A5110372538- Speech Recognition and Synthesis
- Speech and Audio Processing
- Chemical Looping and Thermochemical Processes
- Music and Audio Processing
- Insect Resistance and Genetics
- Catalysis and Oxidation Reactions
- Analytical chemistry methods development
- Adsorption and Cooling Systems
- Speech and dialogue systems
- Consumer Perception and Purchasing Behavior
- Ecology and Conservation Studies
- Freezing and Crystallization Processes
- Topic Modeling
- Pesticide and Herbicide Environmental Studies
- Forest ecology and management
- Phase Change Materials Research
- Pesticide Residue Analysis and Safety
- Diverse Topics in Contemporary Research
- Advanced Photocatalysis Techniques
- Catalytic Processes in Materials Science
- Technology Adoption and User Behaviour
- Advancements in Solid Oxide Fuel Cells
- Metallurgical Processes and Thermodynamics
- Climate change impacts on agriculture
- Education and Work Dynamics
Chinese Academy of Sciences
2006-2025
Laboratoire Procédés, Matériaux et Energie Solaire
2025
University of Chinese Academy of Sciences
2022-2025
Institute of Electrical Engineering
2022-2025
Centre National de la Recherche Scientifique
2025
Microsoft Research Asia (China)
2024
China University of Mining and Technology
2021-2022
Jeonbuk National University
2022
State Key Laboratory for Geomechanics and Deep Underground Engineering
2021
Shanghai Ocean University
2012-2017
Text-to-speech (TTS) has made rapid progress in both academia and industry recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality, how to define/judge it. In this paper, we answer these by first defining the quality based on statistical significance of subjective measure introducing appropriate guidelines judge it, then developing called NaturalSpeech achieves benchmark datasets. Specifically, leverage variational auto-encoder (VAE) for...
Text to speech (TTS) has made rapid progress in both academia and industry recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality, how define/judge quality it. In this paper, we answer these by first defining the based on statistical significance of subjective measure introducing appropriate guidelines judge it, then developing called NaturalSpeech achieves benchmark dataset. Specifically, leverage variational autoencoder (VAE) for end-to-end...
Several recent studies have attempted to autoregressively generate continuous speech representations without discrete tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive computational loads or suboptimal outcomes. In this work, we propose Diffusion Transformer Autoregressive Modeling (DiTAR), a patch-based framework language model transformer. This approach significantly enhances the efficacy of models for reduces demands. DiTAR utilizes...
The redox activity of perovskite materials was tuned by an active cation doping strategy to promote two-step CO 2 splitting for sustainable solar fuel production.
Abstract Background The emergence, resurgence and spread of human food-borne pathogenic Vibrios are one the major contributors to disease burden mortality particularly in developing countries with disputable sanitary conditions. Previous research on Vibrio cholerae parahaemolitycus derived from clinical samples has proposed links between acquisition virulence multiple drug resistance traits intercellular transmissibility mobile genetic elements environment. To date, very few information is...
We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as foundation model for generation and excels in in-context learning, achieving performance speaker similarity naturalness matches ground truth both objective subjective evaluations. With fine-tuning, we achieve even higher scores across these metrics. offers superior controllability over various attributes...
Carboxylesterase-based metabolic resistance to organophosphates (OPs) in insects has been shown originate either from mutations esterase-encoding sequences or amplification of esterase genes. This study aimed test the hypothesis that mosquitoes can acquire OP by functional changes carboxylesterases. Mutations were introduced into B1 mosquito Culex pipiens site-directed mutagenesis at positions 110 and 224. Three single mutants (G110D, W224L, W224S) two double (G110D/W224L G110D/W224S)...
Optimized Quick, Easy, Cheap, Effective, Rugged, and Safe (QuEChERS) pretreatment methods for determination of six polychlorinated biphenyls (PCBs) residues in fish aquatic invertebrates samples were investigated. Large volume injection (LVI) coupled gas chromatography tandem mass spectrometry (GC-MS/MS) with selected reaction monitoring (SRM) was used to provide a very sensitive selective means analyzing PCBs via internal calibration. Three analytical processes validated compared, the...
In this paper, we propose VISinger, a complete end-to-end high-quality singing voice synthesis (SVS) system that directly generates audio waveform from lyrics and musical score. Our approach is inspired by VITS, which adopts VAE-based posterior encoder augmented with normalizing flow-based prior adversarial decoder to realize speech generation. VISinger follows the main architecture of but makes substantial improvements based on characteristics singing. First, instead using phoneme-level...
The water-splitting mechanism-supported material design of a novel Cr-perovskite by Zr doping and ceria mixing for promising H 2 production.
Connotation and extension of practical teaching mode were thought about after seven year-practice specialty construction for Food Quality Safety in Shanghai Ocean University.Omni-bearing multi-layer system was constructed, within which methodology explored, standard quality upgraded.More students with capability innovative spirit cultivated have become talents the fields food analysis, safety assessment, management control.