Related papers: StyleSpeech: Self-supervised Style Enhancing with …
Recent advances in text-to-speech have significantly improved the expressiveness of synthesized speech. However, it is still challenging to generate speech with contextually appropriate and coherent speaking style for multi-sentence text in…
With the demand for autonomous control and personalized speech generation, the style control and transfer in Text-to-Speech (TTS) is becoming more and more important. In this paper, we propose a new TTS system that can perform style…
Previous works on expressive speech synthesis focus on modelling the mono-scale style embedding from the current sentence or context, but the multi-scale nature of speaking style in human speech is neglected. In this paper, we propose a…
We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…
This paper introduces the Procedural (audio) Variational autoEncoder (ProVE) framework as a general approach to learning Procedural Audio PA models of environmental sounds with an improvement to the realism of the synthesis while…
Speech synthesis systems powered by neural networks hold promise for multimedia production, but frequently face issues with producing expressive speech and seamless editing. In response, we present the Cross-Utterance Conditioned…
Translation quality estimation (TQE) is the task of predicting translation quality without reference translations. Due to the enormous cost of creating training data for TQE, only a few translation directions can benefit from supervised…
Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such…
A large part of the expressive speech synthesis literature focuses on learning prosodic representations of the speech signal which are then modeled by a prior distribution during inference. In this paper, we compare different prior…
Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using…
This paper proposes a WaveNet-based neural excitation model (ExcitNet) for statistical parametric speech synthesis systems. Conventional WaveNet-based neural vocoding systems significantly improve the perceptual quality of synthesized…
We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis. We also examine choice of neural vocoder for waveform synthesis, as well as…
Recent advances in expressive text-to-speech (TTS) have introduced diverse methods based on style embedding extracted from reference speech. However, synthesizing high-quality expressive speech remains challenging. We propose Spotlight-TTS,…
Expressive speech synthesis is crucial for many human-computer interaction scenarios, such as audiobooks, podcasts, and voice assistants. Previous works focus on predicting the style embeddings at one single scale from the information…
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…
Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech. Such models typically incorporate a fine-grained variational autoencoder (VAE) structure, extracting…
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…
Automatic speech quality assessment plays a crucial role in the development of speech synthesis systems, but existing models exhibit significant performance variations across different granularity levels of prediction tasks. This paper…
Recent research showed that an autoencoder trained with speech of a single speaker, called exemplar autoencoder (eAE), can be used for any-to-one voice conversion (VC). Compared to large-scale many-to-many models such as AutoVC, the eAE…
The single-speaker singing voice synthesis (SVS) usually underperforms at pitch values that are out of the singer's vocal range or associated with limited training samples. Based on our previous work, this work proposes a…