Sorry, you need to enable JavaScript to visit this website.

ICASSP 2021 - IEEE International Conference on Acoustics, Speech and Signal Processing is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The ICASSP 2021 conference will feature world-class presentations by internationally renowned speakers, cutting-edge session topics and provide a fantastic opportunity to network with like-minded professionals from around the world. Visit website.

We summarise previous work showing that the basic sigmoid activation function arises as an instance of Bayes’s theorem, and that recurrence follows from the prior. We derive a layer- wise recurrence without the assumptions of previous work, and show that it leads to a standard recurrence with modest modifications to reflect use of log-probabilities. The resulting architecture closely resembles the Li-GRU which is the current state of the art for ASR. Although the contribution is mainly theoretical, we show that it is able to outperform the state of the art on the TIMIT and AMI datasets.

Categories:
4 Views

This paper presents a deep neural network (DNN)-based system for phase reconstruction of speech signals solely from their magnitude spectrograms. The phase is very sensitive to time shifts. Therefore it is meaningful to estimate the phase derivatives instead of the phase directly, e.g., using DNNs and then apply a phase reconstruction method to recombine these estimates to a suitable phase spectrum. In this paper, we propose three changes for such a two-stage phase reconstruction system.

Categories:
10 Views

This paper presents a deep neural network (DNN)-based system for phase reconstruction of speech signals solely from their magnitude spectrograms. The phase is very sensitive to time shifts. Therefore it is meaningful to estimate the phase derivatives instead of the phase directly, e.g., using DNNs and then apply a phase reconstruction method to recombine these estimates to a suitable phase spectrum. In this paper, we propose three changes for such a two-stage phase reconstruction system.

Categories:
36 Views

Block-sparse signal recovery without knowledge of block sizes and boundaries, such as those encountered in multi-antenna mmWave channel models, is a hard problem for compressed sensing (CS) algorithms. We propose a novel Sparse Bayesian Learning (SBL) method for block-sparse recovery based on popular CS based regularizers with the function input variable related to total variation (TV). Contrary to conventional approaches that impose the regularization on the signal components, we regularize the SBL hyperparameters.

Categories:
5 Views

The identification of structural differences between a music performance and the score is a challenging yet integral step of audio-to-score alignment, an important subtask of music signal processing. We present a novel method to detect such differences between the score and performance for a given piece of music using progressively dilated convolutional neural networks. Our method incorporates varying dilation rates at different layers to capture both short-term and long-term context, and can be employed successfully in the presence of limited annotated data.

Categories:
18 Views

Recent deep learning approaches have shown great improvement in audio source separation tasks. However, the vast majority of such work is focused on improving average separation performance, often neglecting to examine or control the distribution of the results. In this paper, we propose a simple, unified gradient reweighting scheme, with a lightweight modification to bias the learning process of a model and steer it towards a certain distribution of results. More specifically, we reweight the gradient updates of each batch, using a user-specified probability distribution.

Categories:
3 Views

The ability of an autonomous vehicle to perform 3D tracking is essential for safe planing and navigation in cluttered environments. The main challenges for multi-object tracking (MOT) in autonomous driving applications reside in the inherent uncertainties regarding the number of objects, when and where the objects may appear and disappear, and uncertainties regarding objects' states. Random finite set (RFS) based approaches can naturally model these uncertainties accurately and elegantly, and they have been widely used in radar-based tracking applications.

Categories:
3 Views

Pages