The performance of spoofing countermeasure systems depends fundamentally upon the use
of sufficiently representative training data. With this usually being limited, current solutions …

Conventionally, the extraction of hand-crafted acoustic features has been separated from the
task of establishing robust machine-learning models in speech processing. The manual …

In recent years, speaker recognition systems based on raw waveform inputs have received
increasing attention. However, the performance of such systems are typically inferior to the …

The majority of recent state-of-the-art speaker verification architectures adopt multi-scale
processing and frequency-channel attention mechanisms. Convolutional layers of these …

Time-domain approaches have shown the potential to improve the performance of speaker
verification, but still predominant approaches utilize hand-crafted features such as the mel …

The convolutional neural network (CNN) based approaches have shown great success for
speaker verification (SV) tasks, where modeling long temporal context and reducing …

As the durations of the short utterances are small, it is difficult to learn sufficient information
to distinguish the person, thus, short utterance speaker recognition is highly challenging. In …

In this paper, we propose a more efficient lightweight speaker recognition network, the multi-
level attention network (MANet). MANet aims to generate more robust and discriminative …

Speaker verification (SV) performance deteriorates as utterances become shorter. To this
end, we propose a new architecture called VoiceExtender which provides a promising …

As an attractive research in biometric authentication, Text Independent Speaker Verification
(TI-SV) problem aims to specify whether two given unconstrained utterances come from the …