paper-with-me

Papers

Tacotron: Towards End-to-End Speech Synthesis

2017-03-29 · Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, Quoc Le, Yannis Agiomyrgiannakis, Rob Clark, Rif A. Saurous

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given <text, audio> pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this challenging task. Tacotron achieves a 3.82 subjective 5-scale mean opinion score on US English, outperforming a production parametric system in terms of naturalness. In addition, since Tacotron generates speech at the frame level, it's substantially faster than sample-level autoregressive methods.

📄 PDF Abstract BibTeX arXiv:1703.10135

Code (30)

0fengzi0/tacotron tf
CorentinJ/Real-Time-Voice-Cloning tf
IvKosar/text2speech pytorch
Kyubyong/tacotron tf
OlaWod/my-tacotron2 pytorch
PaddlePaddle/PaddleSpeech paddle
ShuSQ/CCI_AP_PoseLoops tf
TensorSpeech/TensorflowTTS tf
anandaswarup/TTS pytorch
anandaswarup/rnn-tts pytorch
andabi/deep-voice-conversion tf
andabi/voice-vector tf
barronalex/Tacotron tf
cchinchristopherj/Concert-of-Whales
coqui-ai/TTS pytorch
dipjyoti92/SC-WaveRNN pytorch
dipjyoti92/TTS-Style-Transfer pytorch
fatchord/WaveRNN pytorch
izzajalandoni/tts_models pytorch
keithito/tacotron tf
keonlee9420/Comprehensive-Tacotron2 pytorch
mindmapper15/Voice-Converter tf
mozilla/TTS pytorch
r9y9/tacotron_pytorch pytorch
racinmat/lecture-generator tf
shortpoet/Final-Project
thethirdwheel/malumagraph
thuhcsi/tacotron pytorch
tigthor/Voice-Cloning-AI pytorch
vohoaiviet/voice-vector tf

Tasks

Audio SynthesisSpeech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Methods 이 논문이 사용한 방법론

Griffin-Lim Algorithm The Griffin-Lim Algorithm (GLA) is a phase reconstruction method based on the redundancy of the short-time Fourier transform. It promotes the consistency of a spectrogram by…
Sigmoid Activation 설명 없음
Highway Layer 설명 없음
Residual GRU A Residual GRU is a gated recurrent unit (GRU) that incorporates the idea of residual connections from…
BiGRU A Bidirectional GRU, or BiGRU, is a sequence processing model that consists of two GRUs. one taking the input in a forward…
Highway Network A Highway Network is an architecture designed to ease gradient-based training of very deep networks. They allow unimpeded information flow across several layers on…
Residual Connection 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Modeling Prosodic Phrasing with Multi-Task Learning in Tacotron-based TTS

2020-08-11 · Rui Liu, Berrak Sisman, Feilong Bao, Guanglai Gao 외

Tacotron-based end-to-end speech synthesis has shown remarkable voice quality. However, the rendering of prosody in the synthesized speech remains to be improved, especially for long sentences, where prosodic phrasing er…

Multi-Task LearningSpeech Synthesis

Audiovisual Speech Synthesis using Tacotron2

2020-08-03 · Ahmed Hussen Abdelaziz, Anushree Prasanna Kumar, Chloe Seivwright, Gabriele Fanelli 외

Audiovisual speech synthesis is the problem of synthesizing a talking face while maximizing the coherency of the acoustic and visual speech. In this paper, we propose and compare two audiovisual speech synthesis systems …

Face ModelSentenceSpeech Synthesis

Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron

2018-03-24 · ICML 2018 7 · RJ Skerry-Ryan, Eric Battenberg, Ying Xiao, Yuxuan Wang 외

We present an extension to the Tacotron speech synthesis architecture that learns a latent embedding space of prosody, derived from a reference acoustic representation containing the desired prosody. We show that conditi…

Expressive Speech SynthesisSpeech Synthesis

Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesis

2018-08-30 · Yu-An Chung, Yuxuan Wang, Wei-Ning Hsu, Yu Zhang 외

Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In thi…

DecoderSpeech Synthesistext-to-speechText to Speech

ITAcotron 2: Transfering English Speech Synthesis Architectures and Speech Features to Italian

2021-11-01 · ICNLSP 2021 11 · Anna Favaro, Licia Sbattella, Roberto Tedesco, Vincenzo Scotti
Speech Synthesis