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/.
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/.
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/.
Registration is a fundamental but critical task in point cloud processing, which usually depends on finding element correspondence from two point clouds. However, the finding of reliable correspondence relies on establishing a robust and discriminative description of elements and the correct matching of corresponding elements. In this letter, we develop a coarse-to-fine registration strategy, which utilizes rotation-invariant features and a new weighted graph matching method for iteratively finding correspondence. In the graph matching method, the similarity of nodes and edges in Euclidean and feature space are formulated to construct the optimization function. The proposed strategy is evaluated using two benchmark datasets and compared with several state-of-the-art methods. Regarding the experimental results, our proposed method can achieve a fine registration with rotation errors of less than 0.2 degrees and translation errors of less than 0.1m.
In autonomous driving community, numerous benchmarks have been established to assist the tasks of 3D/2D object detection, stereo vision, semantic/instance segmentation. However, the more meaningful dynamic evolution of the surrounding objects of ego-vehicle is rarely exploited, and lacks a large-scale dataset platform. To address this, we introduce BLVD, a large-scale 5D semantics benchmark which does not concentrate on the static detection or semantic/instance segmentation tasks tackled adequately before. Instead, BLVD aims to provide a platform for the tasks of dynamic 4D (3D+temporal) tracking, 5D (4D+interactive) interactive event recognition and intention prediction. This benchmark will boost the deeper understanding of traffic scenes than ever before. We totally yield 249,129 3D annotations, 4,902 independent individuals for tracking with the length of overall 214,922 points, 6,004 valid fragments for 5D interactive event recognition, and 4,900 individuals for 5D intention prediction. These tasks are contained in four kinds of scenarios depending on the object density (low and high) and light conditions (daytime and nighttime). The benchmark can be downloaded from our project site https://github.com/VCCIV/BLVD/.