Phonetic information and linguistic knowledge are an essential component...
Neural text-to-speech systems are often optimized on L1/L2 losses, which...
The Grapheme-to-Phoneme (G2P) task aims to convert orthographic input in...
The availability of data in expressive styles across languages is limite...
The research community has long studied computer-assisted pronunciation
...
State-of-the-art text-to-speech (TTS) systems require several hours of
r...
We address the problem of cross-speaker style transfer for text-to-speec...
Artificial speech synthesis has made a great leap in terms of naturalnes...
Voice Conversion (VC) is a technique that aims to transform the
non-ling...
Many factors influence speech yielding different renditions of a given
s...
We propose a weakly-supervised model for word-level mispronunciation
det...
Developing Text Normalization (TN) systems for Text-to-Speech (TTS) on n...
A common approach to the automatic detection of mispronunciation in lang...
Emotional voice conversion models adapt the emotion in speech without
ch...
This paper describes two novel complementary techniques that improve the...
Recently the state-of-the-art text-to-speech synthesis systems have shif...
While recent neural text-to-speech (TTS) systems perform remarkably well...
We present an approach to synthesize whisper by applying a handcrafted s...
Recent advances in Text-to-Speech (TTS) have improved quality and natura...
We propose a Text-to-Speech method to create an unseen expressive style ...
Nowadays vast amounts of speech data are recorded from low-quality recor...
Neural text-to-speech synthesis (NTTS) models have shown significant pro...
Recent speech synthesis systems based on sampling from autoregressive ne...
This paper introduces a robust universal neural vocoder trained with 74
...
Voice conversion (VC) aims at conversion of speaker characteristic witho...
We present the Voice Conversion Challenge 2018, designed as a follow up ...
Recent advances in speech synthesis suggest that limitations such as the...
Although voice conversion (VC) algorithms have achieved remarkable succe...
Thanks to the growing availability of spoofing databases and rapid advan...