Related papers: Deep Representation Decomposition for Rate-Invaria…
Unsupervised speech disentanglement aims at separating fast varying from slowly varying components of a speech signal. In this contribution, we take a closer look at the embedding vector representing the slowly varying signal components,…
The objective of this work is to train noise-robust speaker embeddings adapted for speaker diarisation. Speaker embeddings play a crucial role in the performance of diarisation systems, but they often capture spurious information such as…
In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings. In contrast to the traditional approaches that build their speaker embeddings using manually hand-crafted…
A number of studies have successfully developed speaker verification or presentation attack detection systems. However, studies integrating the two tasks remain in the preliminary stages. In this paper, we propose two approaches for…
This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…
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…
Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful…
A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning…
Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…
Separating different speaker properties from a multi-speaker environment is challenging. Instead of separating a two-speaker signal in signal space like speech source separation, a speaker embedding de-mixing approach is proposed. The…
Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…
Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate…
Verifying the identity of a speaker is crucial in modern human-machine interfaces, e.g., to ensure privacy protection or to enable biometric authentication. Classical speaker verification (SV) approaches estimate a fixed-dimensional…
Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…
Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…
Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are…
Developing a good speaker embedding has received tremendous interest in the speech community, with representations such as i-vector and d-vector demonstrating remarkable performance across various tasks. Despite their widespread adoption, a…
In this paper, we propose self-supervised speaker representation learning strategies, which comprise of a bootstrap equilibrium speaker representation learning in the front-end and an uncertainty-aware probabilistic speaker embedding…
The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in…
Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to…