Related papers: FreGrad: Lightweight and Fast Frequency-aware Diff…

Deep learning-based speech enhancement (SE) models have recently outperformed traditional techniques, yet their deployment on resource-constrained devices remains challenging due to high computational and memory demands. This paper…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however…

Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing them from mono audio has attracted increasing attention. This…

Recent advances in diffusion models have positioned them as powerful generative frameworks for speech synthesis, demonstrating substantial improvements in audio quality and stability. Nevertheless, their effectiveness in vocoders…

Frequency estimation from measurements corrupted by noise is a fundamental challenge across numerous engineering and scientific fields. Among the pivotal factors shaping the resolution capacity of any frequency estimation technique are…

In this paper, we propose a technique to alleviate the quality degradation caused by collapsed speech segments sometimes generated by the WaveNet vocoder. The effectiveness of the WaveNet vocoder for generating natural speech from acoustic…

Inspired by the success of deep neural networks (DNNs) in speech processing, this paper presents Deep Vocoder, a direct end-to-end low bit rate speech compression method with deep autoencoder (DAE). In Deep Vocoder, DAE is used for…

Diffusion Transformers achieve impressive generative quality but remain computationally expensive due to iterative sampling. Recently, dynamic resolution sampling has emerged as a promising acceleration technique by reducing the resolution…

Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling the generative process using highly compact conditioning signals. In this work,…

Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data…

Communication efficiency is a widely recognised research problem in Federated Learning (FL), with recent work focused on developing techniques for efficient compression, distribution and aggregation of model parameters between clients and…

The rapid advancement of generative models has led to the synthesis of real-fake ambiguous voices. To erase the ambiguity, embedding watermarks into the frequency-domain features of synthesized voices has become a common routine. However,…

Diffusion models exhibit impressive generative capabilities but are significantly impacted by exposure bias. In this paper, we make a key observation: the energy of predicted noisy samples in the reverse process continuously declines…

Recently, BigVGAN has emerged as high-performance speech vocoder. Its sequence-to-sequence-based synthesis, however, prohibits usage in low-latency conversational applications. Our work addresses this shortcoming in three steps. First, we…

Properly setting up recording conditions, including microphone type and placement, room acoustics, and ambient noise, is essential to obtaining the desired acoustic characteristics of speech. In this paper, we propose Diff-R-EN-T, a…

Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods…

Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized…

Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the…

Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time…