arXiv:2203.04638
Speaker Identification Experiments Under Gender De-Identification
원문 초록
The present work is based on the COST Action IC1206 for De-identification in multimedia content. It was performed to test four algorithms of voice modifications on a speech gender recognizer to find the degree of modification of pitch when the speech recognizer have the probability of success equal to the probability of failure. The purpose of this analysis is to assess the intensity of the speech tone modification, the quality, the reversibility and not-reversibility of the changes made. Keywords DeIdentification; Speech Algorithms
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Privacy-Utility Balanced Voice De-Identification Using Adversarial Examples
Enhancing Clinical Models with Pseudo Data for De-identification
CoLMbo: Speaker Language Model for Descriptive Profiling
Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings
Zero-shot generation of synthetic neurosurgical data with large language models
The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.