Related papers: Learning Disentangled Phone and Speaker Representa…

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable models have been shown to learn nontrivial…

We describe our submitted system for the ZeroSpeech Challenge 2019. The current challenge theme addresses the difficulty of constructing a speech synthesizer without any text or phonetic labels and requires a system that can (1) discover…

Wav2vec-C introduces a novel representation learning technique combining elements from wav2vec 2.0 and VQ-VAE. Our model learns to reproduce quantized representations from partially masked speech encoding using a contrastive loss in a way…

Nowadays, recognition-synthesis-based methods have been quite popular with voice conversion (VC). By introducing linguistics features with good disentangling characters extracted from an automatic speech recognition (ASR) model, the VC…

Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label…

In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very close to phoneme sequences of speech utterances. This is…

Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent…

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning…

In this paper, we report our submitted system for the ZeroSpeech 2020 challenge on Track 2019. The main theme in this challenge is to build a speech synthesizer without any textual information or phonetic labels. In order to tackle those…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

Traditional studies on voice conversion (VC) have made progress with parallel training data and known speakers. Good voice conversion quality is obtained by exploring better alignment modules or expressive mapping functions. In this study,…

Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…

Self-supervised speech representations are known to encode both speaker and phonetic information, but how they are distributed in the high-dimensional space remains largely unexplored. We hypothesize that they are encoded in orthogonal…

Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been developed. However,…

In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in…

Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content information in…

Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to…