Related papers: Toward Complex-Valued Neural Networks for Waveform…

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…

Emotional voice conversion (EVC) is one way to generate expressive synthetic speech. Previous approaches mainly focused on modeling one-to-one mapping, i.e., conversion from one emotional state to another emotional state, with Mel-cepstral…

Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…

In this paper, we propose a novel conditional convolution network, named location-variable convolution, to model the dependencies of the waveform sequence. Different from the use of unified convolution kernels in WaveNet to capture the…

Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck…

Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, such as identifying and segmenting a singing person in a…

Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model, WaveNet is limited by a slow sequential waveform generation…

Predictive simulation of vibrational spectra of complex condensed-phase and interface systems with thousands of degrees of freedom has long been a challenging task of modern condensed matter theory. In this work, fourth-generation…

For articulatory-to-acoustic mapping using deep neural networks, typically spectral and excitation parameters of vocoders have been used as the training targets. However, vocoding often results in buzzy and muffled final speech quality.…

Complex-valued processing brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the noise reduction process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram. Complex…

Neural speech synthesis algorithms are a promising new approach for coding speech at very low bitrate. They have so far demonstrated quality that far exceeds traditional vocoders, at the cost of very high complexity. In this work, we…

With the achievements of Transformer in the field of natural language processing, the encoder-decoder and the attention mechanism in Transformer have been applied to computer vision. Recently, in multiple tasks of computer vision (image…

Deep learning methods for perception are the cornerstone of many robotic systems. Despite their potential for impressive performance, obtaining real-world training data is expensive, and can be impractically difficult for some tasks.…

This paper proposes a spectral-domain perceptual weighting technique for Parallel WaveGAN-based text-to-speech (TTS) systems. The recently proposed Parallel WaveGAN vocoder successfully generates waveform sequences using a fast…

This paper proposes a convolutional neural network that can fuse high-level prior for semantic image segmentation. Motivated by humans' vision recognition system, our key design is a three-layer generative structure consisting of high-level…

Recent advances in deep learning have facilitated the design of speaker verification systems that directly input raw waveforms. For example, RawNet extracts speaker embeddings from raw waveforms, which simplifies the process pipeline and…

Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in…

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from…

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we…

Speech separation models are used for isolating individual speakers in many speech processing applications. Deep learning models have been shown to lead to state-of-the-art (SOTA) results on a number of speech separation benchmarks. One…