10 papers
Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards
Yong Ren, Jiangyan Yi, Jianhua Tao +3
Imperceptible text-based speech editing modifies spoken content through transcript manipulation while preserving acoustic continuity. Prior acoustic-space approaches suffer from co…
OV-InstructTTS: Towards Open-Vocabulary Instruct Text-to-Speech
Yong Ren, Jiangyan Yi, Jianhua Tao +5
Instruct Text-to-Speech (InstructTTS) leverages natural language descriptions as style prompts to guide speech synthesis. However, existing InstructTTS methods mainly rely on a dir…
ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection
Hao Gu, Jiangyan Yi, Chenglong Wang +6
Audio deepfake detection (ADD) has grown increasingly important due to the rise of high-fidelity audio generative models and their potential for misuse. Given that audio large lang…
AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
Zheng Lian, Haoyu Chen, Lan Chen +9
The emergence of multimodal large language models (MLLMs) advances multimodal emotion recognition (MER) to the next level, from naive discriminative tasks to complex emotion unders…
P2Mark: Plug-and-play Parameter-level Watermarking for Neural Speech Generation
Yong Ren, Jiangyan Yi, Tao Wang +7
Neural speech generation (NSG) has rapidly advanced as a key component of artificial intelligence-generated content, enabling the generation of high-quality, highly realistic speec…
WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification
Junzuo Zhou, Jiangyan Yi, Yong Ren +3
Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before co…