paper-with-me

Papers

Generative Adversarial Training for Text-to-Speech Synthesis Based on Raw Phonetic Input and Explicit Prosody Modelling

2023-10-14 · Tiberiu Boros, Stefan Daniel Dumitrescu, Ionut Mironica, Radu Chivereanu

We describe an end-to-end speech synthesis system that uses generative adversarial training. We train our Vocoder for raw phoneme-to-audio conversion, using explicit phonetic, pitch and duration modeling. We experiment with several pre-trained models for contextualized and decontextualized word embeddings and we introduce a new method for highly expressive character voice matching, based on discreet style tokens.

📄 PDF Abstract BibTeX arXiv:2310.09636

Code (1)

tiberiu44/TTS-Cube 공식 구현 pytorch

Tasks

Speech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisWord Embeddings

Similar Papers 제목 키워드 기반

GANtron: Emotional Speech Synthesis with Generative Adversarial Networks

2021-10-06 · Enrique Hortal, Rodrigo Brechard Alarcia

Speech synthesis is used in a wide variety of industries. Nonetheless, it always sounds flat or robotic. The state of the art methods that allow for prosody control are very cumbersome to use and do not allow easy tuning…

Emotional Speech SynthesisSpeech Synthesistext-to-speechText to Speech

DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs

2022-01-28 · Songxiang Liu, Dan Su, Dong Yu

Denoising diffusion probabilistic models (DDPMs) are expressive generative models that have been used to solve a variety of speech synthesis problems. However, because of their high sampling costs, DDPMs are difficult to…

DenoisingSpeech Synthesistext-to-speechText to Speech

Waveform generation for text-to-speech synthesis using pitch-synchronous multi-scale generative adversarial networks

2018-10-30 · Lauri Juvela, Bajibabu Bollepalli, Junichi Yamagishi, Paavo Alku

The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference pro…

Image GenerationSpeech Synthesistext-to-speechText to Speech+2

RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks

2022-07-14 · Mohammad Esmaeilpour, Nourhene Chaalia, Patrick Cardinal

This paper introduces a new synthesis-based defense algorithm for counteracting with a varieties of adversarial attacks developed for challenging the performance of the cutting-edge speech-to-text transcription systems. …

Speech-to-Text

Generative adversarial network-based glottal waveform model for statistical parametric speech synthesis

2019-03-14 · Bajibabu Bollepalli, Lauri Juvela, Paavo Alku

Recent studies have shown that text-to-speech synthesis quality can be improved by using glottal vocoding. This refers to vocoders that parameterize speech into two parts, the glottal excitation and vocal tract, that occ…

Generative Adversarial NetworkSpeech Synthesistext-to-speechText to Speech+1