7 papers
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
Haoran Wang, Jinchuan Tian, Siddhant Arora +1
While Large Multimodal Models excel in comprehension, high-throughput inference engines lack native support for multimodal generation. This is severe in Speech Language Models, whe…
Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis
Jinchuan Tian, Haoran Wang, Siddhant Arora +6
Classical TTS systems typically rely on rigid input formats and predefined metadata slots, limiting their ability to fulfill flexible user requirements. This paper introduces Bagpi…
Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
Jinchuan Tian, Haoran Wang, Bo-Hao Su +14
Current audio foundation models typically rely on rigid, task-specific supervision (e.g., speech recognition), addressing isolated factors of audio rather than the whole. In contra…
Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization
Junxiong Lin, Xinji Mai, Qianyu Guo +5
Fidelity and perceptual quality are two inherently competing and conflicting objectives in the image super-resolution (SR) task. Different loss functions focus on these objectives…
Customizing Video Portraits via Identity-ActionDecoupling
Junxiong Lin, Haoran Wang, Xinji Mai +4
Identity-Preserving Text-to-Video Generation (IPT2V) seeks to synthesize a temporally coherent video from a reference image and a textual description, while simultaneously preservi…
Bagpiper-Edit: Zero-Shot Open-Ended Audio Editing via Rich-Caption
Xun Gong, Jinchuan Tian, Haoran Wang +3
Current text-guided audio editing methods rely on paired training data, predefined operation templates, and separate processing pipelines across speech, music, and sound. We presen…