Next-generation Deep-fake Detection Technology Using Frequency Masks
Next-generation Deep-fake Detection Technology Using Frequency Masks
Fake Detection
List of New AI Articles
![FreqNet] Generic Dee](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/freqnet-520x300.png)
FreqNet] Generic Deep Fake Detection By Learning In Frequency Space
FreqNet] Generic Deep Fake Detection By Learning In Frequency Space
Fake Detection
![DIFFUSSM] Attention-](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/diffussm_1_-520x300.png)
DIFFUSSM] Attention-independent Diffusion Model
DIFFUSSM] Attention-independent Diffusion Model
Image Generation
Self-supervised ViT With Deep Fake Detection
Self-supervised ViT With Deep Fake Detection
Self-supervised Learning
![[SpliceBERT] A BERT](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/splicebert-520x300.png)
[SpliceBERT] A BERT Model That Pre-trains With The Genetic Information Of A Species!
[SpliceBERT] A BERT Model That Pre-trains With The Genetic Information Of A Species!
Medical
![[IGModel] Methodolog](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/igmodel-520x300.png)
[IGModel] Methodology Applying GNN+Attention Mechanism Improves Practicality In Drug Discovery
[IGModel] Methodology Applying GNN+Attention Mechanism Improves Practicality In Drug Discovery
Medical
Models Reward Themselves And Train Themselves!
Models Reward Themselves And Train Themselves!
Self Rewarding
![[JMMLU] Prompt Polit](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/jmmlu-520x300.png)
[JMMLU] Prompt Politeness Affects LLM Performance!
[JMMLU] Prompt Politeness Affects LLM Performance!
ChatGPT
Generating Dysarthric Speech! What Is The Magic Data Extension Technology To Solve The Shortage Of Training Data?
Generating Dysarthric Speech! What Is The Magic Data Extension Technology To Solve The Shortage Of T ...
Sound
![[Unit-DSR] Normaliza](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/unit-dsr-520x300.png)
[Unit-DSR] Normalization Of Disabled Speech To Normal Speech By HuBERT
[Unit-DSR] Normalization Of Disabled Speech To Normal Speech By HuBERT
Self-supervised Learning
![[Review] Industrial](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/iiot-review-520x300.png)
[Review] Industrial IoT Driving Smart Manufacturing
[Review] Industrial IoT Driving Smart Manufacturing
Internet Of Things
Enhanced Defect Detection Using Tensor CNN
Enhanced Defect Detection Using Tensor CNN
Tensor
![[Double Descent] Why](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/double_descent-520x300.png)
[Double Descent] Why Are "large Models" And "large Data Sets" Important?
[Double Descent] Why Are "large Models" And "large Data Sets" Important?
Neural Network
![[Chat-REC] Proposal](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/chat-rec-520x300.png)
[Chat-REC] Proposal For LLM-based Recommendation System
[Chat-REC] Proposal For LLM-based Recommendation System
Recommendation
![[HiFi-GAN] GAN-based](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/July2024/hifi-gan-520x300.png)
[HiFi-GAN] GAN-based Vocoder Capable Of Generating 22 KHz Audio On A Single GPU
[HiFi-GAN] GAN-based Vocoder Capable Of Generating 22 KHz Audio On A Single GPU
Speech Synthesis
Latent Diffusion Models Do Not Necessarily "increase In Size"
Latent Diffusion Models Do Not Necessarily "increase In Size"
Diffusion Model
![[Mustango] Music Gen](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/June2024/mustango-520x300.png)
[Mustango] Music Generation Model Utilizing Domain Knowledge Of Music
[Mustango] Music Generation Model Utilizing Domain Knowledge Of Music
Audio And Speech Processing
![[VoiceCraft] A Langu](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/June2024/voice-craft-520x300.png)
[VoiceCraft] A Language Model That Synthesizes Natural Speech At The Highest Level In The Industry
[VoiceCraft] A Language Model That Synthesizes Natural Speech At The Highest Level In The Industry
Speech Synthesis