Related papers: Acoustic Model Adaptation from Raw Waveforms with …
Pattern recognition from audio signals is an active research topic encompassing audio tagging, acoustic scene classification, music classification, and other areas. Spectrogram and mel-frequency cepstral coefficients (MFCC) are among the…
We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed…
Many multichannel systems use a linear filter to retrieve a signal of interest corrupted by noise whose statistics are partly unknown. The optimal filter in Gaussian noise requires knowledge of the noise covariance matrix $\Sigma$ and in…
Most phoneme recognition state-of-the-art systems rely on a classical neural network classifiers, fed with highly tuned features, such as MFCC or PLP features. Recent advances in ``deep learning'' approaches questioned such systems, but…
Deep learning-based channel estimation has been recognized as a promising technique for sixth-generation wireless systems. However, most existing approaches rely solely on least-squares estimates obtained from demodulation reference…
In this paper, adaptive mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, adaptive convolutional neural networks (ACNNs) are employed in frame-level embedding…
We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature spaces of very high dimensionality. In a second step,…
In recent years, waveform-mapping-based speech enhancement (SE) methods have garnered significant attention. These methods generally use a deep learning model to directly process and reconstruct speech waveforms. Because both the input and…
In some DNNs for audio source separation, the relevant model parameters are independent of the sampling frequency of the audio used for training. Considering the application of dialogue separation, this is shown for two DNN architectures: a…
A recurrent Neural Network (RNN) is trained to predict sound samples based on audio input augmented by control parameter information for pitch, volume, and instrument identification. During the generative phase following training, audio…
In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training…
End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we…
Convolutional Neural Networks (CNN) are widely used to face challenging tasks like speech recognition, natural language processing or computer vision. As CNN architectures get larger and more complex, their computational requirements…
Despite recent advances in regularisation theory, the issue of parameter selection still remains a challenge for most applications. In a recent work the framework of statistical learning was used to approximate the optimal Tikhonov…
Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…
Filters are the essential elements in convolutional neural networks (CNNs). Filters are corresponded to the feature maps and form the main part of the computational and memory requirement for the CNN processing. In filter pruning methods, a…
WaveNet is a state-of-the-art text-to-speech vocoder that remains challenging to deploy due to its autoregressive loop. In this work we focus on ways to accelerate the original WaveNet architecture directly, as opposed to modifying the…
Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost. However, this comes at the price of losing granularity in the…
Symmetry is present in nature and science. In image processing, kernels for spatial filtering possess some symmetry (e.g. Sobel operators, Gaussian, Laplacian). Convolutional layers in artificial feed-forward neural networks have typically…
We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous…