An overview of noise-robust automatic speech recognition

J Li, L Deng, Y Gong… - IEEE/ACM Transactions …, 2014 - ieeexplore.ieee.org
New waves of consumer-centric applications, such as voice search and voice interaction
with mobile devices and home entertainment systems, increasingly require automatic …

Machine learning paradigms for speech recognition: An overview

L Deng, X Li - IEEE Transactions on Audio, Speech, and …, 2013 - ieeexplore.ieee.org
Automatic Speech Recognition (ASR) has historically been a driving force behind many
machine learning (ML) techniques, including the ubiquitously used hidden Markov model …

Deep learning: methods and applications

L Deng, D Yu - Foundations and trends® in signal processing, 2014 - nowpublishers.com
This monograph provides an overview of general deep learning methodology and its
applications to a variety of signal and information processing tasks. The application areas …

Noisy training for deep neural networks in speech recognition

S Yin, C Liu, Z Zhang, Y Lin, D Wang, J Tejedor… - EURASIP Journal on …, 2015 - Springer
Deep neural networks (DNNs) have gained remarkable success in speech recognition,
partially attributed to the flexibility of DNN models in learning complex patterns of speech …

Acoustic modeling with hierarchical reservoirs

F Triefenbach, A Jalalvand… - … on Audio, Speech …, 2013 - ieeexplore.ieee.org
Accurate acoustic modeling is an essential requirement of a state-of-the-art continuous
speech recognizer. The Acoustic Model (AM) describes the relation between the observed …

Deep neural network acoustic models for spoken assessment applications

J Cheng, X Chen, A Metallinou - Speech Communication, 2015 - Elsevier
In this paper, we investigate the effectiveness of applying deep neural network hidden
Markov models, or DNN-HMMs, for acoustic modeling in the context of educational …

Sequence classification using the high-level features extracted from deep neural networks

L Deng, J Chen - … Conference on Acoustics, Speech and Signal …, 2014 - ieeexplore.ieee.org
The recent success of deep neural networks (DNNs) in speech recognition can be attributed
largely to their ability to extract a specific form of high-level features from raw acoustic data …

An auditory inspired amplitude modulation filter bank for robust feature extraction in automatic speech recognition

N Moritz, J Anemüller… - IEEE/ACM Transactions on …, 2015 - ieeexplore.ieee.org
The human ability to classify acoustic sounds is still unmatched compared to recent methods
in machine learning. Psychoacoustic and physiological studies indicate that the auditory …

Foundations and trends in signal processing: Deep learning–methods and applications

L Deng, D Yu - 2014 - microsoft.com
This monograph provides an overview of general deep learning methodology and its
applications to a variety of signal and information processing tasks. The application areas …

Classifier architectures for acoustic scenes and events: implications for DNNs, TDNNs, and perceptual features from DCASE 2016

J Schröder, N Moritz, J Anemüller… - … on Audio, Speech …, 2017 - ieeexplore.ieee.org
This paper evaluates neural network (NN) based systems and compares them to Gaussian
mixture model (GMM) and hidden Markov model (HMM) approaches for acoustic scene …