7 accepted papers
Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric optimization for speech generation components, but duration predict
Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of frames. Existing frame sampling strategies, such as uniform or fixed-budget selection, fail to adapt to variations in con…
Image Aesthetic Assessment (IAA) predicts an image’s overall aesthetic score, yet aesthetic is influenced by multiple attributes whose relative importance varies with image content and usage scenarios. Under end-to-end training with only overall-score supervision, attribute signals are blended, whic…
We propose a semantic priori-guided scalable image coding method for simultaneously supporting fast machine vision analysis and high quality human visual experience. To obtain high-performance machine vision analysis results with a more compact base layer bitrate, our base layer directly encodes int…
Music tagging is the task of predicting multiple tags of a music excerpt, and plays an important role in modern music recommendation systems. To obtain superior performance, recent approaches of music tagging focus on developing sophisticated models or exploiting additional multi-modal information.…
Long short-term memory (LSTM) is normally used in recurrent neural network (RNN) as basic recurrent unit. However, conventional LSTM assumes that the state at current time step depends on previous time step. This assumption constraints the time dependency modeling capability. In this study, we propo…
Employing voice-based emotion recognition function in artificial intelligence (AI) product will improve the user experience. Most of researches that have been done only focus on the speech collected under controlled conditions. The scenarios evaluated in these research were well controlled. The conv…