Qifeng Liu

Zhen Ye, Peiwen Sun, Jiahe Lei et al.

Recent advancements in audio generation have been significantly propelled by the capabilities of Large Language Models (LLMs). The existing research on audio LLM has primarily focused on enhancing the architecture and scale of audio language models, as well as leveraging larger datasets, and generally, acoustic codecs, such as EnCodec, are used for audio tokenization. However, these codecs were originally designed for audio compression, which may lead to suboptimal performance in the context of audio LLM. Our research aims to address the shortcomings of current audio LLM codecs, particularly their challenges in maintaining semantic integrity in generated audio. For instance, existing methods like VALL-E, which condition acoustic token generation on text transcriptions, often suffer from content inaccuracies and elevated word error rates (WER) due to semantic misinterpretations of acoustic tokens, resulting in word skipping and errors. To overcome these issues, we propose a straightforward yet effective approach called X-Codec. X-Codec incorporates semantic features from a pre-trained semantic encoder before the Residual Vector Quantization (RVQ) stage and introduces a semantic reconstruction loss after RVQ. By enhancing the semantic ability of the codec, X-Codec significantly reduces WER in speech synthesis tasks and extends these benefits to non-speech applications, including music and sound generation. Our experiments in text-to-speech, music continuation, and text-to-sound tasks demonstrate that integrating semantic information substantially improves the overall performance of language models in audio generation. Our code and demo are available (Demo: https://x-codec-audio.github.io Code: https://github.com/zhenye234/xcodec)

Xingqun Qi, Jiahao Pan, Peng Li et al.

Generating vivid and emotional 3D co-speech gestures is crucial for virtual avatar animation in human-machine interaction applications. While the existing methods enable generating the gestures to follow a single emotion label, they overlook that long gesture sequence modeling with emotion transition is more practical in real scenes. In addition, the lack of large-scale available datasets with emotional transition speech and corresponding 3D human gestures also limits the addressing of this task. To fulfill this goal, we first incorporate the ChatGPT-4 and an audio inpainting approach to construct the high-fidelity emotion transition human speeches. Considering obtaining the realistic 3D pose annotations corresponding to the dynamically inpainted emotion transition audio is extremely difficult, we propose a novel weakly supervised training strategy to encourage authority gesture transitions. Specifically, to enhance the coordination of transition gestures w.r.t different emotional ones, we model the temporal association representation between two different emotional gesture sequences as style guidance and infuse it into the transition generation. We further devise an emotion mixture mechanism that provides weak supervision based on a learnable mixed emotion label for transition gestures. Last, we present a keyframe sampler to supply effective initial posture cues in long sequences, enabling us to generate diverse gestures. Extensive experiments demonstrate that our method outperforms the state-of-the-art models constructed by adapting single emotion-conditioned counterparts on our newly defined emotion transition task and datasets. Our code and dataset will be released on the project page: https://xingqunqi-lab.github.io/Emo-Transition-Gesture/.

Xinyu Liu, Yingqing He, Lanqing Guo et al.

The potential for higher-resolution image generation using pretrained diffusion models is immense, yet these models often struggle with issues of object repetition and structural artifacts especially when scaling to 4K resolution and higher. We figure out that the problem is caused by that, a single prompt for the generation of multiple scales provides insufficient efficacy. In response, we propose HiPrompt, a new tuning-free solution that tackles the above problems by introducing hierarchical prompts. The hierarchical prompts offer both global and local guidance. Specifically, the global guidance comes from the user input that describes the overall content, while the local guidance utilizes patch-wise descriptions from MLLMs to elaborately guide the regional structure and texture generation. Furthermore, during the inverse denoising process, the generated noise is decomposed into low- and high-frequency spatial components. These components are conditioned on multiple prompt levels, including detailed patch-wise descriptions and broader image-level prompts, facilitating prompt-guided denoising under hierarchical semantic guidance. It further allows the generation to focus more on local spatial regions and ensures the generated images maintain coherent local and global semantics, structures, and textures with high definition. Extensive experiments demonstrate that HiPrompt outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality.

Chunyang Jiang, Chi-min Chan, Wei Xue et al.

Large language models (LLMs) have shown remarkable capability in numerous tasks and applications. However, fine-tuning LLMs using high-quality datasets under external supervision remains prohibitively expensive. In response, LLM self-improvement approaches have been vibrantly developed recently. The typical paradigm of LLM self-improvement involves training LLM on self-generated data, part of which may be detrimental and should be filtered out due to the unstable data quality. While current works primarily employs filtering strategies based on answer correctness, in this paper, we demonstrate that filtering out correct but with high distribution shift extent (DSE) samples could also benefit the results of self-improvement. Given that the actual sample distribution is usually inaccessible, we propose a new metric called DS weight to approximate DSE, inspired by the Importance Weighting methods. Consequently, we integrate DS weight with self-consistency to comprehensively filter the self-generated samples and fine-tune the language model. Experiments show that with only a tiny valid set (up to 5\% size of the training set) to compute DS weight, our approach can notably promote the reasoning ability of current LLM self-improvement methods. The resulting performance is on par with methods that rely on external supervision from pre-trained reward models.

Xiaowei Chi, Yatian Wang, Aosong Cheng et al.

Massive multi-modality datasets play a significant role in facilitating the success of large video-language models. However, current video-language datasets primarily provide text descriptions for visual frames, considering audio to be weakly related information. They usually overlook exploring the potential of inherent audio-visual correlation, leading to monotonous annotation within each modality instead of comprehensive and precise descriptions. Such ignorance results in the difficulty of multiple cross-modality studies. To fulfill this gap, we present MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions, and 2M high-quality clips with multimodal captions. Trailers preview full-length video works and integrate context, visual frames, and background music. In particular, the trailer has two main advantages: (1) the topics are diverse, and the content characters are of various types, e.g., film, news, and gaming. (2) the corresponding background music is custom-designed, making it more coherent with the visual context. Upon these insights, we propose a systemic captioning framework, achieving various modality annotations with more than 27.1k hours of trailer videos. Here, to ensure the caption retains music perspective while preserving the authority of visual context, we leverage the advanced LLM to merge all annotations adaptively. In this fashion, our MMtrail dataset potentially paves the path for fine-grained large multimodal-language model training. In experiments, we provide evaluation metrics and benchmark results on our dataset, demonstrating the high quality of our annotation and its effectiveness for model training.

Min Zeng, Wei Xue, Qifeng Liu et al.

Recent advancements in data-driven task-oriented dialogue systems (ToDs) struggle with incremental learning due to computational constraints and time-consuming issues. Continual Learning (CL) attempts to solve this by avoiding intensive pre-training, but it faces the problem of catastrophic forgetting (CF). While generative-based rehearsal CL methods have made significant strides, generating pseudo samples that accurately reflect the underlying task-specific distribution is still a challenge. In this paper, we present Dirichlet Continual Learning (DCL), a novel generative-based rehearsal strategy for CL. Unlike the traditionally used Gaussian latent variable in the Conditional Variational Autoencoder (CVAE), DCL leverages the flexibility and versatility of the Dirichlet distribution to model the latent prior variable. This enables it to efficiently capture sentence-level features of previous tasks and effectively guide the generation of pseudo samples. In addition, we introduce Jensen-Shannon Knowledge Distillation (JSKD), a robust logit-based knowledge distillation method that enhances knowledge transfer during pseudo sample generation. Our experiments confirm the efficacy of our approach in both intent detection and slot-filling tasks, outperforming state-of-the-art methods.

Xiaowei Chi, Junbo Qi, Rongyu Zhang et al.

While current LLM chatbots like GPT-4V bridge the gap between human instructions and visual representations to enable text-image generations, they still lack efficient alignment methods for high-fidelity performance on multiple downstream tasks. In this paper, we propose \textbf{$M^{2}Chat$}, a novel unified multimodal LLM framework for generating interleaved text-image conversation across various scenarios. Specifically, we propose an $M^{3}Adapter$ that efficiently integrates granular low-level visual information and high-level semantic features from multi-modality prompts. Upon the well-aligned fused feature, $M^{3}Adapter$ tailors a learnable gating strategy to balance the model creativity and consistency across various tasks adaptively. Moreover, to further enhance the effectiveness of $M^{3}Adapter$ while preserving the coherence of semantic context comprehension, we introduce a two-stage $M^{3}FT$ fine-tuning strategy. This strategy optimizes disjoint groups of parameters for image-text alignment and visual-instruction respectively. Extensive experiments demonstrate our $M^{2}Chat$ surpasses state-of-the-art counterparts across diverse benchmarks, showcasing its prowess in interleaving generation, storytelling, and multimodal dialogue systems. The demo and code are available at \red{https://mattie-e.github.io/M2Chat.github.io}.

Ruibin Yuan, Hanfeng Lin, Yi Wang et al.

While Large Language Models (LLMs) demonstrate impressive capabilities in text generation, we find that their ability has yet to be generalized to music, humanity's creative language. We introduce ChatMusician, an open-source LLM that integrates intrinsic musical abilities. It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language. ChatMusician can understand and generate music with a pure text tokenizer without any external multi-modal neural structures or tokenizers. Interestingly, endowing musical abilities does not harm language abilities, even achieving a slightly higher MMLU score. Our model is capable of composing well-structured, full-length music, conditioned on texts, chords, melodies, motifs, musical forms, etc, surpassing GPT-4 baseline. On our meticulously curated college-level music understanding benchmark, MusicTheoryBench, ChatMusician surpasses LLaMA2 and GPT-3.5 on zero-shot setting by a noticeable margin. Our work reveals that LLMs can be an excellent compressor for music, but there remains significant territory to be conquered. We release our 4B token music-language corpora MusicPile, the collected MusicTheoryBench, code, model and demo in GitHub.

Yike Guo, Qifeng Liu, Jie Chen et al.

This report presents a comprehensive view of our vision on the development path of the human-machine symbiotic art creation. We propose a classification of the creative system with a hierarchy of 5 classes, showing the pathway of creativity evolving from a mimic-human artist (Turing Artists) to a Machine artist in its own right. We begin with an overview of the limitations of the Turing Artists then focus on the top two-level systems, Machine Artists, emphasizing machine-human communication in art creation. In art creation, it is necessary for machines to understand humans' mental states, including desires, appreciation, and emotions, humans also need to understand machines' creative capabilities and limitations. The rapid development of immersive environment and further evolution into the new concept of metaverse enable symbiotic art creation through unprecedented flexibility of bi-directional communication between artists and art manifestation environments. By examining the latest sensor and XR technologies, we illustrate the novel way for art data collection to constitute the base of a new form of human-machine bidirectional communication and understanding in art creation. Based on such communication and understanding mechanisms, we propose a novel framework for building future Machine artists, which comes with the philosophy that a human-compatible AI system should be based on the "human-in-the-loop" principle rather than the traditional "end-to-end" dogma. By proposing a new form of inverse reinforcement learning model, we outline the platform design of machine artists, demonstrate its functions and showcase some examples of technologies we have developed. We also provide a systematic exposition of the ecosystem for AI-based symbiotic art form and community with an economic model built on NFT technology. Ethical issues for the development of machine artists are also discussed.

Qifeng Liu, Dawei Zhao, Yabo Dong et al.

Recent advances in point cloud object detection have increasingly adopted Transformer-based and State Space Models (SSMs), demonstrating strong performance. However, voxelbased representations in these models require strict consistency in input and output dimensions due to their serialized processing, which limits the spatial diffusion capability typically offered by convolutional operations. This limitation significantly affects detection accuracy. Inspired by CNN-based object detection architectures, we propose a novel Voxel Diffusion Module (VDM) to enhance voxel-level representation and diffusion in point cloud data. VDM is composed of sparse 3D convolutions, submanifold sparse convolutions, and residual connections. To ensure computational efficiency, the output feature maps are downsampled to one-fourth of the original input resolution. VDM serves two primary functions: (1) diffusing foreground voxel features through sparse 3D convolutions to enrich spatial context, and (2) aggregating fine-grained spatial information to strengthen voxelwise feature representation. The enhanced voxel features produced by VDM can be seamlessly integrated into mainstream Transformer- or SSM-based detection models for accurate object classification and localization, highlighting the generalizability of our method. We evaluate VDM on several benchmark datasets by embedding it into both Transformerbased and SSM-based models. Experimental results show that our approach consistently improves detection accuracy over baseline models. Specifically, VDM-SSMs achieve 74.7 mAPH (L2) on Waymo, 72.9 NDS on nuScenes, 42.3 mAP on Argoverse 2, and 67.6 mAP on ONCE, setting new stateof-the-art performance across all datasets. Our code will be made publicly available.

Peng Li, Yuan Liu, Xiaoxiao Long et al.

In this paper, we introduce Era3D, a novel multiview diffusion method that generates high-resolution multiview images from a single-view image. Despite significant advancements in multiview generation, existing methods still suffer from camera prior mismatch, inefficacy, and low resolution, resulting in poor-quality multiview images. Specifically, these methods assume that the input images should comply with a predefined camera type, e.g. a perspective camera with a fixed focal length, leading to distorted shapes when the assumption fails. Moreover, the full-image or dense multiview attention they employ leads to an exponential explosion of computational complexity as image resolution increases, resulting in prohibitively expensive training costs. To bridge the gap between assumption and reality, Era3D first proposes a diffusion-based camera prediction module to estimate the focal length and elevation of the input image, which allows our method to generate images without shape distortions. Furthermore, a simple but efficient attention layer, named row-wise attention, is used to enforce epipolar priors in the multiview diffusion, facilitating efficient cross-view information fusion. Consequently, compared with state-of-the-art methods, Era3D generates high-quality multiview images with up to a 512*512 resolution while reducing computation complexity by 12x times. Comprehensive experiments demonstrate that Era3D can reconstruct high-quality and detailed 3D meshes from diverse single-view input images, significantly outperforming baseline multiview diffusion methods. Project page: https://penghtyx.github.io/Era3D/.

Zekai Gu, Rui Yan, Jiahao Lu et al.

Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images. However, precise control over the video generation process, such as camera manipulation or content editing, remains a significant challenge. Existing methods for controlled video generation are typically limited to a single control type, lacking the flexibility to handle diverse control demands. In this paper, we introduce Diffusion as Shader (DaS), a novel approach that supports multiple video control tasks within a unified architecture. Our key insight is that achieving versatile video control necessitates leveraging 3D control signals, as videos are fundamentally 2D renderings of dynamic 3D content. Unlike prior methods limited to 2D control signals, DaS leverages 3D tracking videos as control inputs, making the video diffusion process inherently 3D-aware. This innovation allows DaS to achieve a wide range of video controls by simply manipulating the 3D tracking videos. A further advantage of using 3D tracking videos is their ability to effectively link frames, significantly enhancing the temporal consistency of the generated videos. With just 3 days of fine-tuning on 8 H800 GPUs using less than 10k videos, DaS demonstrates strong control capabilities across diverse tasks, including mesh-to-video generation, camera control, motion transfer, and object manipulation.

Zhen Ye, Zeqian Ju, Haohe Liu et al.

Recent progress in large-scale zero-shot speech synthesis has been significantly advanced by language models and diffusion models. However, the generation process of both methods is slow and computationally intensive. Efficient speech synthesis using a lower computing budget to achieve quality on par with previous work remains a significant challenge. In this paper, we present FlashSpeech, a large-scale zero-shot speech synthesis system with approximately 5\% of the inference time compared with previous work. FlashSpeech is built on the latent consistency model and applies a novel adversarial consistency training approach that can train from scratch without the need for a pre-trained diffusion model as the teacher. Furthermore, a new prosody generator module enhances the diversity of prosody, making the rhythm of the speech sound more natural. The generation processes of FlashSpeech can be achieved efficiently with one or two sampling steps while maintaining high audio quality and high similarity to the audio prompt for zero-shot speech generation. Our experimental results demonstrate the superior performance of FlashSpeech. Notably, FlashSpeech can be about 20 times faster than other zero-shot speech synthesis systems while maintaining comparable performance in terms of voice quality and similarity. Furthermore, FlashSpeech demonstrates its versatility by efficiently performing tasks like voice conversion, speech editing, and diverse speech sampling. Audio samples can be found in https://flashspeech.github.io/.

Xiaowei Chi, Chun-Kai Fan, Hengyuan Zhang et al.

Video generation models have made significant progress in simulating future states, showcasing their potential as world simulators in embodied scenarios. However, existing models often lack robust understanding, limiting their ability to perform multi-step predictions or handle Out-of-Distribution (OOD) scenarios. To address this challenge, we propose the Reflection of Generation (RoG), a set of intermediate reasoning strategies designed to enhance video prediction. It leverages the complementary strengths of pre-trained vision-language and video generation models, enabling them to function as a world model in embodied scenarios. To support RoG, we introduce Embodied Video Anticipation Benchmark(EVA-Bench), a comprehensive benchmark that evaluates embodied world models across diverse tasks and scenarios, utilizing both in-domain and OOD datasets. Building on this foundation, we devise a world model, Embodied Video Anticipator (EVA), that follows a multistage training paradigm to generate high-fidelity video frames and apply an autoregressive strategy to enable adaptive generalization for longer video sequences. Extensive experiments demonstrate the efficacy of EVA in various downstream tasks like video generation and robotics, thereby paving the way for large-scale pre-trained models in real-world video prediction applications. The video demos are available at \hyperlink{https://sites.google.com/view/icml-eva}{https://sites.google.com/view/icml-eva}.

Yiwen Lu, Zhen Ye, Wei Xue et al.

The diffusion-based Singing Voice Conversion (SVC) methods have achieved remarkable performances, producing natural audios with high similarity to the target timbre. However, the iterative sampling process results in slow inference speed, and acceleration thus becomes crucial. In this paper, we propose CoMoSVC, a consistency model-based SVC method, which aims to achieve both high-quality generation and high-speed sampling. A diffusion-based teacher model is first specially designed for SVC, and a student model is further distilled under self-consistency properties to achieve one-step sampling. Experiments on a single NVIDIA GTX4090 GPU reveal that although CoMoSVC has a significantly faster inference speed than the state-of-the-art (SOTA) diffusion-based SVC system, it still achieves comparable or superior conversion performance based on both subjective and objective metrics. Audio samples and codes are available at https://comosvc.github.io/.

Xinyu Liu, Ailing Zeng, Wei Xue et al.

Crafting magic and illusions is one of the most thrilling aspects of filmmaking, with visual effects (VFX) serving as the powerhouse behind unforgettable cinematic experiences. While recent advances in generative artificial intelligence have driven progress in generic image and video synthesis, the domain of controllable VFX generation remains relatively underexplored. In this work, we propose a novel paradigm for animated VFX generation as image animation, where dynamic effects are generated from user-friendly textual descriptions and static reference images. Our work makes two primary contributions: (i) Open-VFX, the first high-quality VFX video dataset spanning 15 diverse effect categories, annotated with textual descriptions, instance segmentation masks for spatial conditioning, and start-end timestamps for temporal control. (ii) VFX Creator, a simple yet effective controllable VFX generation framework based on a Video Diffusion Transformer. The model incorporates a spatial and temporal controllable LoRA adapter, requiring minimal training videos. Specifically, a plug-and-play mask control module enables instance-level spatial manipulation, while tokenized start-end motion timestamps embedded in the diffusion process, alongside the text encoder, allow precise temporal control over effect timing and pace. Extensive experiments on the Open-VFX test set demonstrate the superiority of the proposed system in generating realistic and dynamic effects, achieving state-of-the-art performance and generalization ability in both spatial and temporal controllability. Furthermore, we introduce a specialized metric to evaluate the precision of temporal control. By bridging traditional VFX techniques with generative approaches, VFX Creator unlocks new possibilities for efficient and high-quality video effect generation, making advanced VFX accessible to a broader audience.

Jianyi Chen, Wei Xue, Xu Tan et al.

Singing Accompaniment Generation (SAG), which generates instrumental music to accompany input vocals, is crucial to developing human-AI symbiotic art creation systems. The state-of-the-art method, SingSong, utilizes a multi-stage autoregressive (AR) model for SAG, however, this method is extremely slow as it generates semantic and acoustic tokens recursively, and this makes it impossible for real-time applications. In this paper, we aim to develop a Fast SAG method that can create high-quality and coherent accompaniments. A non-AR diffusion-based framework is developed, which by carefully designing the conditions inferred from the vocal signals, generates the Mel spectrogram of the target accompaniment directly. With diffusion and Mel spectrogram modeling, the proposed method significantly simplifies the AR token-based SingSong framework, and largely accelerates the generation. We also design semantic projection, prior projection blocks as well as a set of loss functions, to ensure the generated accompaniment has semantic and rhythm coherence with the vocal signal. By intensive experimental studies, we demonstrate that the proposed method can generate better samples than SingSong, and accelerate the generation by at least 30 times. Audio samples and code are available at https://fastsag.github.io/.

Xingqun Qi, Yatian Wang, Hengyuan Zhang et al.

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/}}.

Shiying Li, Xingqun Qi, Bingkun Yang et al.

Generating responsive listener head dynamics with nuanced emotions and expressive reactions is crucial for practical dialogue modeling in various virtual avatar animations. Previous studies mainly focus on the direct short-term production of listener behavior. They overlook the fine-grained control over motion variations and emotional intensity, especially in long-sequence modeling. Moreover, the lack of long-term and large-scale paired speaker-listener corpora including head dynamics and fine-grained multi-modality annotations (e.g., text-based expression descriptions, emotional intensity) also limits the application of dialogue modeling.Therefore, we first newly collect a large-scale multi-turn dataset of 3D dyadic conversation containing more than 1.4M valid frames for multi-modal responsive interaction, dubbed ListenerX. Additionally, we propose VividListener, a novel framework enabling fine-grained, expressive and controllable listener dynamics modeling. This framework leverages multi-modal conditions as guiding principles for fostering coherent interactions between speakers and listeners.Specifically, we design the Responsive Interaction Module (RIM) to adaptively represent the multi-modal interactive embeddings. RIM ensures the listener dynamics achieve fine-grained semantic coordination with textual descriptions and adjustments, while preserving expressive reaction with speaker behavior. Meanwhile, we design the Emotional Intensity Tags (EIT) for emotion intensity editing with multi-modal information integration, applying to both text descriptions and listener motion amplitude.Extensive experiments conducted on our newly collected ListenerX dataset demonstrate that VividListener achieves state-of-the-art performance, realizing expressive and controllable listener dynamics.

Zeyue Tian, Zhaoyang Liu, Ruibin Yuan et al.

In this work, we systematically study music generation conditioned solely on the video. First, we present a large-scale dataset comprising 360K video-music pairs, including various genres such as movie trailers, advertisements, and documentaries. Furthermore, we propose VidMuse, a simple framework for generating music aligned with video inputs. VidMuse stands out by producing high-fidelity music that is both acoustically and semantically aligned with the video. By incorporating local and global visual cues, VidMuse enables the creation of musically coherent audio tracks that consistently match the video content through Long-Short-Term modeling. Through extensive experiments, VidMuse outperforms existing models in terms of audio quality, diversity, and audio-visual alignment. The code and datasets are available at https://vidmuse.github.io/.

Zhen Ye, Wei Xue, Xu Tan et al.

Developing digital sound synthesizers is crucial to the music industry as it provides a low-cost way to produce high-quality sounds with rich timbres. Existing traditional synthesizers often require substantial expertise to determine the overall framework of a synthesizer and the parameters of submodules. Since expert knowledge is hard to acquire, it hinders the flexibility to quickly design and tune digital synthesizers for diverse sounds. In this paper, we propose ``NAS-FM'', which adopts neural architecture search (NAS) to build a differentiable frequency modulation (FM) synthesizer. Tunable synthesizers with interpretable controls can be developed automatically from sounds without any prior expert knowledge and manual operating costs. In detail, we train a supernet with a specifically designed search space, including predicting the envelopes of carriers and modulators with different frequency ratios. An evolutionary search algorithm with adaptive oscillator size is then developed to find the optimal relationship between oscillators and the frequency ratio of FM. Extensive experiments on recordings of different instrument sounds show that our algorithm can build a synthesizer fully automatically, achieving better results than handcrafted synthesizers. Audio samples are available at https://nas-fm.github.io/.

Zhen Ye, Wei Xue, Xu Tan et al.

Denoising diffusion probabilistic models (DDPMs) have shown promising performance for speech synthesis. However, a large number of iterative steps are required to achieve high sample quality, which restricts the inference speed. Maintaining sample quality while increasing sampling speed has become a challenging task. In this paper, we propose a "Co"nsistency "Mo"del-based "Speech" synthesis method, CoMoSpeech, which achieve speech synthesis through a single diffusion sampling step while achieving high audio quality. The consistency constraint is applied to distill a consistency model from a well-designed diffusion-based teacher model, which ultimately yields superior performances in the distilled CoMoSpeech. Our experiments show that by generating audio recordings by a single sampling step, the CoMoSpeech achieves an inference speed more than 150 times faster than real-time on a single NVIDIA A100 GPU, which is comparable to FastSpeech2, making diffusion-sampling based speech synthesis truly practical. Meanwhile, objective and subjective evaluations on text-to-speech and singing voice synthesis show that the proposed teacher models yield the best audio quality, and the one-step sampling based CoMoSpeech achieves the best inference speed with better or comparable audio quality to other conventional multi-step diffusion model baselines. Audio samples are available at https://comospeech.github.io/.