Deep Neural Networks for Automatic Speaker Recognition Do Not Learn Supra-Segmental Temporal Features
원문 초록
While deep neural networks have shown impressive results in automatic speaker recognition and related tasks, it is dissatisfactory how little is understood about what exactly is responsible for these results. Part of the success has been attributed in prior work to their capability to model supra-segmental temporal information (SST), i.e., learn rhythmic-prosodic characteristics of speech in addition to spectral features. In this paper, we (i) present and apply a novel test to quantify to what extent the performance of state-of-the-art neural networks for speaker recognition can be explained by modeling SST; and (ii) present several means to force respective nets to focus more on SST and evaluate their merits. We find that a variety of CNN- and RNN-based neural network architectures for speaker recognition do not model SST to any sufficient degree, even when forced. The results provide a highly relevant basis for impactful future research into better exploitation of the full speech signal and give insights into the inner workings of such networks, enhancing explainability of deep learning for speech technologies.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CoLMbo: Speaker Language Model for Descriptive Profiling
Private kNN-VC: Interpretable Anonymization of Converted Speech
SEED: Speaker Embedding Enhancement Diffusion Model
USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction
VoxSim: A perceptual voice similarity dataset
Reshape Dimensions Network for Speaker Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.