相关论文: Adversarial Speaker Disentanglement Using Unannota…
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…
Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody…
In this paper, we propose a semi-supervised learning (SSL) technique for training deep neural networks (DNNs) to generate speaker-discriminative acoustic embeddings (speaker embeddings). Obtaining large amounts of speaker recognition…
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and…
Traditional voice conversion (VC) methods typically attempt to separate speaker identity and linguistic information into distinct representations, which are then combined to reconstruct the audio. However, effectively disentangling these…
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.…
The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…
We present a large-scale comparative study of self-supervised speech representation (S3R)-based voice conversion (VC). In the context of recognition-synthesis VC, S3Rs are attractive owing to their potential to replace expensive supervised…
Recently, voice conversion (VC) has been widely studied. Many VC systems use disentangle-based learning techniques to separate the speaker and the linguistic content information from a speech signal. Subsequently, they convert the voice by…
We present a method for converting the voices between a set of speakers. Our method is based on training multiple autoencoder paths, where there is a single speaker-independent encoder and multiple speaker-dependent decoders. The…
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…
Singing Voice Synthesis (SVS) has witnessed significant advancements with the advent of deep learning techniques. However, a significant challenge in SVS is the scarcity of labeled singing voice data, which limits the effectiveness of…
The goal of voice conversion is to transform the speech of a source speaker to sound like that of a reference speaker while preserving the original content. A key challenge is to extract disentangled linguistic content from the source and…
Non-parallel voice conversion aims to convert voice from a source domain to a target domain without paired training data. Cycle-Consistent Generative Adversarial Networks (CycleGAN) and Variational Autoencoders (VAE) have been used for this…
Speech enhancement has recently achieved great success with various deep learning methods. However, most conventional speech enhancement systems are trained with supervised methods that impose two significant challenges. First, a majority…
Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that…
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…
With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models,…
Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing. Recent works also investigated SSL from speech. They were notably successful to improve performance on…
As a foundational technology for intelligent human-computer interaction, voice conversion (VC) seeks to transform speech from any source timbre into any target timbre. Traditional voice conversion methods based on Generative Adversarial…