There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave model, that ai
ms to restore the original speech signal. DiffWave, a recently published diffusion-based vocoder, has shown state-of-the-art synthesized speech quality and relatively shorter waveform generation times, with only a small set of parameters. We replace the mel-spectrum upsampler in DiffWave with a deep CNN upsampler, which is trained to alter the degraded speech mel-spectrum to match that of the original speech. The model is trained using the original speech waveform, but conditioned on the degraded speech mel-spectrum. Post-training, only the degraded mel-spectrum is used as input and the model generates an estimate of the original speech. Our model results in improved speech quality (original DiffWave model as baseline) on several different experiments. These include improving the quality of speech degraded by LPC-10 compression, AMR-NB compression, and signal clipping. Compared to the original DiffWave architecture, our scheme achieves better performance on several objective perceptual metrics and in subjective comparisons. Improvements over baseline are further amplified in a out-of-corpus evaluation setting.
Fourier domain methods are fast algorithms for SAR imaging. They typically involve an interpolation in the frequency domain to re-grid non-uniform data so inverse fast Fourier transforms can be performed. In this paper, we apply a frame reconstructio
n algorithm, extending the non-uniform fast Fourier transform, to stripmap SAR data. Further, we present an improved thresholded frame reconstruction algorithm for robust performance and improved computational efficiency. We demonstrate compelling results on real stripmap SAR data.
The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging. However, one of the common assumptions in most GAN architectures is the assump
tion of simple parametric latent-space distributions. While easy to implement, a simple latent-space distribution can be problematic for uses such as interpolation. This is due to distributional mismatches when samples are interpolated in the latent space. We present a straightforward formalization of this problem; using basic results from probability theory and off-the-shelf-optimization tools, we develop ways to arrive at appropriate non-parametric priors. The obtained prior exhibits unusual qualitative properties in terms of its shape, and quantitative benefits in terms of lower divergence with its mid-point distribution. We demonstrate that our designed prior helps improve image generation along any Euclidean straight line during interpolation, both qualitatively and quantitatively, without any additional training or architectural modifications. The proposed formulation is quite flexible, paving the way to impose newer constraints on the latent-space statistics.
Hardware support for deep convolutional neural networks (CNNs) is critical to advanced computer vision in mobile and embedded devices. Current designs, however, accelerate generic CNNs; they do not exploit the unique characteristics of real-time visi
on. We propose to use the temporal redundancy in natural video to avoid unnecessary computation on most frames. A new algorithm, activation motion compensation, detects changes in the visual input and incrementally updates a previously-computed output. The technique takes inspiration from video compression and applies well-known motion estimation techniques to adapt to visual changes. We use an adaptive key frame rate to control the trade-off between efficiency and vision quality as the input changes. We implement the technique in hardware as an extension to existing state-of-the-art CNN accelerator designs. The new unit reduces the average energy per frame by 54.2%, 61.7%, and 87.6% for three CNNs with less than 1% loss in vision accuracy.
Advancements in deep learning have ignited an explosion of research on efficient hardware for embedded computer vision. Hardware vision acceleration, however, does not address the cost of capturing and processing the image data that feeds these algor
ithms. We examine the role of the image signal processing (ISP) pipeline in computer vision to identify opportunities to reduce computation and save energy. The key insight is that imaging pipelines should be designed to be configurable: to switch between a traditional photography mode and a low-power vision mode that produces lower-quality image data suitable only for computer vision. We use eight computer vision algorithms and a reversible pipeline simulation tool to study the imaging systems impact on vision performance. For both CNN-based and classical vision algorithms, we observe that only two ISP stages, demosaicing and gamma compression, are critical for task performance. We propose a new image sensor design that can compensate for skipping these stages. The sensor design features an adjustable resolution and tunable analog-to-digital converters (ADCs). Our proposed imaging systems vision mode disables the ISP entirely and configures the sensor to produce subsampled, lower-precision image data. This vision mode can save ~75% of the average energy of a baseline photography mode while having only a small impact on vision task accuracy.
