Related papers: Manifold learning-supported estimation of relative…

Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generative models are either…

Reconstructing the room transfer functions needed to calculate the complex sound field in a room has several important real-world applications. However, an unpractical number of microphones is often required. Recently, in addition to…

Air pollution, especially particulate matter 2.5 (PM2.5), is a pressing concern for public health and is difficult to estimate in developing countries (data-poor regions) due to a lack of ground sensors. Transfer learning models can be…

Deep speaker embedding has achieved satisfactory performance in speaker verification. By enforcing the neural model to discriminate the speakers in the training set, deep speaker embedding (called `x-vectors`) can be derived from the hidden…

Head-related transfer functions (HRTFs) are crucial for spatial soundfield reproduction in virtual reality applications. However, obtaining personalized, high-resolution HRTFs is a time-consuming and costly task. Recently, deep…

Impressive advances in acquisition and sharing technologies have made the growth of multimedia collections and their applications almost unlimited. However, the opposite is true for the availability of labeled data, which is needed for…

This paper introduces the Procedural (audio) Variational autoEncoder (ProVE) framework as a general approach to learning Procedural Audio PA models of environmental sounds with an improvement to the realism of the synthesis while…

To achieve robust far-field automatic speech recognition (ASR), existing techniques typically employ an acoustic front end (AFE) cascaded with a neural transducer (NT) ASR model. The AFE output, however, could be unreliable, as the…

In recent years, speech emotion recognition (SER) has been used in wide ranging applications, from healthcare to the commercial sector. In addition to signal processing approaches, methods for SER now also use deep learning techniques which…

In hearing aid applications, an important objective is to accurately estimate the direction of arrival (DOA) of multiple speakers in noisy and reverberant environments. Recently, we proposed a binaural DOA estimation method, where the DOAs…

Information in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features. In this paper, we propose adaptive feature selection (AFS)…

The randomized distributed function computation (RDFC) framework, which unifies many cutting-edge distributed computation and learning applications, is considered. An autoencoder (AE) architecture is proposed to minimize the total variation…

In this paper we introduce a recurrent neural network (RNN) based variational autoencoder (VAE) model with a new constrained loss function that can generate more meaningful electroencephalography (EEG) features from raw EEG features to…

In text-to-speech (TTS) and voice conversion (VC), acoustic features, such as mel spectrograms, are typically used as synthesis or conversion targets owing to their compactness and ease of learning. However, because the ultimate goal is to…

For 6-DOF (degrees of freedom) interactive virtual acoustic environments (VAEs), the spatial rendering of diffuse late reverberation in addition to early (specular) reflections is important. In the interest of computational efficiency, the…

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…

Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400)…

Variational Autoencoders (VAEs) have proven to be effective models for producing latent representations of cognitive and semantic value. We assess the degree to which VAEs trained on a prototypical tonal music corpus of 371 Bach's chorales…

This paper presents an accurate phoneme alignment model that aims for speech analysis and video content creation. We propose a variational autoencoder (VAE)-based alignment model in which a probable path is searched using encoded acoustic…

Dictionary learning algorithms or supervised deep convolution networks have considerably improved the efficiency of predefined feature representations such as SIFT. We introduce a deep scattering convolution network, with predefined wavelet…