Related papers: Learning Disentangled Phone and Speaker Representa…

Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting.…

We study the problem of cross-lingual voice conversion in non-parallel speech corpora and one-shot learning setting. Most prior work require either parallel speech corpora or enough amount of training data from a target speaker. However, we…

The human perception system is often assumed to recruit motor knowledge when processing auditory speech inputs. Using articulatory modeling and deep learning, this study examines how this articulatory information can be used for discovering…

This paper presents an analysis of speech synthesis quality achieved by simultaneously performing voice conversion and language code-switching using multilingual VQ-VAE speech synthesis in German, French, English and Italian. In this paper,…

Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based…

Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However,…

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. In this paper, a hierarchical attention network is proposed to solve a weakly labelled speaker identification problem. The use of…

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e.g., videos and audios) under self-supervision. Specifically, we exploit the benefits of some readily accessible supervisory signals…

By representing speaker characteristic as a single fixed-length vector extracted solely from speech, we can train a neural multi-speaker speech synthesis model by conditioning the model on those vectors. This model can also be adapted to…

This study tackles unsupervised subword modeling in the zero-resource scenario, learning frame-level speech representation that is phonetically discriminative and speaker-invariant, using only untranscribed speech for target languages.…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

The primary characteristic of robust speaker representations is that they are invariant to factors of variability not related to speaker identity. Disentanglement of speaker representations is one of the techniques used to improve…

One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize that the training…

Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but…

In recent years, extending variational autoencoder's framework to learn disentangled representations has received much attention. We address this problem by proposing a framework capable of disentangling class-related and class-independent…

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,…

In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…

Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between different speakers using parallel data, which is expensive to…

One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement. Existing work generally…