13 papers
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
Wenxi Chen, Dongya Jia, Yushen Chen +11
Recently, diffusion models operating on VAE latents or mel-spectrograms have become the dominant paradigm for zero-shot TTS. Although these compressed representations improve gener…
On the Distillation Loss Functions of Speech VAE for Unified Reconstruction, Understanding, and Generation
Changhao Cheng, Wei Wang, Wangyou Zhang +4
Continuous speech representations based on Variational Autoencoders (VAEs) have emerged as a promising alternative to traditional spectrogram or discrete token based features for s…
DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
Yakun Song, Xiaobin Zhuang, Jiawei Chen +8
Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under d…
Heptapod: Language Modeling on Visual Signals
Yongxin Zhu, Jiawei Chen, Yuanzhe Chen +6
We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs \textbf{causal attention}, \textbf{eliminate…
Direct Preference Optimization for Speech Autoregressive Diffusion Models
Zhijun Liu, Dongya Jia, Xiaoqiang Wang +4
Autoregressive diffusion models (ARDMs) have recently been applied to speech generation, achieving state-of-the-art (SOTA) performance in zero-shot text-to-speech. By autoregressiv…
DreamAudio: Customized Text-to-Audio Generation with Diffusion Models
Yi Yuan, Xubo Liu, Haohe Liu +5
With the development of large-scale diffusion-based and language-modeling-based generative models, impressive progress has been achieved in text-to-audio generation. Despite produc…
Sounding that Object: Interactive Object-Aware Image to Audio Generation
Tingle Li, Baihe Huang, Xiaobin Zhuang +6
Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an {\em inter…
MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation
Yakun Song, Jiawei Chen, Xiaobin Zhuang +9
Neural audio codecs have made significant strides in efficiently mapping raw audio waveforms into discrete token representations, which are foundational for contemporary audio gene…
AudioMorphix: Training-free audio editing with diffusion probabilistic models
Jinhua Liang, Yuanzhe Chen, Yi Yuan +5
Editing sound with precision is a crucial yet underexplored challenge in audio content creation. While existing works can manipulate sounds by text instructions or audio exemplar p…
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
Kai Li, Can Shen, Yile Liu +31
The rapid development and widespread adoption of Audio Large Language Models (ALLMs) demand rigorous evaluation of their trustworthiness. However, existing evaluation frameworks ar…
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
Dongya Jia, Zhuo Chen, Jiawei Chen +8
Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models…
Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions
Yi Yuan, Dongya Jia, Xiaobin Zhuang +9
Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performan…
T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining
Yi Yuan, Zhuo Chen, Xubo Liu +6
Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classificatio…