Related papers: Speech and Speaker Recognition from Raw Waveform w…
Deep learning approaches have been widely used in Automatic Speech Recognition (ASR) and they have achieved a significant accuracy improvement. Especially, Convolutional Neural Networks (CNNs) have been revisited in ASR recently. However,…
Inspired by the progress of the End-to-End approach [1], this paper systematically studies the effects of Number of Filters of convolutional layers on the model prediction accuracy of CNN+RNN (Convolutional Neural Networks adding to…
Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within…
Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-AR models were…
Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…
Deep convolutional neural networks have achieved impressive performance on a broad range of problems, beating prior art on established benchmarks, but it often remains unclear what are the representations learnt by those systems and how…
Sentence classification is one of the basic tasks of natural language processing. Convolution neural network (CNN) has the ability to extract n-grams features through convolutional filters and capture local correlations between consecutive…
This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin…
The Deep Convolutional Neural Networks (CNNs) have obtained a great success for pattern recognition, such as recognizing the texts in images. But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling…
Speech emotion recognition (SER) is to study the formation and change of speaker's emotional state from the speech signal perspective, so as to make the interaction between human and computer more intelligent. SER is a challenging task that…
Data-driven models achieve successful results in Speech Emotion Recognition (SER). However, these models, which are often based on general acoustic features or end-to-end approaches, show poor performance when the testing set has a…
Encoding-decoding CNNs play a central role in data-driven noise reduction and can be found within numerous deep-learning algorithms. However, the development of these CNN architectures is often done in ad-hoc fashion and theoretical…
Attempts to develop speech enhancement algorithms with improved speech intelligibility for cochlear implant (CI) users have met with limited success. To improve speech enhancement methods for CI users, we propose to perform speech…
We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters. A convolution filter is typically implemented as a linear affine transformation followed by a non-linear…
The convolutional neural network (CNN) based approaches have shown great success for speaker verification (SV) tasks, where modeling long temporal context and reducing information loss of speaker characteristics are two important challenges…
Recent studies have demonstrated that incorporating auxiliary information, such as speaker voiceprint or visual cues, can substantially improve Speech Enhancement (SE) performance. However, single-channel methods often yield suboptimal…
Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would…
Speech recognition from raw waveform involves learning the spectral decomposition of the signal in the first layer of the neural acoustic model using a convolution layer. In this work, we propose a raw waveform convolutional filter learning…
Deep structured output learning shows great promise in tasks like semantic image segmentation. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to…
Automatic speaker verification (ASV) systems are often affected by spoofing attacks. Recent transformer-based models have improved anti-spoofing performance by learning strong feature representations. However, these models usually need high…