Imagen de Portada

Eliminating stability hallucinations in llm-based tts models via attention guidance

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, ShiMing, Du, ZhiHao, Xiang, Yang, Zhao, TianYu, Zhao, Han, Chen, Qian, Li, XianGang, Guo, HanJie, Ling, ZhenHua
Formato:	Preprint
Publicado:	2025
Materias:	Sound Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Neural Speech Separation with Parallel Amplitude and Phase Spectrum Estimation
por: Liu, Fei, et al.
Publicado: (2025)

UniVocal: Unified Speech-Singing Code-Switching Synthesis
por: Shi, Yufei, et al.
Publicado: (2026)

LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matching
por: Liu, Fei, et al.
Publicado: (2026)

Low-Latency Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Losses for Speech Generation Tasks
por: Ai, Yang, et al.
Publicado: (2024)

Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval
por: Wang, Qian, et al.
Publicado: (2024)

Universal Discrete-Domain Speech Enhancement
por: Liu, Fei, et al.
Publicado: (2025)

BiVocoder: A Bidirectional Neural Vocoder Integrating Feature Extraction and Waveform Generation
por: Du, Hui-Peng, et al.
Publicado: (2024)

APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm
por: Du, Hui-Peng, et al.
Publicado: (2024)

Resnet-conformer network with shared weights and attention mechanism for sound event localization, detection, and distance estimation
por: Vo, Quoc Thinh, et al.
Publicado: (2025)

Omni-directional attention mechanism based on Mamba for speech separation
por: Xue, Ke, et al.
Publicado: (2026)

A Streamable Neural Audio Codec with Residual Scalar-Vector Quantization for Real-Time Communication
por: Jiang, Xiao-Hang, et al.
Publicado: (2025)

Cross-attention and Self-attention for Audio-visual Speaker Diarization in MISP-Meeting Challenge
por: Li, Zhaoyang, et al.
Publicado: (2025)

Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising
por: Lu, Ye-Xin, et al.
Publicado: (2025)

We Can Hear You with mmWave Radar! An End-to-End Eavesdropping System
por: Han, Dachao, et al.
Publicado: (2025)

Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement
por: Lu, Ye-Xin, et al.
Publicado: (2023)

Universal Preference-Score-based Pairwise Speech Quality Assessment
por: Shi, Yu-Fei, et al.
Publicado: (2025)

EnchantDance: Unveiling the Potential of Music-Driven Dance Movement
por: Han, Bo, et al.
Publicado: (2023)

Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction
por: Lu, Ye-Xin, et al.
Publicado: (2024)

Unispeaker: A Unified Approach for Multimodality-driven Speaker Generation
por: Sheng, Zhengyan, et al.
Publicado: (2025)

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features
por: Shi, Yu-Fei, et al.
Publicado: (2024)

ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram
por: Jiang, Xiao-Hang, et al.
Publicado: (2024)

Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion
por: Shi, Yu-Fei, et al.
Publicado: (2024)

APCodec: A Neural Audio Codec with Parallel Amplitude and Phase Spectrum Encoding and Decoding
por: Ai, Yang, et al.
Publicado: (2024)

Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning
por: Zhao, Siyi, et al.
Publicado: (2025)

DAIEN-TTS: Disentangled Audio Infilling for Environment-Aware Text-to-Speech Synthesis
por: Lu, Ye-Xin, et al.
Publicado: (2025)

Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding
por: Zheng, Rui-Chen, et al.
Publicado: (2025)

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS
por: Wang, Cong, et al.
Publicado: (2025)

From Coarse to Fine: Recursive Audio-Visual Semantic Enhancement for Speech Separation
por: Xue, Ke, et al.
Publicado: (2025)

WTFormer: A Wavelet Conformer Network for MIMO Speech Enhancement with Spatial Cues Peservation
por: Han, Lu, et al.
Publicado: (2025)

Vision-Integrated High-Quality Neural Speech Coding
por: Guo, Yao, et al.
Publicado: (2025)

Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models
por: Zhang, Jing-Xuan, et al.
Publicado: (2025)

Knowledge-Decoupled Functionally Invariant Path with Synthetic Personal Data for Personalized ASR
por: Gu, Yue, et al.
Publicado: (2025)

The First Voice Timbre Attribute Detection Challenge
por: Chen, Liping, et al.
Publicado: (2025)

AudioFab: Building A General and Intelligent Audio Factory through Tool Learning
por: Zhu, Cheng, et al.
Publicado: (2025)

Decoding Speaker-Normalized Pitch from EEG for Mandarin Perception
por: Chen, Jiaxin, et al.
Publicado: (2025)

MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios
por: Jiang, Xiao-Hang, et al.
Publicado: (2024)

Leveraging Prompt Learning and Pause Encoding for Alzheimer's Disease Detection
por: Liu, Yin-Long, et al.
Publicado: (2024)

Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Control
por: Lu, Ye-Xin, et al.
Publicado: (2024)

CartoonSing: Unifying Human and Nonhuman Timbres in Singing Generation
por: Han, Jionghao, et al.
Publicado: (2025)

Adapting Speech Language Model to Singing Voice Synthesis
por: Zhao, Yiwen, et al.
Publicado: (2025)