Recent developments in neural speech synthesis and vocoding have sparked a renewed interest in voice conversion (VC). Beyond timbre transfer, achieving controllability on para-linguistic parameters such as pitch and Speed is critical in deploying VC systems in many application scenarios. Existing studies, however, either only provide utterance-level global control or lack interpretability on the controls. In this paper, we propose ControlVC, the first neural voice conversion system that achieves time-varying controls on pitch and speed. ControlVC uses pre-trained encoders to compute pitch and linguistic embeddings from the source utterance and speaker embeddings from the target utterance. These embeddings are then concatenated and converted to speech using a vocoder. It achieves speed control through TD-PSOLA pre-processing on the source utterance, and achieves pitch control by manipulating the pitch contour before feeding it to the pitch encoder. Systematic subjective and objective evaluations are conducted to assess the speech quality and controllability. Results show that, on non-parallel and zero-shot conversion tasks, ControlVC significantly outperforms two other self-constructed baselines on speech quality, and it can successfully achieve time-varying pitch and speed control.
相關內容
The tree-based ensembles are known for their outstanding performance in classification and regression problems characterized by feature vectors represented by mixed-type variables from various ranges and domains. However, considering regression problems, they are primarily designed to provide deterministic responses or model the uncertainty of the output with Gaussian or parametric distribution. In this work, we introduce TreeFlow, the tree-based approach that combines the benefits of using tree ensembles with the capabilities of modeling flexible probability distributions using normalizing flows. The main idea of the solution is to use a tree-based model as a feature extractor and combine it with a conditional variant of normalizing flow. Consequently, our approach is capable of modeling complex distributions for the regression outputs. We evaluate the proposed method on challenging regression benchmarks with varying volume, feature characteristics, and target dimensionality. We obtain the SOTA results for both probabilistic and deterministic metrics on datasets with multi-modal target distributions and competitive results on unimodal ones compared to tree-based regression baselines.
Voice conversion (VC), as a voice style transfer technology, is becoming increasingly prevalent while raising serious concerns about its illegal use. Proactively tracing the origins of VC-generated speeches, i.e., speaker traceability, can prevent the misuse of VC, but unfortunately has not been extensively studied. In this paper, we are the first to investigate the speaker traceability for VC and propose a traceable VC framework named VoxTracer. Our VoxTracer is similar to but beyond the paradigm of audio watermarking. We first use unique speaker embedding to represent speaker identity. Then we design a VAE-Glow structure, in which the hiding process imperceptibly integrates the source speaker identity into the VC, and the tracing process accurately recovers the source speaker identity and even the source speech in spite of severe speech quality degradation. To address the speech mismatch between the hiding and tracing processes affected by different distortions, we also adopt an asynchronous training strategy to optimize the VAE-Glow models. The VoxTracer is versatile enough to be applied to arbitrary VC methods and popular audio coding standards. Extensive experiments demonstrate that the VoxTracer achieves not only high imperceptibility in hiding, but also nearly 100% tracing accuracy against various types of audio lossy compressions (AAC, MP3, Opus and SILK) with a broad range of bitrates (16 kbps - 128 kbps) even in a very short time duration (0.74s). Our speech demo is available at //anonymous.4open.science/w/DEMOofVoxTracer.
Current referring video object segmentation (R-VOS) techniques extract conditional kernels from encoded (low-resolution) vision-language features to segment the decoded high-resolution features. We discovered that this causes significant feature drift, which the segmentation kernels struggle to perceive during the forward computation. This negatively affects the ability of segmentation kernels. To address the drift problem, we propose a Spectrum-guided Multi-granularity (SgMg) approach, which performs direct segmentation on the encoded features and employs visual details to further optimize the masks. In addition, we propose Spectrum-guided Cross-modal Fusion (SCF) to perform intra-frame global interactions in the spectral domain for effective multimodal representation. Finally, we extend SgMg to perform multi-object R-VOS, a new paradigm that enables simultaneous segmentation of multiple referred objects in a video. This not only makes R-VOS faster, but also more practical. Extensive experiments show that SgMg achieves state-of-the-art performance on four video benchmark datasets, outperforming the nearest competitor by 2.8% points on Ref-YouTube-VOS. Our extended SgMg enables multi-object R-VOS, runs about 3 times faster while maintaining satisfactory performance. Code is available at //github.com/bo-miao/SgMg.
Recently, speech codecs based on neural networks have proven to perform better than traditional methods. However, redundancy in traditional parameter quantization is visible within the codec architecture of combining the traditional codec with the neural vocoder. In this paper, we propose a novel framework named CQNV, which combines the coarsely quantized parameters of a traditional parametric codec to reduce the bitrate with a neural vocoder to improve the quality of the decoded speech. Furthermore, we introduce a parameters processing module into the neural vocoder to enhance the application of the bitstream of traditional speech coding parameters to the neural vocoder, further improving the reconstructed speech's quality. In the experiments, both subjective and objective evaluations demonstrate the effectiveness of the proposed CQNV framework. Specifically, our proposed method can achieve higher quality reconstructed speech at 1.1 kbps than Lyra and Encodec at 3 kbps.
This paper presents a deep reinforcement learning solution for optimizing multi-UAV cell-association decisions and their moving velocity on a 3D aerial highway. The objective is to enhance transportation and communication performance, including collision avoidance, connectivity, and handovers. The problem is formulated as a Markov decision process (MDP) with UAVs' states defined by velocities and communication data rates. We propose a neural architecture with a shared decision module and multiple network branches, each dedicated to a specific action dimension in a 2D transportation-communication space. This design efficiently handles the multi-dimensional action space, allowing independence for individual action dimensions. We introduce two models, Branching Dueling Q-Network (BDQ) and Branching Dueling Double Deep Q-Network (Dueling DDQN), to demonstrate the approach. Simulation results show a significant improvement of 18.32% compared to existing benchmarks.
Accurately localizing and identifying vertebrae from CT images is crucial for various clinical applications. However, most existing efforts are performed on 3D with cropping patch operation, suffering from the large computation costs and limited global information. In this paper, we propose a multi-view vertebra localization and identification from CT images, converting the 3D problem into a 2D localization and identification task on different views. Without the limitation of the 3D cropped patch, our method can learn the multi-view global information naturally. Moreover, to better capture the anatomical structure information from different view perspectives, a multi-view contrastive learning strategy is developed to pre-train the backbone. Additionally, we further propose a Sequence Loss to maintain the sequential structure embedded along the vertebrae. Evaluation results demonstrate that, with only two 2D networks, our method can localize and identify vertebrae in CT images accurately, and outperforms the state-of-the-art methods consistently. Our code is available at //github.com/ShanghaiTech-IMPACT/Multi-View-Vertebra-Localization-and-Identification-from-CT-Images.
In Federated Learning (FL), a number of clients or devices collaborate to train a model without sharing their data. Models are optimized locally at each client and further communicated to a central hub for aggregation. While FL is an appealing decentralized training paradigm, heterogeneity among data from different clients can cause the local optimization to drift away from the global objective. In order to estimate and therefore remove this drift, variance reduction techniques have been incorporated into FL optimization recently. However, these approaches inaccurately estimate the clients' drift and ultimately fail to remove it properly. In this work, we propose an adaptive algorithm that accurately estimates drift across clients. In comparison to previous works, our approach necessitates less storage and communication bandwidth, as well as lower compute costs. Additionally, our proposed methodology induces stability by constraining the norm of estimates for client drift, making it more practical for large scale FL. Experimental findings demonstrate that the proposed algorithm converges significantly faster and achieves higher accuracy than the baselines across various FL benchmarks.
Diffusion models have shown incredible capabilities as generative models; indeed, they power the current state-of-the-art models on text-conditioned image generation such as Imagen and DALL-E 2. In this work we review, demystify, and unify the understanding of diffusion models across both variational and score-based perspectives. We first derive Variational Diffusion Models (VDM) as a special case of a Markovian Hierarchical Variational Autoencoder, where three key assumptions enable tractable computation and scalable optimization of the ELBO. We then prove that optimizing a VDM boils down to learning a neural network to predict one of three potential objectives: the original source input from any arbitrary noisification of it, the original source noise from any arbitrarily noisified input, or the score function of a noisified input at any arbitrary noise level. We then dive deeper into what it means to learn the score function, and connect the variational perspective of a diffusion model explicitly with the Score-based Generative Modeling perspective through Tweedie's Formula. Lastly, we cover how to learn a conditional distribution using diffusion models via guidance.
Multimodal sentiment analysis is a very actively growing field of research. A promising area of opportunity in this field is to improve the multimodal fusion mechanism. We present a novel feature fusion strategy that proceeds in a hierarchical fashion, first fusing the modalities two in two and only then fusing all three modalities. On multimodal sentiment analysis of individual utterances, our strategy outperforms conventional concatenation of features by 1%, which amounts to 5% reduction in error rate. On utterance-level multimodal sentiment analysis of multi-utterance video clips, for which current state-of-the-art techniques incorporate contextual information from other utterances of the same clip, our hierarchical fusion gives up to 2.4% (almost 10% error rate reduction) over currently used concatenation. The implementation of our method is publicly available in the form of open-source code.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191