15 accepted papers
Real-world speech recordings suffer from degradations such as background noise and reverberation. Speech enhancement aims to mitigate these issues by generating clean high-fidelity signals. While recent generative approaches for speech enhancement have shown promising results, they still face two ma…
Blind room impulse response (RIR) estimation is a core task for capturing and transferring acoustic properties; yet existing methods often suffer from limited modeling capability and degraded performance under unseen conditions. Moreover, emerging generative audio applications call for more flexible…
While generative Text-to-Speech (TTS) systems leverage vast "in-the-wild" data to achieve remarkable success, speech-to-speech processing tasks like enhancement face data limitations, which lead data-hungry generative approaches to distort speech content and speaker identity. To bridge this gap, we…
As large-scale multi-agent systems evolve, the communication protocol layer has become a critical, yet understudied, component affecting system performance and reliability. Despite a range of protocols, such as JSON-RPC, A2A, ANP, and ACP, protocol selection remains ad hoc. To address this, we intro…
End-to-end (E2E) autonomous driving (AD) models require diverse, high-quality data to perform well across various driving scenarios. However, collecting large-scale real-world data is expensive and time-consuming, making high-fidelity synthetic data essential for enhancing data diversity and model r…
Research in generative self-supervised learning (SSL) has largely focused on local embeddings for tokenized sequences. We introduce a generative SSL framework that learns a global representation that is disentangled from local embeddings. We apply this technique to jointly learn a global speaker emb…
As a cross-modal task, visual storytelling aims to generate a semantically coherent story for an ordered image sequence. Despite significant achievements in existing methods for this task, few works focus on improving the conception ability which humans usually use when writing stories. In this work…
Audio source separation aims to extract individual sound sources from an audio mixture. Recent studies on source separation focus primarily on minimizing signal-level distance, typically measured by source-to-distortion ratio (SDR). However, scant attention has been given to the perceptual quality o…
High-quality speech synthesis models may be used to spread misinformation or impersonate voices. Audio watermarking can combat misuse by embedding a traceable signature in generated audio. However, existing audio watermarks typically demonstrate robustness to only a small set of transformations of t…
As a cross-modal task, visual storytelling aims to generate a story for an ordered image sequence automatically. Different from the image captioning task, visual storytelling requires not only modeling the relationships between objects in the image but also mining the connections between adjacent im…
Speech representation learning transforms speech into features that are suitable for downstream tasks, e.g. speech recognition, phoneme classification, or speaker identification. For such recognition tasks, a representation can be lossy (non-invertible), which is typical of BERT-like self-supervised…
Speech generation and enhancement have seen recent breakthroughs in quality thanks to deep learning. These methods typically operate at a limited sampling rate of 16-22kHz due to computational complexity and available datasets. This limitation imposes a gap between the output of such methods and tha…
The goal of acoustic matching is to transform an audio recording made in one acoustic environment to sound as if it had been recorded in a different environment, based on reference audio from the target environment. This paper introduces a deep learning solution for two parts of the acoustic matchin…
We introduce a perceptually motivated approach to bandwidth expansion for speech. Our method pairs a new 3-way split variant of the FFTNet neural vocoder structure with a perceptual loss function, combining objectives from both the time and frequency domains. Mean opinion score tests show that it ou…
This paper introduces a deep learning approach to enhance speech recordings made in a specific environment. A single neural network learns to ameliorate several types of recording artifacts, including noise, reverberation, and non-linear equalization. The method relies on a new perceptual loss funct…