paper-with-me

Papers

FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

2020-06-08 · ICLR 2021 1 · Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu

Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated and time-consuming, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of fully end-to-end inference. Experimental results show that 1) FastSpeech 2 achieves a 3x training speed-up over FastSpeech, and FastSpeech 2s enjoys even faster inference speed; 2) FastSpeech 2 and 2s outperform FastSpeech in voice quality, and FastSpeech 2 can even surpass autoregressive models. Audio samples are available at https://speechresearch.github.io/fastspeech2/.

📄 PDF Abstract BibTeX arXiv:2006.04558

Code (37)

2024-MindSpore-1/Code2/tree/main/model-1/fastspeech2_conformer mindspore
KevinMIN95/StyleSpeech pytorch
Munna-Manoj/Team6_FastSpeech2_TTS pytorch
OlaWod/my-fastspeech2 pytorch
PaddlePaddle/PaddleSpeech paddle
RayeRen/RayeRen
TensorSpeech/TensorflowTTS tf
ai-unicamp/tts-objective-metrics pytorch
as-ideas/TransformerTTS tf
cadia-lvl/fastspeech2 pytorch
coqui-ai/TTS pytorch
dathudeptrai/TensorflowTTS tf
ga642381/FastSpeech2 pytorch
galaxycong/hpmdubbing pytorch
keonlee9420/Comprehensive-E2E-TTS pytorch
keonlee9420/Comprehensive-Transformer-TTS pytorch
keonlee9420/DiffSinger pytorch
keonlee9420/Expressive-FastSpeech2 pytorch
keonlee9420/PortaSpeech pytorch
keonlee9420/STYLER pytorch
keonlee9420/StyleSpeech pytorch
komyeongjin/specdiff-gan pytorch
majidAdibian77/ResGrad pytorch
ming024/FastSpeech2 pytorch
mtresearcher/FastSpeech2 pytorch
ndkgit339/fastspeech2-filled_pause_speech_synthesis pytorch
rishikksh20/FastSpeech2 pytorch
rishikksh20/LightSpeech pytorch
roedoejet/fastspeech2 pytorch
roedoejet/fastspeech2_acl2022_reproducibility pytorch
shivammehta25/BetterFastSpeech2 pytorch
tartunlp/transformertts tf
wataru-nakata/fastspeech2-jsut pytorch
xcmyz/FastSpeech pytorch
yangyucheng000/University/tree/main/model-2/fastspeech2_conformer mindspore
yoshifumi-nakano/visual-text-to-speech pytorch
zhangbo2008/fastSpeeck2_chinese_train pytorch

Tasks

Knowledge DistillationSpeech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Methods 이 논문이 사용한 방법론

Attention 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Batch Normalization 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis

2021-06-29 · Jinhyeok Yang, Jae-Sung Bae, Taejun Bak, Youngik Kim 외

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 synthesize the speech of a speaker with limite…

Speech Synthesistext-to-speechText to SpeechVocal Bursts Intensity Prediction

Towards Natural and Controllable Cross-Lingual Voice Conversion Based on Neural TTS Model and Phonetic Posteriorgram

2021-02-03 · Shengkui Zhao, Hao Wang, Trung Hieu Nguyen, Bin Ma

Cross-lingual voice conversion (VC) is an important and challenging problem due to significant mismatches of the phonetic set and the speech prosody of different languages. In this paper, we build upon the neural text-to…

text-to-speechText to SpeechVoice Conversion

MultiSpeech: Multi-Speaker Text to Speech with Transformer

2020-06-08 · Mingjian Chen, Xu Tan, Yi Ren, Jin Xu 외

Transformer-based text to speech (TTS) model (e.g., Transformer TTS~\cite{li2019neural}, FastSpeech~\cite{ren2019fastspeech}) has shown the advantages of training and inference efficiency over RNN-based model (e.g., Taco…

Decodertext-to-speechText to Speech

SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis

2023-08-02 · Ramanan Sivaguru, Vasista Sai Lodagala, S Umesh

While FastSpeech2 aims to integrate aspects of speech such as pitch, energy, and duration as conditional inputs, it still leaves scope for richer representations. As a part of this work, we leverage representations from …

DecoderSelf-Supervised LearningSpeech Synthesistext-to-speech+2

Towards Robust FastSpeech 2 by Modelling Residual Multimodality

2023-06-02 · Fabian Kögel, Bac Nguyen, Fabien Cardinaux

State-of-the-art non-autoregressive text-to-speech (TTS) models based on FastSpeech 2 can efficiently synthesise high-fidelity and natural speech. For expressive speech datasets however, we observe characteristic audio d…

Decodertext-to-speechText to Speech