Separating Content from Speaker Identity in Speech for the Assessment of Cognitive Impairments
원문 초록
Deep speaker embeddings have been shown effective for assessing cognitive impairments aside from their original purpose of speaker verification. However, the research found that speaker embeddings encode speaker identity and an array of information, including speaker demographics, such as sex and age, and speech contents to an extent, which are known confounders in the assessment of cognitive impairments. In this paper, we hypothesize that content information separated from speaker identity using a framework for voice conversion is more effective for assessing cognitive impairments and train simple classifiers for the comparative analysis on the DementiaBank Pitt Corpus. Our results show that while content embeddings have an advantage over speaker embeddings for the defined problem, further experiments show their effectiveness depends on information encoded in speaker embeddings due to the inherent design of the architecture used for extracting contents.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning
ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
SKQVC: One-Shot Voice Conversion by K-Means Quantization with Self-Supervised Speech Representations
CTEFM-VC: Zero-Shot Voice Conversion Based on Content-Aware Timbre Ensemble Modeling and Flow Matching
USTC-KXDIGIT System Description for ASVspoof5 Challenge
AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge
토론
이 논문과 연결된 포럼 글이 아직 없습니다.