Search Results for author:
Found 20 papers, 7 papers with code
Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech
In this study, we propose a fine-grained preference optimization approach (FPO) to enhance the robustness of TTS systems.
GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training
Given the significant differences between geometric diagram-symbol and natural image-text, we introduce unimodal pre-training to develop a diagram encoder and symbol decoder, enhancing the understanding of geometric images and corpora.
OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems.
Chimera: Improving Generalist Model with Domain-Specific Experts
This results in a versatile model that excels across the chart, table, math, and document domains, achieving state-of-the-art performance on multi-modal reasoning and visual content extraction tasks, both of which are challenging tasks for assessing existing LMMs.
StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching
Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content.
ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving
Offboard perception aims to automatically generate high-quality 3D labels for autonomous driving (AD) scenes.
CTEFM-VC: Zero-Shot Voice Conversion Based on Content-Aware Timbre Ensemble Modeling and Flow Matching
Zero-shot voice conversion (VC) aims to transform the timbre of a source speaker into any previously unseen target speaker, while preserving the original linguistic content.
Takin-ADA: Emotion Controllable Audio-Driven Animation with Canonical and Landmark Loss Optimization
We discovered that these issues stem from limitations in motion representation and the lack of fine-grained control over facial expressions.
Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling
Expressive zero-shot voice conversion (VC) is a critical and challenging task that aims to transform the source timbre into an arbitrary unseen speaker while preserving the original content and expressive qualities.
Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models
In this report, we introduce Takin AudioLLM, a series of techniques and models, mainly including Takin TTS, Takin VC, and Takin Morphing, specifically designed for audiobook production.
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models
Scientific documents record research findings and valuable human knowledge, comprising a vast corpus of high-quality data.
PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders
In this paper, we propose PSCodec, a series of neural speech codecs based on prompt encoders, comprising PSCodec-Base, PSCodec-DRL-ICT, and PSCodec-CasAN, which are capable of delivering high-performance speech reconstruction with low bandwidths.
ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning
Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously.
OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous Driving
With the development of implicit rendering technology and in-depth research on using generative models to produce data at scale, we propose OASim, an open and adaptive simulator and autonomous driving data generator based on implicit neural rendering.
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations
Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e. g., autonomous driving, yet it still remains notoriously labor-intensive.
PromptVC: Flexible Stylistic Voice Conversion in Latent Space Driven by Natural Language Prompts
In this study, we propose PromptVC, a novel style voice conversion approach that employs a latent diffusion model to generate a style vector driven by natural language prompts.
METTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer
However, such data-efficient approaches have ignored synthesizing emotional aspects of speech due to the challenges of cross-speaker cross-lingual emotion transfer - the heavy entanglement of speaker timbre, emotion, and language factors in the speech signal will make a system produce cross-lingual synthetic speech with an undesired foreign accent and weak emotion expressiveness.
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
Extensive experiments on Waymo Open Dataset show our DetZero outperforms all state-of-the-art onboard and offboard 3D detection methods.
Ranked #1 on
3D Multi-Object Tracking
on Waymo Open Dataset
MASNet:Improve Performance of Siamese Networks with Mutual-attention for Remote Sensing Change Detection Tasks
In this work we present Mutual-Attention Siamese Network (MASNet), a general siamese network with mutual-attention plug-in, so to exchange information between the two feature extraction branches.
Improving Cross-lingual Speech Synthesis with Triplet Training Scheme
Recent advances in cross-lingual text-to-speech (TTS) made it possible to synthesize speech in a language foreign to a monolingual speaker.
