Cover Image

Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Bohan, Li, Zhihan, Wang, Haoran, Zhang, Hanglei, Guo, Yiwei, Wang, Hankun, Chen, Xie, Yu, Kai
Format:	Preprint
Published:	2025
Subjects:	Sound Computation and Language Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency
by: Wang, Haoran, et al.
Published: (2025)

CodecSlime: Temporal Redundancy Compression of Neural Speech Codec via Dynamic Frame Rate
by: Wang, Hankun, et al.
Published: (2025)

Recent Advances in Discrete Speech Tokens: A Review
by: Guo, Yiwei, et al.
Published: (2025)

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

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

Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate
by: Zhang, Hanglei, et al.
Published: (2025)

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

AHAMask: Reliable Task Specification for Large Audio Language Models without Instructions
by: Guo, Yiwei, et al.
Published: (2025)

HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
by: Li, Bohan, et al.
Published: (2026)

Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding
by: Li, Bohan, et al.
Published: (2024)

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

vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders
by: Guo, Yiwei, et al.
Published: (2024)

ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models
by: Li, Bohan, et al.
Published: (2025)

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

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

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

ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription
by: Le, Khanh, et al.
Published: (2025)

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

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

EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
by: Wang, Jianzong, et al.
Published: (2024)

SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution
by: Wang, Fangyuan, et al.
Published: (2022)

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

On the Effectiveness of Acoustic BPE in Decoder-Only TTS
by: Li, Bohan, et al.
Published: (2024)

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

A Transcription Prompt-based Efficient Audio Large Language Model for Robust Speech Recognition
by: Li, Yangze, et al.
Published: (2024)

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

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

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

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

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

StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations
by: Liu, Sen, et al.
Published: (2024)

Efficient Autoregressive Audio Modeling via Next-Scale Prediction
by: Qiu, Kai, et al.
Published: (2024)

Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers
by: Cai, Runyuan, et al.
Published: (2026)

LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech
by: Mu, Bingshen, et al.
Published: (2026)

Autoregressive Speech Synthesis without Vector Quantization
by: Meng, Lingwei, et al.
Published: (2024)

SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
by: Wang, Helin, et al.
Published: (2024)

Layer-wise Analysis for Quality of Multilingual Synthesized Speech
by: Cooper, Erica, et al.
Published: (2025)

MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis
by: Yang, Qian, et al.
Published: (2024)

Human-Inspired Computing for Robust and Efficient Audio-Visual Speech Recognition
by: Liu, Qianhui, et al.
Published: (2024)

Robust Audio Tagging under Class-wise Supervision Unreliability
by: Hou, Yuanbo, et al.
Published: (2026)