scalable Factorized Hierarchical Variational Autoencoder Training

Wei-Ning Hsu, James R. Glass•Sun Apr 08 2018

A hierarchical sampling training algorithm to address limitations in terms of runtime, memory, and hyperparameter optimization, and a new visualization method for qualitatively evaluating the performance with respect to the interpretability and disentanglement is presented.

26 0

Paper Graph

Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition

Junbo Zhang, Yujun Wang, Lei Xie, Ke Wang, Sining Sun, Fei Xiang•Mon Mar 26 2018

Deep investigations in the use of GAN-based dereverberation front-end in ASR find that LSTM leads a significant improvement as compared with feed-forward DNN and CNN in the dataset and it is important to update the generator and the discriminator using the same mini-batch data during training.

39 0

Paper Graph

Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition

Hyung-Min Park, Jong-Hyeon Park, Myungwoo Oh•Thu Apr 11 2019

A domain adaptation method based on generative adversarial nets (GANs) with disentangled representation learning to achieve robustness in ASR systems is proposed and can be used for gender adaptation in gender-mismatched recognition.

8 0

Paper Graph

Learning Waveform-Based Acoustic Models Using Deep Variational Convolutional Neural Networks

Dino Oglic, Z. Cvetković, Peter Sollich•Sat Jun 22 2019

This work investigates the potential of stochastic neural networks for learning effective waveform-based acoustic models and proposes an effective approximation based on the Gauss–Hermite quadrature for regularization.

8 0

Paper Graph

Multi-Task Self-Supervised Learning for Robust Speech Recognition

Yoshua Bengio, M. Ravanelli, J. Trmal, P. Swietojanski, Jianyuan Zhong, Santiago Pascual, João Monteiro•Fri Jan 24 2020

PASE+ is proposed, an improved version of PASE that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks and learns transferable representations suitable for highly mismatched acoustic conditions.

303 0

Paper Graph

Domain Adaptation Using Class Similarity for Robust Speech Recognition

Pengyuan Zhang, L. xilinx Wang, Hanlin Zhu, Jiangjiang Zhao, Yuling Ren•Sat Oct 24 2020

This paper proposes a novel adaptation method for DNN acoustic model using class similarity, which outperforms fine-tuning using one-hot labels on both accent and noise adaptation task, especially when source and target domain are highly mismatched.

9 0

Paper Graph

An Investigation of End-to-End Models for Robust Speech Recognition

Archiki Prasad, R. Velmurugan, P. Jyothi•Wed Feb 10 2021

A detailed comparison of speech enhancement-based techniques and three different model-based adaptation techniques covering data augmentation, multi-task learning, and adversarial learning for robust ASR suggests that knowledge of the underlying noise type can meaningfully inform the choice of adaptation technique.

23 0

Paper Graph

Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition

Chng Eng Siong, Chen Chen, Yuchen Hu, Nana Hou•Sun Oct 10 2021

An interactive feature fusion network (IFF-Net) is proposed for noise-robust speech recognition to learn complementary information from the enhanced feature and original noisy feature to complement some missing information in the over-suppressed enhanced feature.

46 0

Paper Graph

Sequential Randomized Smoothing for Adversarially Robust Speech Recognition

B. Raj, R. Olivier•Thu Nov 04 2021

This paper applies adaptive versions of state-of-the-art attacks, such as the Imperceptible ASR attack, to their model, and shows that the strongest defense is robust to all attacks that use inaudible noise, and can only be broken with very high distortion.

11 0

Paper Graph

Adding a benchmark result helps the community track progress.