相关论文: HiFi-Codec: Group-residual Vector quantization for…

Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited resources. As an efficient model compression technique, vector quantization (VQ) excels in…

This paper presents PhoenixCodec, a comprehensive neural speech coding and decoding framework designed for extremely low-resource conditions. The proposed system integrates an optimized asymmetric frequency-time architecture, a Cyclical…

Language models have been successfully used to model natural signals, such as images, speech, and music. A key component of these models is a high quality neural compression model that can compress high-dimensional natural signals into…

The application of generative adversarial networks (GANs) has recently advanced speech super-resolution (SR) based on intermediate representations like mel-spectrograms. However, existing SR methods that typically rely on independently…

Neural audio codecs are widely used as tokenizers for spoken language models, but they are optimized for waveform reconstruction rather than autoregressive prediction. This mismatch injects acoustically driven uncertainty into the discrete…

In order to efficiently transmit and store speech signals, speech codecs create a minimally redundant representation of the input signal which is then decoded at the receiver with the best possible perceptual quality. In this work we…

Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resort to explicit vectorization using intrinsics, as…

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity…

The video technology scenery has been very vivid over the past years, with novel video coding technologies introduced that promise improved compression performance over state-of-the-art technologies. Despite the fact that a lot of video…

As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs. To mitigate these…

Discrete Audio codecs (or audio tokenizers) have recently regained interest due to the ability of Large Language Models (LLMs) to learn their compressed acoustic representations. Various publicly available trainable discrete tokenizers…

We propose a method named AudioFormer,which learns audio feature representations through the acquisition of discrete acoustic codes and subsequently fine-tunes them for audio classification tasks. Initially,we introduce a novel perspective…

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the quantization strategy for better reconstruction quality,…

Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long contexts. We present Hierarchical Embedding Fusion (HEF), a…

This paper presents LongCat-Audio-Codec, an audio tokenizer and detokenizer solution designed for industrial grade end-to-end speech large language models. By leveraging a decoupled model architecture and a multistage training strategy,…

Recent advancements in end-to-end neural speech codecs enable compressing audio at extremely low bitrates while maintaining high-fidelity reconstruction. Meanwhile, low computational complexity and low latency are crucial for real-time…

At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Generative Video Codebook Codec (GVCC), a zero-shot framework in…

Neural Audio Codecs (NACs) can reduce transmission overhead by performing compact compression and reconstruction, which also aim to bridge the gap between continuous and discrete signals. Existing NACs can be divided into two categories:…

Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation…

We introduce LMCodec, a causal neural speech codec that provides high quality audio at very low bitrates. The backbone of the system is a causal convolutional codec that encodes audio into a hierarchy of coarse-to-fine tokens using residual…