Related papers: High-Fidelity Generative Audio Compression at 0.27…
Large Language Models (LLMs) have significantly advanced audio processing by leveraging audio codecs to discretize audio into tokens, enabling the application of language modeling techniques to speech data. However, existing audio codecs…
Recently, AI-generated content (AIGC) has gained significant traction due to its powerful creation capability. However, the storage and transmission of large amounts of high-quality AIGC images inevitably pose new challenges for recent file…
Building on recent advances in video generation, generative video compression has emerged as a new paradigm for achieving visually pleasing reconstructions. However, existing methods exhibit limited exploitation of temporal correlations,…
Neural audio codecs (NACs) typically encode the short-term energy (gain) and normalized structure (shape) of speech/audio signals jointly within the same latent space. As a result, they are poorly robust to a global variation of the input…
Real-world speech communication is rarely affected by a single type of degradation. Instead, it suffers from a complex interplay of acoustic interference, codec compression, and, increasingly, secondary artifacts introduced by upstream…
The rapid progress in large language models (LLMs) has paved the way for novel approaches in knowledge-intensive tasks. Among these, Cache-Augmented Generation (CAG) has emerged as a promising alternative to Retrieval-Augmented Generation…
Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression, yet maintaining naturalness and speaker identity at such extreme bit budgets remains challenging due to pronounced information loss and…
Privacy and security have rapidly emerged as priorities in system design. One powerful solution for providing both is privacy-preserving computation, where functions are computed directly on encrypted data and control can be provided over…
We introduce EGIC, an enhanced generative image compression method that allows traversing the distortion-perception curve efficiently from a single model. EGIC is based on two novel building blocks: i) OASIS-C, a conditional pre-trained…
Neural speech codecs aim to compress input signals into minimal bits while maintaining content quality in a low-latency manner. However, existing neural codecs often trade model complexity for reconstruction performance. These codecs…
Conditional waveform synthesis models learn a distribution of audio waveforms given conditioning such as text, mel-spectrograms, or MIDI. These systems employ deep generative models that model the waveform via either sequential…
Our previous work, the unified source-filter GAN (uSFGAN) vocoder, introduced a novel architecture based on the source-filter theory into the parallel waveform generative adversarial network to achieve high voice quality and pitch…
High-efficiency absorption of low-frequency sounds (< 1000 Hz) while maintaining a free flow of fluids remains a significant challenge in acoustical engineering due to the rigid trade-off between absorption and ventilation performances.…
End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we…
Modern generative and multimodal models increasingly rely on compact latent representations that trade and balance semantic richness with high-fidelity reconstruction. We introduce SALAD-VAE, a continuous and highly compact semantic Audio…
Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence. Autoregressive models, such as WaveNet, model local structure at the…
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and…
Text-to-audio (TTA) generation can significantly benefit the media industry by reducing production costs and enhancing work efficiency. However, most current TTA models (primarily diffusion-based) suffer from slow inference speeds and high…
Conditional Generative Adversarial Networks (cGANs) have enabled controllable image synthesis for many vision and graphics applications. However, recent cGANs are 1-2 orders of magnitude more compute-intensive than modern recognition CNNs.…
Despite significant advancements in traditional syntactic communications based on Shannon's theory, these methods struggle to meet the requirements of 6G immersive communications, especially under challenging transmission conditions. With…