1

Hearing-Impaired Bio-Inspired Cochlear Models for Real-Time Auditory Applications

Biophysically realistic models of the cochlea are based on cascaded transmission-line (TL) models which capture longitudinal coupling, cochlear nonlinearities, as well as the human frequency selectivity. However, these models are slow to compute …

SERGAN: Speech Enhancement using Relativistic Generative Adversarial Networks with Gradient Penalty

Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Recently, conditional generative adversarial networks (cGANs) have shown promise in …

Biophysically-inspired Features Improve the Generalizability of Neural Network-based Speech Enhancement Systems

Recent advances in neural network (NN)-based speech enhancement schemes are shown to outperform most conventional techniques. However, the performance of such systems in adverse listening conditions such as negative signal-to-noise ratios and unseen …

Supervised Speech Dereverberation in Noisy Environments using Exemplar-based Sparse Representations

Exemplar-based techniques, where the noisy speech is decomposed as a linear combination of the speech and noise exemplars stored in a dictionary, have been successfully used for speech enhancement in noisy environments. This paper extends this …

Investigating Modulation Spectrogram Features for Deep Neural Network-Based Automatic Speech Recognition

Deep neural network (DNN) based acoustic modelling has been shown to yield significant improvements over Gaussian Mixture Models (GMM) for a variety of automatic speech recognition (ASR) tasks. In addition, it is also becoming popular to use rich …

Noise Robust Exemplar Matching for Speech Enhancement: Applications to Automatic Speech Recognition

We present a novel automatic speech recognition (ASR) scheme which uses the recently proposed noise robust exemplar matching framework for speech enhancement in the front-end. The proposed system employs a GMM-HMM back-end to recognize the enhanced …

Hybrid input spaces for exemplar-based noise robust speech recognition using coupled dictionaries

Exemplar-based feature enhancement successfully exploits a wide temporal signal context. We extend this technique with hybrid input spaces that are chosen for a more effective separation of speech from background noise. This work investigates the use …

Noise robust exemplar matching with coupled dictionaries for single-channel speech enhancement

In this paper, we propose a single-channel speech enhancement system based on the noise robust exemplar matching (N-REM) framework using coupled dictionaries. N-REM approximates noisy speech segments as a sparse linear combination of speech and noise …

Exemplar-based speech enhancement for deep neural network based automatic speech recognition

Deep neural network (DNN) based acoustic modelling has been successfully used for a variety of automatic speech recognition (ASR) tasks, thanks to its ability to learn higher-level information using multiple hidden layers. This paper investigates the …

Exemplar-based noise robust automatic speech recognition using modulation spectrogram features

We propose a novel exemplar-based feature enhancement method for automatic speech recognition which uses coupled dictionaries: an input dictionary containing atoms sampled in the modulation (envelope) spectrogram domain and an output dictionary with …