Related papers: Speaker diarization using latent space clustering …
Speaker diarization determines who spoke and when? in an audio stream. In this study, we propose a model-based approach for robust speaker clustering using i-vectors. The ivectors extracted from different segments of same speaker are…
Speaker diarization is usually referred to as the task that determines ``who spoke when'' in a recording. Until a few years ago, all competitive approaches were modular. Systems based on this framework reached state-of-the-art performance…
Speaker diarization, the process of segmenting an audio stream or transcribed speech content into homogenous partitions based on speaker identity, plays a crucial role in the interpretation and analysis of human speech. Most existing…
Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings -- maps of matching words across languages -- without supervision. Despite these successes, GANs' performance for the difficult case of distant…
The x-vector maps segments of arbitrary duration to vectors of fixed dimension using deep neural network. Combined with the probabilistic linear discriminant analysis (PLDA) backend, the x-vector/PLDA has become the dominant framework in…
This paper describes the system developed by the BUT team for the fourth track of the VoxCeleb Speaker Recognition Challenge, focusing on diarization on the VoxConverse dataset. The system consists of signal pre-processing, voice activity…
Generative adversarial networks (GANs) have an enormous potential impact on digital content creation, e.g., photo-realistic digital avatars, semantic content editing, and quality enhancement of speech and images. However, the performance of…
Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped…
Applying generative adversarial networks (GANs) to text-related tasks is challenging due to the discrete nature of language. One line of research resolves this issue by employing reinforcement learning (RL) and optimizing the next-word…
The recently proposed VBx diarization method uses a Bayesian hidden Markov model to find speaker clusters in a sequence of x-vectors. In this work we perform an extensive comparison of performance of the VBx diarization with other…
Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch between training and test conditions. This study puts…
Current Generative Adversarial Network (GAN)-based approaches for time series generation face challenges such as suboptimal convergence, information loss in embedding spaces, and instability. To overcome these challenges, we introduce an…
In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation methods have been successfully used for eliminating the domain…
We propose two new techniques for training Generative Adversarial Networks (GANs). Our objectives are to alleviate mode collapse in GAN and improve the quality of the generated samples. First, we propose neighbor embedding, a manifold…
Bayesian HMM clustering of x-vector sequences (VBx) has become a widely adopted diarization baseline model in publications and challenges. It uses an HMM to model speaker turns, a generatively trained probabilistic linear discriminant…
Image clustering has recently attracted significant attention due to the increased availability of unlabelled datasets. The efficiency of traditional clustering algorithms heavily depends on the distance functions used and the…
Automatic Speaker Verification (ASV) suffers from performance degradation in noisy conditions. To address this issue, we propose a novel adversarial learning framework that incorporates noise-disentanglement to establish a noise-independent…
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the…
Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode…
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions.…