Copertina

Llasa+: Free Lunch for Accelerated and Streaming Llama-Based Speech Synthesis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tian, Wenjie, Zhu, Xinfa, Xie, Hanke, Ye, Zhen, Xue, Wei, Xie, Lei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Sound Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
di: Ye, Zhen, et al.
Pubblicazione: (2025)

DialoSpeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching
di: Xie, Hanke, et al.
Pubblicazione: (2025)

KALL-E:Autoregressive Speech Synthesis with Next-Distribution Prediction
di: Xia, Kangxiang, et al.
Pubblicazione: (2024)

Boosting Multi-Speaker Expressive Speech Synthesis with Semi-supervised Contrastive Learning
di: Zhu, Xinfa, et al.
Pubblicazione: (2023)

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

DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis
di: Tian, Wenjie, et al.
Pubblicazione: (2025)

FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter
di: Lv, Yuanjun, et al.
Pubblicazione: (2024)

U-SAM: An audio language Model for Unified Speech, Audio, and Music Understanding
di: Wang, Ziqian, et al.
Pubblicazione: (2025)

CosyAudio: Improving Audio Generation with Confidence Scores and Synthetic Captions
di: Zhu, Xinfa, et al.
Pubblicazione: (2025)

Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought
di: Zhao, Zhixian, et al.
Pubblicazione: (2025)

SponTTS: modeling and transferring spontaneous style for TTS
di: Li, Hanzhao, et al.
Pubblicazione: (2023)

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
di: Wang, Xinsheng, et al.
Pubblicazione: (2025)

SoCodec: A Semantic-Ordered Multi-Stream Speech Codec for Efficient Language Model Based Text-to-Speech Synthesis
di: Guo, Haohan, et al.
Pubblicazione: (2024)

Accent-VITS:accent transfer for end-to-end TTS
di: Ma, Linhan, et al.
Pubblicazione: (2023)

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

Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study
di: Chen, Peikun, et al.
Pubblicazione: (2024)

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding
di: Guo, Dake, et al.
Pubblicazione: (2025)

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
di: Tian, Wenjie, et al.
Pubblicazione: (2026)

MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow
di: Zhu, Yike, et al.
Pubblicazione: (2025)

ZSVC: Zero-shot Style Voice Conversion with Disentangled Latent Diffusion Models and Adversarial Training
di: Zhu, Xinfa, et al.
Pubblicazione: (2025)

MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech
di: Chen, Huakang, et al.
Pubblicazione: (2026)

Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR
di: Shao, Mingchen, et al.
Pubblicazione: (2025)

Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy
di: Ma, Linhan, et al.
Pubblicazione: (2024)

Towards Expressive Zero-Shot Speech Synthesis with Hierarchical Prosody Modeling
di: Jiang, Yuepeng, et al.
Pubblicazione: (2024)

Seeing the Context: Rich Visual Context-Aware Speech Recognition via Multimodal Reasoning
di: Tian, Wenjie, et al.
Pubblicazione: (2026)

FleSpeech: Flexibly Controllable Speech Generation with Various Prompts
di: Li, Hanzhao, et al.
Pubblicazione: (2025)

DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion
di: Ning, Ziqian, et al.
Pubblicazione: (2023)

StreamVoice+: Evolving into End-to-end Streaming Zero-shot Voice Conversion
di: Wang, Zhichao, et al.
Pubblicazione: (2024)

Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
di: Zheng, Qixi, et al.
Pubblicazione: (2025)

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
di: Xue, Hongfei, et al.
Pubblicazione: (2025)

CoDiff-VC: A Codec-Assisted Diffusion Model for Zero-shot Voice Conversion
di: Li, Yuke, et al.
Pubblicazione: (2024)

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition
di: Mu, Bingshen, et al.
Pubblicazione: (2025)

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

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
di: Li, Longhao, et al.
Pubblicazione: (2025)

Adaptive Data Augmentation with NaturalSpeech3 for Far-field Speaker Verification
di: Zhang, Li, et al.
Pubblicazione: (2025)

Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text
di: Xue, Hongfei, et al.
Pubblicazione: (2024)

LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation
di: Luong, Hieu-Thi, et al.
Pubblicazione: (2024)

YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance
di: Hao, Chunbo, et al.
Pubblicazione: (2026)

Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning
di: Xue, Hongfei, et al.
Pubblicazione: (2025)

SynthVC: Leveraging Synthetic Data for End-to-End Low Latency Streaming Voice Conversion
di: Guo, Zhao, et al.
Pubblicazione: (2025)