An unsupervised deep domain adaptation approach for robust speech recognition
S Sun, B Zhang, L Xie, Y Zhang - Neurocomputing, 2017 - Elsevier
This paper addresses the robust speech recognition problem as a domain adaptation task.
Specifically, we introduce an unsupervised deep domain adaptation (DDA) approach to …
Specifically, we introduce an unsupervised deep domain adaptation (DDA) approach to …
Transfer linear subspace learning for cross-corpus speech emotion recognition
P Song - IEEE transactions on affective computing, 2017 - ieeexplore.ieee.org
Speech emotion recognition has received an increasing interest in recent years, which is
often conducted on the assumption that speech utterances in training and testing datasets …
often conducted on the assumption that speech utterances in training and testing datasets …
Feature extraction methods for speaker recognition: A review
G Chaudhary, S Srivastava… - International Journal of …, 2017 - World Scientific
This paper presents main paradigms of research for feature extraction methods to further
augment the state of art in speaker recognition (SR) which has been recognized extensively …
augment the state of art in speaker recognition (SR) which has been recognized extensively …
An end-to-end deep learning approach to simultaneous speech dereverberation and acoustic modeling for robust speech recognition
We propose an integrated end-to-end automatic speech recognition (ASR) paradigm by joint
learning of the front-end speech signal processing and back-end acoustic modeling. We …
learning of the front-end speech signal processing and back-end acoustic modeling. We …
New Era for Robust Speech Recognition
The field of automatic speech recognition has evolved greatly since the introduction of deep
learning, which began only about 5 years ago. In particular, as more and more products …
learning, which began only about 5 years ago. In particular, as more and more products …
Regularized speaker adaptation of KL-HMM for dysarthric speech recognition
This paper addresses the problem of recognizing the speech uttered by patients with
dysarthria, which is a motor speech disorder impeding the physical production of speech …
dysarthria, which is a motor speech disorder impeding the physical production of speech …
Adaptive unscented Kalman filter based on maximum posterior and random weighting
Z Gao, D Mu, S Gao, Y Zhong, C Gu - Aerospace Science and Technology, 2017 - Elsevier
The unscented Kalman filter (UKF) is an effective technique of state estimation for nonlinear
dynamic systems. However, its performance depends on prior knowledge on system noise. If …
dynamic systems. However, its performance depends on prior knowledge on system noise. If …
Adaptation of deep neural network acoustic models for robust automatic speech recognition
Deep neural networks (DNNs) have been successfully applied to many pattern classification
problems, including acoustic modelling for automatic speech recognition (ASR). However …
problems, including acoustic modelling for automatic speech recognition (ASR). However …
Embedding-based speaker adaptive training of deep neural networks
An embedding-based speaker adaptive training (SAT) approach is proposed and
investigated in this paper for deep neural network acoustic modeling. In this approach …
investigated in this paper for deep neural network acoustic modeling. In this approach …
[PDF][PDF] Acoustic scene classification using a CNN-SuperVector system trained with auditory and spectrogram image features.
Enabling smart devices to infer about the environment using audio signals has been one of
the several long-standing challenges in machine listening. The availability of public-domain …
the several long-standing challenges in machine listening. The availability of public-domain …