10 citations · 17 across the 25 of their papers we have counts for
34 papers
VoxCanvas-41M: A Large-Scale Bilingual Dataset for Instruction-Based Speech Editing and Its Learning Dynamics
Zhikang Niu, Wenming Tu, Yalin Li +8
Recent advances in speech generation have spurred the development of speech editing techniques. However, achieving high-quality speech editing remains challenging due to two key li…
Route-DMD: Distribution Matching Distillation with Task-Routed Mechanism for Speech Foundation Models
Yanru Huo, Zhikang Niu, Wenming Tu +7
Speech foundation models built on flow matching handle generation, editing, and processing in one system, but every request costs 20-50 iterative steps, and classifier-free guidanc…
TinyAudio: Compact and Efficient Text-to-Audio Generation for Low-Resource Deployment
Junxi Liu, Xiquan Li, Wenhao Guan +5
Text-to-audio (TTA) generation has advanced rapidly in generation quality and instruction following. However, representative systems often require around a billion parameters, limi…
Cross-Lingual F5-TTS 2: A Simplified Framework for Language-Agnostic Voice Cloning
Qingyu Liu, Rixi Xu, Yushen Chen +11
Zero-shot text-to-speech (TTS) can clone a speaker's voice from a short audio prompt, yet most TTS systems still require the audio prompt transcript during inference. This dependen…
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing
Ziyang Ma, Zhikang Niu, Wenming Tu +30
We introduce AuK, an open-source foundational model that unifies speech generation and editing through a common interface of natural-language instructions and audio context. To sup…
GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model
Guanrou Yang, Tian Tan, Qian Chen +8
Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE…
GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
Yujie Tu, Yifan Yang, Tianrui Wang +35
While modern ASR systems achieve low error rates on high-resource benchmarks, such performance often overestimates real-world robustness. Existing evaluations address challenges in…
MMAE: A Massive Multitask Audio Editing Benchmark
Ziyang Ma, Ruiqi Yan, Ruiyang Xu +35
We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing.…
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
Wenxi Chen, Dongya Jia, Yushen Chen +11
Recently, diffusion models operating on VAE latents or mel-spectrograms have become the dominant paradigm for zero-shot TTS. Although these compressed representations improve gener…
Evaluating the Expressive Appropriateness of Speech in Rich Contexts
Tianrui Wang, Ziyang Ma, Yizhou Peng +26
Evaluating expressive speech remains challenging, as existing methods mainly assess emotional intensity and overlook whether a speech sample is expressively appropriate for its con…
X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning
Rixi Xu, Qingyu Liu, Haitao Li +10
In this paper, we present X-Voice, a 0.4B multilingual zero-shot voice cloning model that clones arbitrary voices and enables everyone to speak 30 languages. X-Voice is trained on…
WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
Guanrou Yang, Tian Tan, Qian Chen +12
Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks current…
SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing
Ziyang Ma, Guanrou Yang, Wenxi Chen +19
The recent surge in open-source Multimodal Large Language Models (MLLM) frameworks, such as LLaVA, provides a convenient kickoff for artificial intelligence developers and research…
Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis
Yushen Chen, Junzhe Liu, Yujie Tu +6
Arabic spans over 30 spoken varieties, yet no open-source text-to-speech system unifies them. Key barriers include substantial cross-dialect lexical and phonological divergence, sc…
Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis
Pengchao Feng, Yao Xiao, Ziyang Ma +5
Recent advances in text-to-speech (TTS) have yielded remarkable improvements in naturalness and intelligibility. Building on these achievements, research has increasingly shifted t…
STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
Zihan Liu, Zhikang Niu, Qiuyang Xiao +10
Despite rapid progress in Multi-modal Large Language Models and Large Audio-Language Models, existing audio benchmarks largely test semantics that can be recovered from text captio…
DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
Yakun Song, Xiaobin Zhuang, Jiawei Chen +8
Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under d…
SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization
Wenxi Chen, Xinsheng Wang, Ruiqi Yan +9
Speech codecs that convert continuous speech signals into discrete tokens have become essential for speech language models. However, existing codecs struggle to balance high-qualit…
UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models
Wenhao Guan, Zhikang Niu, Ziyue Jiang +5
Large language models (LLMs) have demonstrated promising performance in both automatic speech recognition (ASR) and text-to-speech (TTS) systems, gradually becoming the mainstream…
Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis
Zhikang Niu, Shujie Hu, Jeongsoo Choi +8
Mel-spectrograms have been widely used in zero-shot text-to-speech (TTS); their inherent redundancy leads to inefficiency in text-speech alignment. Compact VAE-based latent represe…
Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis
Qingyu Liu, Yushen Chen, Zhikang Niu +7
Flow-matching-based text-to-speech (TTS) models have shown high-quality speech synthesis. However, most current flow-matching-based TTS models still rely on reference transcripts c…
MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows
Xiquan Li, Junxi Liu, Yuzhe Liang +3
Recent years have witnessed remarkable progress in Text-to-Audio Generation (TTA), providing sound creators with powerful tools to transform inspirations into vivid audio. Yet desp…
Traceable TTS: Toward Watermark-Free TTS with Strong Traceability
Yuxiang Zhao, Yunchong Xiao, Yushen Chen +4
Recent advances in Text-To-Speech (TTS) technology have enabled synthetic speech to mimic human voices with remarkable realism, raising significant security concerns. This undersco…
Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
Qixi Zheng, Yushen Chen, Zhikang Niu +4
Flow-matching-based text-to-speech (TTS) models, such as Voicebox, E2 TTS, and F5-TTS, have attracted significant attention in recent years. These models require multiple sampling…