Related papers: QINCODEC: Neural Audio Compression with Implicit N…
Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications. Asymptotically optimal channel codes have been developed by mathematicians…
Neural Speech Codecs face a fundamental trade-off at low bitrates: preserving acoustic fidelity often compromises semantic richness. To address this, we introduce SACodec, a novel codec built upon an asymmetric dual-quantizer that employs…
Neural audio/speech coding has recently demonstrated its capability to deliver high quality at much lower bitrates than traditional methods. However, existing neural audio/speech codecs employ either acoustic features or learned blind…
Discrete speech tokenization is a fundamental component in speech codecs. However, in large-scale speech-to-speech systems, the complexity of parallel streams from multiple quantizers and the computational cost of high-time-dimensional…
Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation…
Quantum autoencoders which aim at compressing quantum information in a low-dimensional latent space lie in the heart of automatic data compression in the field of quantum information. In this paper, we establish an upper bound of the…
This paper introduces Associative Compression Networks (ACNs), a new framework for variational autoencoding with neural networks. The system differs from existing variational autoencoders (VAEs) in that the prior distribution used to model…
Vector quantization is a fundamental operation for data compression and vector search. To obtain high accuracy, multi-codebook methods represent each vector using codewords across several codebooks. Residual quantization (RQ) is one such…
Noise reduction is an important part of modern hearing aids and is included in most commercially available devices. Deep learning-based state-of-the-art algorithms, however, either do not consider real-time and frequency resolution…
Neural audio codec models are becoming increasingly important as they serve as tokenizers for audio, enabling efficient transmission or facilitating speech language modeling. The ideal neural audio codec should maintain content,…
Audio codecs power discrete music generative modelling, music streaming and immersive media by shrinking PCM audio to bandwidth-friendly bit-rates. Recent works have gravitated towards processing in the spectral domain; however,…
Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs…
Recent advancements in audio generation have been significantly propelled by the capabilities of Large Language Models (LLMs). The existing research on audio LLM has primarily focused on enhancing the architecture and scale of audio…
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 recent years, machine learning and deep learning have driven advances in domains such as image classification, speech recognition, and anomaly detection by leveraging multi-layer neural networks to model complex data. Simultaneously,…
A popular approach to learning encoders for lossy compression is to use additive uniform noise during training as a differentiable approximation to test-time quantization. We demonstrate that a uniform noise channel can also be implemented…
We present PECMAE, an interpretable model for music audio classification based on prototype learning. Our model is based on a previous method, APNet, which jointly learns an autoencoder and a prototypical network. Instead, we propose to…
In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serve as an…
Neural speech codecs have achieved strong performance in low-bitrate compression, but residual vector quantization (RVQ) often suffers from unstable training and ineffective decomposition, limiting reconstruction quality and efficiency. We…
Signal compression based on implicit neural representation (INR) is an emerging technique to represent multimedia signals with a small number of bits. While INR-based signal compression achieves high-quality reconstruction for relatively…