A survey on neural speech synthesis
Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural
speech given text, is a hot research topic in speech, language, and machine learning …
speech given text, is a hot research topic in speech, language, and machine learning …
Adaspeech: Adaptive text to speech for custom voice
Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims
to adapt a source TTS model to synthesize personal voice for a target speaker using few …
to adapt a source TTS model to synthesize personal voice for a target speaker using few …
Review of end-to-end speech synthesis technology based on deep learning
Z Mu, X Yang, Y Dong - arXiv preprint arXiv:2104.09995, 2021 - arxiv.org
As an indispensable part of modern human-computer interaction system, speech synthesis
technology helps users get the output of intelligent machine more easily and intuitively, thus …
technology helps users get the output of intelligent machine more easily and intuitively, thus …
Non-attentive tacotron: Robust and controllable neural tts synthesis including unsupervised duration modeling
This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-to-speech model,
replacing the attention mechanism with an explicit duration predictor. This improves …
replacing the attention mechanism with an explicit duration predictor. This improves …
GANSpeech: Adversarial training for high-fidelity multi-speaker speech synthesis
Recent advances in neural multi-speaker text-to-speech (TTS) models have enabled the
generation of reasonably good speech quality with a single model and made it possible to …
generation of reasonably good speech quality with a single model and made it possible to …
Accented text-to-speech synthesis with limited data
This paper presents an accented text-to-speech (TTS) synthesis framework with limited
training data. We study two aspects concerning accent rendering: phonetic (phoneme …
training data. We study two aspects concerning accent rendering: phonetic (phoneme …
Emovie: A mandarin emotion speech dataset with a simple emotional text-to-speech model
Recently, there has been an increasing interest in neural speech synthesis. While the deep
neural network achieves the state-of-the-art result in text-to-speech (TTS) tasks, how to …
neural network achieves the state-of-the-art result in text-to-speech (TTS) tasks, how to …
Non-autoregressive TTS with explicit duration modelling for low-resource highly expressive speech
Whilst recent neural text-to-speech (TTS) approaches produce high-quality speech, they
typically require a large amount of recordings from the target speaker. In previous work, a 3 …
typically require a large amount of recordings from the target speaker. In previous work, a 3 …
Residual adapters for few-shot text-to-speech speaker adaptation
Adapting a neural text-to-speech (TTS) model to a target speaker typically involves fine-
tuning most if not all of the parameters of a pretrained multi-speaker backbone model …
tuning most if not all of the parameters of a pretrained multi-speaker backbone model …
Voice filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module
State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data
to generate high-quality synthetic speech. When using reduced amounts of training data …
to generate high-quality synthetic speech. When using reduced amounts of training data …