Copertina

Direct Preference Optimization for Speech Autoregressive Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Zhijun, Jia, Dongya, Wang, Xiaoqiang, Du, Chenpeng, Wang, Shuai, Chen, Zhuo, Li, Haizhou
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
di: Song, Yakun, et al.
Pubblicazione: (2025)

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
di: Jia, Dongya, et al.
Pubblicazione: (2025)

Autoregressive Diffusion Transformer for Text-to-Speech Synthesis
di: Liu, Zhijun, et al.
Pubblicazione: (2024)

E1 TTS: Simple and Fast Non-Autoregressive TTS
di: Liu, Zhijun, et al.
Pubblicazione: (2024)

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
di: Du, Chenpeng, et al.
Pubblicazione: (2023)

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms
di: Li, Sirui, et al.
Pubblicazione: (2025)

Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis
di: Du, Chenpeng, et al.
Pubblicazione: (2021)

Attention-Constrained Inference for Robust Decoder-Only Text-to-Speech
di: Wang, Hankun, et al.
Pubblicazione: (2024)

SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
di: Yang, Chenyu, et al.
Pubblicazione: (2025)

Hierarchical Control of Emotion Rendering in Speech Synthesis
di: Inoue, Sho, et al.
Pubblicazione: (2024)

Hierarchical Emotion Prediction and Control in Text-to-Speech Synthesis
di: Inoue, Sho, et al.
Pubblicazione: (2024)

Fine-Grained Quantitative Emotion Editing for Speech Generation
di: Inoue, Sho, et al.
Pubblicazione: (2024)

Multi-Step Prediction and Control of Hierarchical Emotion Distribution in Text-to-Speech Synthesis
di: Inoue, Sho, et al.
Pubblicazione: (2025)

VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature
di: Du, Chenpeng, et al.
Pubblicazione: (2022)

VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech
di: Du, Chenpeng, et al.
Pubblicazione: (2024)

Acoustic BPE for Speech Generation with Discrete Tokens
di: Shen, Feiyu, et al.
Pubblicazione: (2023)

Context-Aware Two-Step Training Scheme for Domain Invariant Speech Separation
di: Wang, Wupeng, et al.
Pubblicazione: (2025)

Data Augmentation for End-to-end Code-switching Speech Recognition
di: Du, Chenpeng, et al.
Pubblicazione: (2020)

AudioMorphix: Training-free audio editing with diffusion probabilistic models
di: Liang, Jinhua, et al.
Pubblicazione: (2025)

The X-LANCE Technical Report for Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge
di: Guo, Yiwei, et al.
Pubblicazione: (2024)

MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion
di: Inoue, Sho, et al.
Pubblicazione: (2024)

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis
di: Wang, Huimeng, et al.
Pubblicazione: (2026)

Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study
di: Zhang, Qiquan, et al.
Pubblicazione: (2025)

A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognition
di: Guo, Zilu, et al.
Pubblicazione: (2024)

M-Vec: Matryoshka Speaker Embeddings with Flexible Dimensions
di: Wang, Shuai, et al.
Pubblicazione: (2024)

Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment
di: Zhang, Xueyao, et al.
Pubblicazione: (2025)

Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective
di: Wang, Hankun, et al.
Pubblicazione: (2024)

LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec
di: Guo, Yiwei, et al.
Pubblicazione: (2024)

Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization
di: Gao, Xiaoxue, et al.
Pubblicazione: (2024)

PhiNet: Speaker Verification with Phonetic Interpretability
di: Ma, Yi, et al.
Pubblicazione: (2026)

UniTalker: Conversational Speech-Visual Synthesis
di: Hu, Yifan, et al.
Pubblicazione: (2025)

Controllable Accent Normalization via Discrete Diffusion
di: Bai, Qibing, et al.
Pubblicazione: (2026)

Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation
di: Wang, Wupeng, et al.
Pubblicazione: (2025)

Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning
di: Wang, Shuai, et al.
Pubblicazione: (2024)

Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives
di: Liu, Hexin, et al.
Pubblicazione: (2025)

S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models
di: Jiang, Feng, et al.
Pubblicazione: (2025)

Speech Separation with Pretrained Frontend to Minimize Domain Mismatch
di: Wang, Wupeng, et al.
Pubblicazione: (2024)

Exploring Length Generalization For Transformer-based Speech Enhancement
di: Zhang, Qiquan, et al.
Pubblicazione: (2025)

An Exploration of Length Generalization in Transformer-Based Speech Enhancement
di: Zhang, Qiquan, et al.
Pubblicazione: (2024)

Parallel Synthesis for Autoregressive Speech Generation
di: Hsu, Po-chun, et al.
Pubblicazione: (2022)