Related papers: Learning Multiscale Features Directly From Wavefor…

Our goal is to provide a review of deep learning methods which provide insight into structured high-dimensional data. Rather than using shallow additive architectures common to most statistical models, deep learning uses layers of…

Raw waveform acoustic modelling has recently gained interest due to neural networks' ability to learn feature extraction, and the potential for finding better representations for a given scenario than hand-crafted features. SincNet has been…

Learning expressive representations for high-dimensional yet sparse features has been a longstanding problem in information retrieval. Though recent deep learning methods can partially solve the problem, they often fail to handle the…

Employing deep neural networks (DNNs) to directly learn filters for multi-channel speech enhancement has potentially two key advantages over a traditional approach combining a linear spatial filter with an independent tempo-spectral…

Deep learning models develop successive representations of their input in sequential layers, the last of which maps the final representation to the output. Here we investigate the informational content of these representations by observing…

Learning features from massive unlabelled data is a vast prevalent topic for high-level tasks in many machine learning applications. The recent great improvements on benchmark data sets achieved by increasingly complex unsupervised learning…

Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We introduce Neural Low-Degree Filtering (Neural LoFi), a stylized limit of gradient-based…

Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to…

Transformers have seen an unprecedented rise in Natural Language Processing and Computer Vision tasks. However, in audio tasks, they are either infeasible to train due to extremely large sequence length of audio waveforms or incur a…

While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability. Speaking rate mismatch is often observed in practical speaker…

Algorithmic latency in speech processing is dominated by the frame length used for Fourier analysis, which in turn limits the achievable performance of magnitude-centric approaches. As previous studies suggest the importance of phase grows…

Speech derverberation using a single microphone is addressed in this paper. Motivated by the recent success of the fully convolutional networks (FCN) in many image processing applications, we investigate their applicability to enhance the…

Deep learning based on deep neural networks has been very successful in many practical applications, but it lacks enough theoretical understanding due to the network architectures and structures. In this paper we establish some analysis for…

Processing data streams arriving at high speed requires the development of models that can provide fast and accurate predictions. Although deep neural networks are the state-of-the-art for many machine learning tasks, their performance in…

Transient loud intrusions, often occurring in noisy environments, can completely overpower speech signal and lead to an inevitable loss of information. While existing algorithms for noise suppression can yield impressive results, their…

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

Ordinary Deep Learning models require having the dimension of their outputs determined by a human practitioner prior to training and operation. For design tasks, this places a hard limit on the maximum complexity of any designs produced by…

Deep neural networks have shown the ability to extract universal feature representations from data such as images and text that have been useful for a variety of learning tasks. However, the fruits of representation learning have yet to be…

Artificial intelligence techniques are considered an effective means to accelerate flow field simulations. However, current deep learning methods struggle to achieve generalization to flow field resolutions while ensuring computational…

Automatic classification of sound commands is becoming increasingly important, especially for mobile and embedded devices. Many of these devices contain both cameras and microphones, and companies that develop them would like to use the…