LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

Real-time, intelligent, and natural speech interaction is an essential part of the next-generation human-computer interaction. Recent advancements have showcased the potential of building intelligent spoken chatbots based on large language models (LLMs). In this paper, we introduce LLaMA-Omni 2, a series of speech language models (SpeechLMs) ranging from 0.5B to 14B parameters, capable of achieving high-quality real-time speech interaction. LLaMA-Omni 2 is built upon the Qwen2.5 series models, integrating a speech encoder and an autoregressive streaming speech decoder. Despite being trained on only 200K multi-turn speech dialogue samples, LLaMA-Omni 2 demonstrates strong performance on several spoken question answering and speech instruction following benchmarks, surpassing previous state-of-the-art SpeechLMs like GLM-4-Voice, which was trained on millions of hours of speech data.

Co$^{3}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion

Generating gestures from human speech has gained tremendous progress in animating virtual avatars. While the existing methods enable synthesizing gestures cooperated by individual self-talking, they overlook the practicality of concurrent gesture modeling with two-person interactive conversations. Moreover, the lack of high-quality datasets with concurrent co-speech gestures also limits handling this issue. To fulfill this goal, we first construct a large-scale concurrent co-speech gesture dataset that contains more than 7M frames for diverse two-person interactive posture sequences, dubbed GES-Inter. Additionally, we propose Co$^3$Gesture, a novel framework that enables coherent concurrent co-speech gesture synthesis including two-person interactive movements. Considering the asymmetric body dynamics of two speakers, our framework is built upon two cooperative generation branches conditioned on separated speaker audio. Specifically, to enhance the coordination of human postures with respect to corresponding speaker audios while interacting with the conversational partner, we present a Temporal Interaction Module (TIM). TIM can effectively model the temporal association representation between two speakers' gesture sequences as interaction guidance and fuse it into the concurrent gesture generation. Then, we devise a mutual attention mechanism to further holistically boost learning dependencies of interacted concurrent motions, thereby enabling us to generate vivid and coherent gestures. Extensive experiments demonstrate that our method outperforms the state-of-the-art models on our newly collected GES-Inter dataset. The dataset and source code are publicly available at \href{https://mattie-e.github.io/Co3/}{\textit{https://mattie-e.github.io/Co3/}}.

Scaling On-Device GPU Inference for Large Generative Models

Driven by the advancements in generative AI, large machine learning models have revolutionized domains such as image processing, audio synthesis, and speech recognition. While server-based deployments remain the locus of peak performance, the imperative for on-device inference, necessitated by privacy and efficiency considerations, persists. Recognizing GPUs as the on-device ML accelerator with the widest reach, we present ML Drift--an optimized framework that extends the capabilities of state-of-the-art GPU-accelerated inference engines. ML Drift enables on-device execution of generative AI workloads which contain 10 to 100x more parameters than existing on-device generative AI models. ML Drift addresses intricate engineering challenges associated with cross-GPU API development, and ensures broad compatibility across mobile and desktop/laptop platforms, thereby facilitating the deployment of significantly more complex models on resource-constrained devices. Our GPU-accelerated ML/AI inference engine achieves an order-of-magnitude performance improvement relative to existing open-source GPU inference engines.

AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation

In this paper, we address the task of multimodal-to-speech generation, which aims to synthesize high-quality speech from multiple input modalities: text, video, and reference audio. This task has gained increasing attention due to its wide range of applications, such as film production, dubbing, and virtual avatars. Despite recent progress, existing methods still suffer from limitations in speech intelligibility, audio-video synchronization, speech naturalness, and voice similarity to the reference speaker. To address these challenges, we propose AlignDiT, a multimodal Aligned Diffusion Transformer that generates accurate, synchronized, and natural-sounding speech from aligned multimodal inputs. Built upon the in-context learning capability of the DiT architecture, AlignDiT explores three effective strategies to align multimodal representations. Furthermore, we introduce a novel multimodal classifier-free guidance mechanism that allows the model to adaptively balance information from each modality during speech synthesis. Extensive experiments demonstrate that AlignDiT significantly outperforms existing methods across multiple benchmarks in terms of quality, synchronization, and speaker similarity. Moreover, AlignDiT exhibits strong generalization capability across various multimodal tasks, such as video-to-speech synthesis and visual forced alignment, consistently achieving state-of-the-art performance. The demo page is available at https://mm.kaist.ac.kr/projects/AlignDiT .

Towards Flow-Matching-based TTS without Classifier-Free Guidance

Flow matching has demonstrated strong generative capabilities and has become a core component in modern Text-to-Speech (TTS) systems. To ensure high-quality speech synthesis, Classifier-Free Guidance (CFG) is widely used during the inference of flow-matching-based TTS models. However, CFG incurs substantial computational cost as it requires two forward passes, which hinders its applicability in real-time scenarios. In this paper, we explore removing CFG from flow-matching-based TTS models to improve inference efficiency, while maintaining performance. Specifically, we reformulated the flow matching training target to directly approximate the CFG optimization trajectory. This training method eliminates the need for unconditional model evaluation and guided tuning during inference, effectively cutting the computational overhead in half. Furthermore, It can be seamlessly integrated with existing optimized sampling strategies. We validate our approach using the F5-TTS model on the LibriTTS dataset. Experimental results show that our method achieves a 9$\times$ inference speed-up compared to the baseline F5-TTS, while preserving comparable speech quality. We will release the code and models to support reproducibility and foster further research in this area.

Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancements

Voice conversion (VC) stands as a crucial research area in speech synthesis, enabling the transformation of a speaker's vocal characteristics to resemble another while preserving the linguistic content. This technology has broad applications, including automated movie dubbing, speech-to-singing conversion, and assistive devices for pathological speech rehabilitation. With the increasing demand for high-quality and natural-sounding synthetic voices, researchers have developed a wide range of VC techniques. Among these, generative adversarial network (GAN)-based approaches have drawn considerable attention for their powerful feature-mapping capabilities and potential to produce highly realistic speech. Despite notable advancements, challenges such as ensuring training stability, maintaining linguistic consistency, and achieving perceptual naturalness continue to hinder progress in GAN-based VC systems. This systematic review presents a comprehensive analysis of the voice conversion landscape, highlighting key techniques, key challenges, and the transformative impact of GANs in the field. The survey categorizes existing methods, examines technical obstacles, and critically evaluates recent developments in GAN-based VC. By consolidating and synthesizing research findings scattered across the literature, this review provides a structured understanding of the strengths and limitations of different approaches. The significance of this survey lies in its ability to guide future research by identifying existing gaps, proposing potential directions, and offering insights for building more robust and efficient VC systems. Overall, this work serves as an essential resource for researchers, developers, and practitioners aiming to advance the state-of-the-art (SOTA) in voice conversion technology.

Muyan-TTS: A Trainable Text-to-Speech Model Optimized for Podcast Scenarios with a $50K Budget

Recent advancements in text-to-speech (TTS) models have been driven by the integration of large language models (LLMs), enhancing semantic comprehension and improving speech naturalness. However, existing LLM-based TTS models often lack open-source training code and efficient inference acceleration frameworks, limiting their accessibility and adaptability. Additionally, there is no publicly available TTS model specifically optimized for podcast scenarios, which are in high demand for voice interaction applications. To address these limitations, we introduce Muyan-TTS, an open-source trainable TTS model designed for podcast applications within a $50,000 budget. Our model is pre-trained on over 100,000 hours of podcast audio data, enabling zero-shot TTS synthesis with high-quality voice generation. Furthermore, Muyan-TTS supports speaker adaptation with dozens of minutes of target speech, making it highly customizable for individual voices. In addition to open-sourcing the model, we provide a comprehensive data collection and processing pipeline, a full training procedure, and an optimized inference framework that accelerates LLM-based TTS synthesis. Our code and models are available at https://github.com/MYZY-AI/Muyan-TTS.

DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue

Speech synthesis is crucial for human-computer interaction, enabling natural and intuitive communication. However, existing datasets involve high construction costs due to manual annotation and suffer from limited character diversity, contextual scenarios, and emotional expressiveness. To address these issues, we propose DialogueAgents, a novel hybrid agent-based speech synthesis framework, which integrates three specialized agents -- a script writer, a speech synthesizer, and a dialogue critic -- to collaboratively generate dialogues. Grounded in a diverse character pool, the framework iteratively refines dialogue scripts and synthesizes speech based on speech review, boosting emotional expressiveness and paralinguistic features of the synthesized dialogues. Using DialogueAgent, we contribute MultiTalk, a bilingual, multi-party, multi-turn speech dialogue dataset covering diverse topics. Extensive experiments demonstrate the effectiveness of our framework and the high quality of the MultiTalk dataset. We release the dataset and code https://github.com/uirlx/DialogueAgents to facilitate future research on advanced speech synthesis models and customized data generation.

FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning

Recently, fake audio detection has gained significant attention, as advancements in speech synthesis and voice conversion have increased the vulnerability of automatic speaker verification (ASV) systems to spoofing attacks. A key challenge in this task is generalizing models to detect unseen, out-of-distribution (OOD) attacks. Although existing approaches have shown promising results, they inherently suffer from overconfidence issues due to the usage of softmax for classification, which can produce unreliable predictions when encountering unpredictable spoofing attempts. To deal with this limitation, we propose a novel framework called fake audio detection with evidential learning (FADEL). By modeling class probabilities with a Dirichlet distribution, FADEL incorporates model uncertainty into its predictions, thereby leading to more robust performance in OOD scenarios. Experimental results on the ASVspoof2019 Logical Access (LA) and ASVspoof2021 LA datasets indicate that the proposed method significantly improves the performance of baseline models. Furthermore, we demonstrate the validity of uncertainty estimation by analyzing a strong correlation between average uncertainty and equal error rate (EER) across different spoofing algorithms.

SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation

The accelerated advancement of speech generative models has given rise to security issues, including model infringement and unauthorized abuse of content. Although existing generative watermarking techniques have proposed corresponding solutions, most methods require substantial computational overhead and training costs. In addition, some methods have limitations in robustness when handling variable-length inputs. To tackle these challenges, we propose \textsc{SOLIDO}, a novel generative watermarking method that integrates parameter-efficient fine-tuning with speech watermarking through low-rank adaptation (LoRA) for speech diffusion models. Concretely, the watermark encoder converts the watermark to align with the input of diffusion models. To achieve precise watermark extraction from variable-length inputs, the watermark decoder based on depthwise separable convolution is designed for watermark recovery. To further enhance speech generation performance and watermark extraction capability, we propose a speech-driven lightweight fine-tuning strategy, which reduces computational overhead through LoRA. Comprehensive experiments demonstrate that the proposed method ensures high-fidelity watermarked speech even at a large capacity of 2000 bps. Furthermore, against common individual and compound speech attacks, our SOLIDO achieves a maximum average extraction accuracy of 99.20\% and 98.43\%, respectively. It surpasses other state-of-the-art methods by nearly 23\% in resisting time-stretching attacks.