相关论文: MSR-NV: Neural Vocoder Using Multiple Sampling Rat…

We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images,…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

Diffusion models have become emerging generative models. Their sampling process involves multiple steps, and in each step the models predict the noise from a noisy sample. When the models make prediction, the output deviates from the ground…

Vector quantization-based image semantic communication systems have successfully boosted transmission efficiency, but face challenges with conflicting requirements between codebook design and digital constellation modulation. Traditional…

Maximum Voiced Frequency (MVF) is used in various speech models as the spectral boundary separating periodic and aperiodic components during the production of voiced sounds. Recent studies have shown that its proper estimation and modeling…

It is desirable for a text-to-speech system to take into account the environment where synthetic speech is presented, and provide appropriate context-dependent output to the user. In this paper, we present and compare various approaches for…

In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models. Therefore mixed-bandwidth (MB) acoustic modeling has important practical values…

Representing a signal as a continuous function parameterized by neural network (a.k.a. Implicit Neural Representations, INRs) has attracted increasing attention in recent years. Neural Processes (NPs), which model the distributions over…

We provide a speech coding scheme employing a generative model based on SampleRNN that, while operating at significantly lower bitrates, matches or surpasses the perceptual quality of state-of-the-art classic wide-band codecs. Moreover, it…

Image super-resolution research recently been dominated by transformer models which need higher computational resources than CNNs due to the quadratic complexity of self-attention. We propose a new neural network -- WaveMixSR -- for image…

Speech restoration aims at restoring high quality speech in the presence of a diverse set of distortions. Although several deep learning paradigms have been studied for this task, the power of the recently emerging language models has not…

There are two types of methods for non-autoregressive text-to-speech models to learn the one-to-many relationship between text and speech effectively. The first one is to use an advanced generative framework such as normalizing flow (NF).…

This paper presents a new neural speech compression method that is practical in the sense that it operates at low bitrate, introduces a low latency, is compatible in computational complexity with current mobile devices, and provides a…

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…

Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations.…

A novel approach for speech segmentation is proposed, based on Multilevel Hybrid (mean/min) Filters (MHF) with the following features: An accurate transition location. Good performance in noisy environments (gaussian and impulsive noise).…

Voice conversion has gained increasing popularity within the field of audio manipulation and speech synthesis. Often, the main objective is to transfer the input identity to that of a target speaker without changing its linguistic content.…

Automatic speaker verification (ASV) is the process to recognize persons using voice as biometric. The ASV systems show considerable recognition performance with sufficient amount of speech from matched condition. One of the crucial…

A typical neural speech enhancement (SE) approach mainly handles speech and noise mixtures, which is not optimal for singing voice enhancement scenarios. Music source separation (MSS) models treat vocals and various accompaniment components…