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

Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data remains a significant challenge in the field. Self-supervised…

The research in Deep Learning applications in sound and music computing have gathered an interest in the recent years; however, there is still a missing link between these new technologies and on how they can be incorporated into real-world…

State-of-the-art speaker recognition systems comprise an x-vector (or i-vector) speaker embedding front-end followed by a probabilistic linear discriminant analysis (PLDA) backend. The effectiveness of these components relies on the…

In our previous work, we proposed a language-independent speaker anonymization system based on self-supervised learning models. Although the system can anonymize speech data of any language, the anonymization was imperfect, and the speech…

The goal of this paper is to adapt speaker embeddings for solving the problem of speaker diarisation. The quality of speaker embeddings is paramount to the performance of speaker diarisation systems. Despite this, prior works in the field…

In this work, we investigate the effectiveness of two techniques for improving variational autoencoder (VAE) based voice conversion (VC). First, we reconsider the relationship between vocoder features extracted using the high quality…

Recently, an audio-visual speech generative model based on variational autoencoder (VAE) has been proposed, which is combined with a nonnegative matrix factorization (NMF) model for noise variance to perform unsupervised speech enhancement.…

Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injected in their stochastic hidden layer, with a regularizer…

Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model the global interaction between token embeddings, it is…

Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of…

Deep metric learning has been demonstrated to be highly effective in learning semantic representation and encoding information that can be used to measure data similarity, by relying on the embedding learned from metric learning. At the…

An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoencoders to learn…

One of the obstacles in many-to-many voice conversion is the requirement of the parallel training data, which contain pairs of utterances with the same linguistic content spoken by different speakers. Since collecting such parallel data is…

Domain adaptation solves the learning problem in a target domain by leveraging the knowledge in a relevant source domain. While remarkable advances have been made, almost all existing domain adaptation methods heavily require large amounts…

Voice conversion has made great progress in the past few years under the studio-quality test scenario in terms of speech quality and speaker similarity. However, in real applications, test speech from source speaker or target speaker can be…

Voice conversion is a challenging task which transforms the voice characteristics of a source speaker to a target speaker without changing linguistic content. Recently, there have been many works on many-to-many Voice Conversion (VC) based…

Recent advancements in learning Discrete Representations as opposed to continuous ones have led to state of art results in tasks that involve Language, Audio and Vision. Some latent factors such as words, phonemes and shapes are better…

The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. On the other…

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…

For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could be useful for…