Related papers: VAE-based Domain Adaptation for Speaker Verificati…

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable…

Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings. In this paper, the content-aware speaker embeddings…

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training strategy to enable the…

In this paper, we propose a novel way of addressing text-dependent automatic speaker verification (TD-ASV) by using a shared-encoder with task-specific decoders. An autoregressive predictive coding (APC) encoder is pre-trained in an…

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…

We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using paired (parallel) reverberant-clean speech, we trained a…

Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully…

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…

While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability. Speaking rate mismatch is often observed in practical speaker…

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. This paper proposes a hierarchical network with transformer encoders and memory mechanism to address this problem. The proposed…

We propose an approach for training speaker identification models in a weakly supervised manner. We concentrate on the setting where the training data consists of a set of audio recordings and the speaker annotation is provided only at the…

Decoding speech from non-invasive brain signals, such as electroencephalography (EEG), has the potential to advance brain-computer interfaces (BCIs), with applications in silent communication and assistive technologies for individuals with…

Most of the prevalent approaches in speech prosody modeling rely on learning global style representations in a continuous latent space which encode and transfer the attributes of reference speech. However, recent work on neural codecs which…

Recent research shows that deep neural networks (DNNs) can be used to extract deep speaker vectors (d-vectors) that preserve speaker characteristics and can be used in speaker verification. This new method has been tested on text-dependent…

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…

Neural speaker embeddings trained using classification objectives have demonstrated state-of-the-art performance in multiple applications. Typically, such embeddings are trained on an out-of-domain corpus on a single task e.g., speaker…

In previous work, we proposed a variational autoencoder-based (VAE) Bayesian permutation training speech enhancement (SE) method (PVAE) which indicated that the SE performance of the traditional deep neural network-based (DNN) method could…

The generalizability of speech enhancement (SE) models across speaker conditions remains largely unexplored, despite its critical importance for broader applicability. This paper investigates the performance of the hybrid variational…

Performance degradation caused by language mismatch is a common problem when applying a speaker verification system on speech data in different languages. This paper proposes a domain transfer network, named EDITnet, to alleviate the…