Search Results for author:
Found 16 papers, 9 papers with code
DiffCSS: Diverse and Expressive Conversational Speech Synthesis with Diffusion Models
A diffusion-based context-aware prosody predictor is proposed to sample diverse prosody embeddings conditioned on multimodal conversational context.
SongCreator: Lyrics-based Universal Song Generation
While various aspects of song generation have been explored by previous works, such as singing voice, vocal composition and instrumental arrangement, etc., generating songs with both vocals and accompaniment given lyrics remains a significant challenge, hindering the application of music generation models in the real world.
VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization
Through the integration of vector quantization (VQ), we empower the flow models to distinguish different concepts of multi-class normal data in an unsupervised manner, resulting in a novel flow-based unified method, named VQ-Flow.
Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models
Moreover, fine-grained prosody modeling is introduced to enhance the model's ability to capture subtle prosody variations in spontaneous speech. Experimental results show that our proposed method significantly outperforms the baseline methods in terms of prosody naturalness and spontaneous behavior naturalness.
BatchNorm-based Weakly Supervised Video Anomaly Detection
In the proposed BN-WVAD, we leverage the Divergence of Feature from Mean vector (DFM) of BatchNorm as a reliable abnormality criterion to discern potential abnormal snippets in abnormal videos.
Anomaly Detection In Surveillance Videos
Weakly-supervised Video Anomaly Detection
X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention
Inspired by this observation, we introduce a lightweight and powerful alternative, Spatially Unidimensional Self-Attention (SUSA), to the pointwise (1x1) convolution that is the main computational bottleneck in the depthwise separable 3c3 convolution.
Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis
The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style.
MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection
Unsupervised anomaly detection (UAD) attracts a lot of research interest and drives widespread applications, where only anomaly-free samples are available for training.
Ranked #9 on
Anomaly Detection
on MVTec AD
ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition
To overcome this bottleneck, we leverage class priors to restrict the generalization scope of the class-agnostic SAM and propose a class-aware smoothness optimization algorithm named Imbalanced-SAM (ImbSAM).
Semi-supervised Anomaly Detection
Supervised Anomaly Detection
AnoOnly: Semi-Supervised Anomaly Detection with the Only Loss on Anomalies
Unlike existing SSAD methods that resort to strict loss supervision, AnoOnly suspends it and introduces a form of weak supervision for normal data.
Semi-supervised Anomaly Detection
Supervised Anomaly Detection
+1
KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences
Human densepose estimation, aiming at establishing dense correspondences between 2D pixels of human body and 3D human body template, is a key technique in enabling machines to have an understanding of people in images.
A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
In this paper, we propose a span-based Mandarin prosodic structure prediction model to obtain an optimal prosodic structure tree, which can be converted to corresponding prosodic label sequence.
Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis
In this paper, we propose a hierarchical framework to model speaking style from context.
Post-training Quantization for Neural Networks with Provable Guarantees
Additionally, our error analysis expands the results of previous work on GPFQ to handle general quantization alphabets, showing that for quantizing a single-layer network, the relative square error essentially decays linearly in the number of weights -- i. e., level of over-parametrization.
Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis
Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS).
Syntactic representation learning for neural network based TTS with syntactic parse tree traversal
Meanwhile, nuclear-norm maximization loss is introduced to enhance the discriminability and diversity of the embeddings of constituent labels.
