相关论文: Neural Feature Predictor and Discriminative Residu…

In this paper, we investigate the use of prediction-adaptation-correction recurrent neural networks (PAC-RNNs) for low-resource speech recognition. A PAC-RNN is comprised of a pair of neural networks in which a {\it correction} network uses…

Despite being the best known objective for learning speech representations, the HuBERT objective has not been further developed and improved. We argue that it is the lack of an underlying principle that stalls the development, and, in this…

The quality of speech codecs deteriorates at low bitrates due to high quantization noise. A post-filter is generally employed to enhance the quality of the coded speech. In this paper, a data-driven post-filter relying on masking in the…

In this work, we propose a new recurrent autoencoder architecture, termed Feedback Recurrent AutoEncoder (FRAE), for online compression of sequential data with temporal dependency. The recurrent structure of FRAE is designed to efficiently…

Neural speech codecs have been widely used in audio compression and various downstream tasks. Current mainstream codecs are fixed-frame-rate (FFR), which allocate the same number of tokens to every equal-duration slice. However, speech is…

Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or…

We present a lightweight adaptable neural TTS system with high quality output. The system is composed of three separate neural network blocks: prosody prediction, acoustic feature prediction and Linear Prediction Coding Net as a neural…

We introduce Noise Recycling, a method that substantially enhances decoding performance of orthogonal channels subject to correlated noise without the need for joint encoding or decoding. The method can be used with any combination of…

Long short-term memory (LSTM) recurrent neural networks (RNNs) have been shown to give state-of-the-art performance on many speech recognition tasks, as they are able to provide the learned dynamically changing contextual window of all…

Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded promising results. Existing methods using a single-scale…

Predictive coding is an influential model of cortical neural activity. It proposes that perceptual beliefs are furnished by sequentially minimising "prediction errors" - the differences between predicted and observed data. Implicit in this…

Intra prediction is an important component of modern video codecs, which is able to efficiently squeeze out the spatial redundancy in video frames. With preceding pixels as the context, traditional intra prediction schemes generate linear…

We introduce Noise Recycling, a method that enhances decoding performance of channels subject to correlated noise without joint decoding. The method can be used with any combination of codes, code-rates and decoding techniques. In the…

We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters. The system has an associative memory based on complex-valued vectors and is closely related to…

Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, following a semantic-modeling and acoustic-synthesis paradigm.…

Inspired by "predictive coding" - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural…

Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural…

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…

Despite the advancements in cutting-edge technologies, audio signal processing continues to pose challenges and lacks the precision of a human speech processing system. To address these challenges, we propose a novel approach to simplify…

LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of existing methods. To…