Buchumschlag

Group Relative Policy Optimization for Text-to-Speech with Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Liu, Chang, Hu, Ya-Jun, Gao, Ying-Ying, Zhang, Shi-Lei, Ling, Zhen-Hua
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Audio and Speech Processing
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Adapting Speech Foundation Models for Unified Multimodal Speech Recognition with Large Language Models
von: Zhang, Jing-Xuan, et al.
Veröffentlicht: (2025)

Group Relative Policy Optimization for Speech Recognition
von: Shivakumar, Prashanth Gurunath, et al.
Veröffentlicht: (2025)

B-GRPO: Unsupervised Speech Emotion Recognition based on Batched-Group Relative Policy Optimization
von: Gao, Yingying, et al.
Veröffentlicht: (2026)

F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization
von: Sun, Xiaohui, et al.
Veröffentlicht: (2025)

Interleaved Speech-Text Language Models for Simple Streaming Text-to-Speech Synthesis
von: Yang, Yifan, et al.
Veröffentlicht: (2024)

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

Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation
von: Gu, Yi, et al.
Veröffentlicht: (2026)

Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis
von: Lu, Ye-Xin, et al.
Veröffentlicht: (2024)

MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra
von: Lu, Ye-Xin, et al.
Veröffentlicht: (2023)

MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech
von: Xia, Kangxiang, et al.
Veröffentlicht: (2025)

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

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
von: Shao, Mingchen, et al.
Veröffentlicht: (2025)

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

Sparsity-Driven EEG Channel Selection for Brain-Assisted Speech Enhancement
von: Zhang, Jie, et al.
Veröffentlicht: (2023)

Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization
von: Wan, Genshun, et al.
Veröffentlicht: (2026)

Clever Hans Effect Found in Automatic Detection of Alzheimer's Disease through Speech
von: Liu, Yin-Long, et al.
Veröffentlicht: (2024)

Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis
von: Liao, Shijia, et al.
Veröffentlicht: (2024)

Rethinking Flow and Diffusion Bridge Models for Speech Enhancement
von: Wang, Dahan, et al.
Veröffentlicht: (2026)

High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model
von: Lee, Joun Yeop, et al.
Veröffentlicht: (2024)

Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining
von: Xue, Jinlong, et al.
Veröffentlicht: (2024)

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

A High-Quality and Low-Complexity Streamable Neural Speech Codec with Knowledge Distillation
von: Zhang, En-Wei, et al.
Veröffentlicht: (2025)

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

Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model
von: Xue, Jinlong, et al.
Veröffentlicht: (2024)

A Survey on Speech Large Language Models for Understanding
von: Peng, Jing, et al.
Veröffentlicht: (2024)

FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech
von: Ma, Linhan, et al.
Veröffentlicht: (2025)

Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model
von: Wang, Siyang, et al.
Veröffentlicht: (2024)

SECodec: Structural Entropy-based Compressive Speech Representation Codec for Speech Language Models
von: Wang, Linqin, et al.
Veröffentlicht: (2024)

Total-Duration-Aware Duration Modeling for Text-to-Speech Systems
von: Eskimez, Sefik Emre, et al.
Veröffentlicht: (2024)

Comprehend and Talk: Text to Speech Synthesis via Dual Language Modeling
von: Cao, Junjie, et al.
Veröffentlicht: (2025)

Beyond Manual Transcripts: The Potential of Automated Speech Recognition Errors in Improving Alzheimer's Disease Detection
von: Liu, Yin-Long, et al.
Veröffentlicht: (2025)

SELM: Speech Enhancement Using Discrete Tokens and Language Models
von: Wang, Ziqian, et al.
Veröffentlicht: (2023)

Text-aware and Context-aware Expressive Audiobook Speech Synthesis
von: Guo, Dake, et al.
Veröffentlicht: (2024)

Ultra-Low-Bitrate Mel-Spectrogram-based Neural Speech Coding with Flow-Matching-based Refinement and Vocoding-driven Reconstruction
von: Du, Hui-Peng, et al.
Veröffentlicht: (2026)

CFMDCTCodec: A Low-Bitrate Neural Speech Codec with Noise-Prior-aware Conditional Flow Matching for MDCT-Spectral Enhancement
von: Jiang, Xiao-Hang, et al.
Veröffentlicht: (2026)

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

VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning
von: Peng, Yifan, et al.
Veröffentlicht: (2024)

CodeSep: Low-Bitrate Codec-Driven Speech Separation with Base-Token Disentanglement and Auxiliary-Token Serial Prediction
von: Du, Hui-Peng, et al.
Veröffentlicht: (2026)

Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis
von: Tu, Zehai, et al.
Veröffentlicht: (2024)

Reasoning Beyond Majority Vote: An Explainable SpeechLM Framework for Speech Emotion Recognition
von: Su, Bo-Hao, et al.
Veröffentlicht: (2025)