MeanVoiceFlow2 is a new voice conversion framework that jointly optimizes a flow-based conversion module and a computationally efficient content encoder. It is trained via conversion distillation from MeanVoiceFlow and real data reconstruction, and further enhanced with diffusion-GAN training, sample mixing, and teacher-guided conditioning augmentation. Experiments on zero-shot voice conversion show that MeanVoiceFlow2 delivers higher perceptual quality and about nine times faster inference than its predecessor while preserving speaker similarity.
By Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
arXiv:2607. 09134v1 Announce Type: cross Abstract: Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity.
By Sang-Hoon Lee, Ha-Yeong Choi
arXiv:2601. 09239v5 Announce Type: replace-cross Abstract: Speech tokenizers are a key building block of fully discrete Speech LLMs.
By Hanlin Zhang, Daxin Tan, Dehua Tao, Xiao Chen, Haochen Tan, Yunhe Li, Yuchen Cao, Linqi Song
X-VC is a zero‑shot streaming voice conversion system that performs one‑step conversion directly in the latent space of a pretrained neural codec. It employs a dual‑conditioning acoustic converter that jointly models source codec latents and target acoustic conditions, while using adaptive normalization to inject utterance‑level speaker information. The model is trained with generated paired data and a role‑assignment strategy, and uses a chunkwise inference scheme with overlap smoothing to achieve low‑latency streaming inference, achieving superior WER, speaker similarity, and real‑time factor on the Seed‑TTS‑Eval benchmark.
By Qixi Zheng, Yuxiang Zhao, Tianrui Wang, Wenxi Chen, Kele Xu, Yikang Li, Qinyuan Cheng, Xipeng Qiu, Kai Yu, Xie Chen
arXiv:2608. 15690v1 Announce Type: cross Abstract: Text-to-audio-video (T2AV) generation models produce a video and its soundtrack from a textual description, but offer no control over whose voice speaks in the output.
By Ivan Mikheev, Viacheslav Vasilev, Anna Dmitrienko, Alexey Letunovskiy, Ivan Kirillov, Kirill Chernyshev, Denis Dimitrov
arXiv:2608. 13613v1 Announce Type: cross Abstract: Recent breakthroughs in generative models have made text-to-voice generation (TTV) possible, enabling the synthesis of speech directly from textual voice descriptions.
By Jiarui Hai, Karan Thakkar, Ke Chen, Yunyun Wang, Jiaqi Su, Rithesh Kumar, Mounya Elhilali, Zeyu Jin
The paper introduces Alignment-Free Text‑Audiobox (Text‑AB), a unified diffusion‑based framework that performs high‑quality voice dubbing and full‑duplex dialogue synthesis without requiring forced alignment. Text‑AB uses a latent diffusion model with DAC‑VAE features, achieving over 10× compression compared to prior EnCodec representations, and learns text‑speech alignment via cross‑attention. The authors pretrain a 3B‑parameter model on 480k hours of monolingual speech and fine‑tune it for cross‑lingual dubbing, full‑duplex dialogue, and emotional dialogue, reporting significant improvements in prosody, voice similarity, naturalness, and emotional expressivity over existing internal systems.
By Sanyuan Chen, Min-Jae Hwang, Sho Inoue, Anna Sun, Bokai Yu, David Kant, Dongmin Hyun, Dorian Desblancs, Gregory Antonovsky, Oleg Repin, Peng-Jen Chen, Xutai Ma, Zehai Tu, Juan Pino, Wei-Ning Hsu
arXiv:2606. 09048v1 Announce Type: cross Abstract: Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling.
By Wei Fan, Chao-Hong Tan, Qian Chen, Wen Wang, Xiangang Li, Kejiang Chen, Weiming Zhang, Nenghai Yu
arXiv:2608. 08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools.
By Yuqian Zhang, Yao Shi, Kexin Huang, Botian Jiang, Zhe Xu, Yiwei Zhao, Min Liang, Shuang Chen, Xipeng Qiu
The paper investigates how different speech content representations—such as SSL features, supervised tokens, posteriorgrams, and neural audio codecs—perform when used to train a generative model that produces audio conditioned only on each representation. By evaluating the generated audio on content, speaker identity, and prosody, the study identifies two regimes: some representations almost fully reconstruct the original audio, while others effectively separate speaker identity. The findings reveal that disentanglement of speaker identity depends on both the training objective and the representation’s information capacity, rather than supervision alone.
By Diego Torres, Axel Roebel, Nicolas Obin
arXiv:2603. 09234v2 Announce Type: cross Abstract: Achieving high perceptual quality without hallucination remains a challenge in generative speech enhancement (SE).
By Xiaobin Rong, Jun Gao, Zheng Wang, Mansur Yesilbursa, Kamil Wojcicki, Jing Lu
arXiv:2606. 24745v1 Announce Type: cross Abstract: Generative models, particularly diffusion and score-based approaches, have recently achieved strong performance in speech enhancement, but their iterative sampling process limits real-time deployment.
By Wangyi Pu, Michele Scarpiniti