Related papers: SuperCodec: A Neural Speech Codec with Selective B…
In this paper, we propose a new super resolution technique based on the interpolation followed by registering them using iterative back projection (IBP). Low resolution images are being interpolated and then the interpolated images are…
Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase…
This paper targets a new scenario that integrates speech separation with speech compression, aiming to disentangle multiple speakers while producing discrete representations for efficient transmission or storage, with applications in online…
The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder…
Bitrate scalability is a desirable feature for audio coding in real-time communications. Existing neural audio codecs usually enforce a specific bitrate during training, so different models need to be trained for each target bitrate, which…
In recent years, neural network-based image compression techniques have been able to outperform traditional codecs and have opened the gates for the development of learning-based video codecs. However, to take advantage of the high temporal…
Implicit neural representations have recently been extended to represent convolutional neural network weights via neural representation for neural networks, offering promising parameter compression benefits. However, standard multi-layer…
We propose a data-driven approach for deep convolutional neural network compression that achieves high accuracy with high throughput and low memory requirements. Current network compression methods either find a low-rank factorization of…
A rapidly increasing portion of Internet traffic is dominated by requests from mobile devices with limited- and metered-bandwidth constraints. To satisfy these requests, it has become standard practice for websites to transmit small and…
We propose sandwiched video compression -- a video compression system that wraps neural networks around a standard video codec. The sandwich framework consists of a neural pre- and post-processor with a standard video codec between them.…
Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to…
In models to generate program source code from natural language, representing this code in a tree structure has been a common approach. However, existing methods often fail to generate complex code correctly due to a lack of ability to…
While humans can effortlessly transform complex visual scenes into simple words and the other way around by leveraging their high-level understanding of the content, conventional or the more recent learned image compression codecs do not…
High-fidelity neural audio codecs in Text-to-speech (TTS) aim to compress speech signals into discrete representations for faithful reconstruction. However, prior approaches faced challenges in effectively disentangling acoustic and…
Recently deep learning-based methods have been applied in image compression and achieved many promising results. In this paper, we propose an improved hybrid layered image compression framework by combining deep learning and the traditional…
In speech enhancement, complex neural network has shown promising performance due to their effectiveness in processing complex-valued spectrum. Most of the recent speech enhancement approaches mainly focus on wide-band signal with a…
Binaural speech enhancement (BSE) aims to jointly improve the speech quality and intelligibility of noisy signals received by hearing devices and preserve the spatial cues of the target for natural listening. Existing methods often suffer…
Learned image compression methods have shown impressive performance but are often highly specialized for either human perception or specific machine vision tasks. This specialization limits their versatility and requires costly retraining…
Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native support for variable bitrate and progressive delivery, and their…
Due to the high computational complexity to model more frequency bands, it is still intractable to conduct real-time full-band speech enhancement based on deep neural networks. Recent studies typically utilize the compressed perceptually…