Speaker verification is the verifying the identity of a person from characteristics of the voice.
In this study, we explore end-to-end deep neural networks that input raw waveforms to improve various aspects: front-end speaker embedding extraction including model architecture, pre-training scheme, additional objective functions, and back-end classification.
This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations.
This thesis describes our ongoing work on Contrastive Predictive Coding (CPC) features for speaker verification.
In this work, we propose our replay attacks detection system - Attentive Filtering Network, which is composed of an attention-based filtering mechanism that enhances feature representations in both the frequency and time domains, and a ResNet-based classifier.
Most current state-of-the-art text-independent speaker verification systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers.
Rather than employing standard hand-crafted features, the latter CNNs learn low-level speech representations from waveforms, potentially allowing the network to better capture important narrow-band speaker characteristics such as pitch and formants.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
SOTA for Text-To-Speech Synthesis on LJSpeech (using extra training data)
Our second contribution is to apply and compare various state of the art speaker identification techniques on our dataset to establish baseline performance.
The performance of speaker-related systems usually degrades heavily in practical applications largely due to the presence of background noise.