Related papers: Unlocking Temporal Flexibility: Neural Speech Code…
Noise robustness remains a critical challenge for deploying neural speech codecs in real-world acoustic scenarios where background noise is often inevitable. A key observation we make is that even slight input noise perturbations can cause…
Neural audio compression has emerged as a promising technology for efficiently representing speech, music, and general audio. However, existing methods suffer from significant performance degradation at limited bitrates, where the available…
Building on recent advances in video generation, generative video compression has emerged as a new paradigm for achieving visually pleasing reconstructions. However, existing methods exhibit limited exploitation of temporal correlations,…
Neural video compression (NVC) technologies have advanced rapidly in recent years, yielding state-of-the-art schemes such as DCVC-RT that offer superior compression efficiency to H.266/VVC and real-time encoding/decoding capabilities.…
Neural Radiance Fields (NeRF) have exhibited highly effective performance for photorealistic novel view synthesis recently. However, the key limitation it meets is the reliance on a hand-crafted frequency annealing strategy to recover 3D…
The wide deployment of speech-based biometric systems usually demands high-performance speaker recognition algorithms. However, most of the prior works for speaker recognition either process the speech in the frequency domain or time…
CTC-based ASR systems face computational and memory bottlenecks in resource-limited environments. Traditional CTC decoders, requiring up to 90% of processing time in systems (e.g., wav2vec2-large on L4 GPUs), face inefficiencies due to…
Inspired by the facts that retinal cells actually segregate the visual scene into different attributes (e.g., spatial details, temporal motion) for respective neuronal processing, we propose to first decompose the input video into…
This paper introduces FlowMAC, a novel neural audio codec for high-quality general audio compression at low bit rates based on conditional flow matching (CFM). FlowMAC jointly learns a mel spectrogram encoder, quantizer and decoder. At…
The neural radiance fields (NeRF) have advanced the development of 3D volumetric video technology, but the large data volumes they involve pose significant challenges for storage and transmission. To address these problems, the existing…
Extracting a target source from underdetermined mixtures is challenging for beamforming approaches. Recently proposed time-frequency-bin-wise switching (TFS) and linear combination (TFLC) strategies mitigate this by combining multiple…
Although deep neural networks have facilitated significant progress of neural vocoders in recent years, they usually suffer from intrinsic challenges like opaque modeling, inflexible retraining under different input configurations, and…
Neuroimaging-based prediction methods for intelligence and cognitive abilities have seen a rapid development in literature. Among different neuroimaging modalities, prediction based on functional connectivity (FC) has shown great promise.…
This paper presents a novel algorithm for building an automatic speech recognition (ASR) model with imperfect training data. Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the…
Most speech enhancement algorithms make use of the short-time Fourier transform (STFT), which is a simple and flexible time-frequency decomposition that estimates the short-time spectrum of a signal. However, the duration of short STFT…
Despite a short history, neural image codecs have been shown to surpass classical image codecs in terms of rate-distortion performance. However, most of them suffer from significantly longer decoding times, which hinders the practical…
In this work we propose a novel approach to utilize convolutional neural networks for time series forecasting. The time direction of the sequential data with spatial dimensions $D=1,2$ is considered democratically as the input of a…
Modern video codecs have been extensively optimized to preserve perceptual quality, leveraging models of the human visual system. However, in split inference systems-where intermediate features from neural network are transmitted instead of…
The sequence length along the time axis is often the dominant factor of the computation in speech processing. Works have been proposed to reduce the sequence length for lowering the computational cost in self-supervised speech models.…
Learned image compression has exhibited promising compression performance, but variable bitrates over a wide range remain a challenge. State-of-the-art variable rate methods compromise the loss of model performance and require numerous…