Methods › Audio › Text-to-Speech Models › FastSpeech 2
FastSpeech 2
Introduced by Yi Ren et al. in FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
FastSpeech2 is a text-to-speech model that aims to improve upon FastSpeech by better solving the one-to-many mapping problem in TTS, i.e., multiple speech variations corresponding to the same text. It attempts to solve this problem 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, in FastSpeech 2, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference.
The encoder converts the phoneme embedding sequence into the phoneme hidden sequence, and then the variance adaptor adds different variance information such as duration, pitch and energy into the hidden sequence, finally the mel-spectrogram decoder converts the adapted hidden sequence into mel-spectrogram sequence in parallel. FastSpeech 2 uses a feed-forward Transformer block, which is a stack of self-attention and 1D-convolution as in FastSpeech, as the basic structure for the encoder and mel-spectrogram decoder.
Papers archive 2025-07-28
20 shown of 20, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
AMNet: An Acoustic Model Network for Enhanced Mandarin Speech Synthesis 12 Apr 2025 · 0 repositories · arXiv:2504.09225
-
AMuSeD: An Attentive Deep Neural Network for Multimodal Sarcasm Detection Incorporating Bi-modal Data Augmentation 13 Dec 2024 · 0 repositories · arXiv:2412.10103
-
Training Universal Vocoders with Feature Smoothing-Based Augmentation Methods for High-Quality TTS Systems 4 Sep 2024 · 0 repositories · arXiv:2409.02517
-
AttentionStitch: How Attention Solves the Speech Editing Problem 5 Mar 2024 · 0 repositories · arXiv:2403.04804
-
Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors 25 Oct 2023 · 2 repositories · arXiv:2310.16609
-
Energy-Based Models For Speech Synthesis 19 Oct 2023 · 0 repositories · arXiv:2310.12765
-
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation 11 Oct 2023 · 1 repository · arXiv:2310.07403Syntology ran 5 of 7 samples · 2 unverified · 7 pointer-only (licence)
-
Towards Robust FastSpeech 2 by Modelling Residual Multimodality 2 Jun 2023 · 1 repository · arXiv:2306.01442
-
The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech 1 Jun 2023 · 0 repositories · arXiv:2306.00535
-
LibriS2S: A German-English Speech-to-Speech Translation Corpus 22 Apr 2022 · 1 repository · arXiv:2204.10593
-
Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech 31 Mar 2022 · 0 repositories · arXiv:2203.17190
-
ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis 20 Mar 2022 · 1 repository · arXiv:2203.10473
-
Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus 20 Dec 2021 · 2 repositories · arXiv:2112.10358Syntology ran 0 of 2 samples · 2 unverified
-
Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data 15 Nov 2021 · 0 repositories · arXiv:2111.07549
-
PortaSpeech: Portable and High-Quality Generative Text-to-Speech 30 Sep 2021 · 4 repositories · arXiv:2109.15166Syntology ran 6 of 12 samples · 6 unverified · 1 pointer-only (licence)
-
One TTS Alignment To Rule Them All 23 Aug 2021 · 3 repositories · arXiv:2108.10447
-
Digital Einstein Experience: Fast Text-to-Speech for Conversational AI 21 Jul 2021 · 0 repositories · arXiv:2107.10658
-
Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech 6 Mar 2021 · 1 repository · arXiv:2103.04088
-
Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators 27 Oct 2020 · 0 repositories · arXiv:2010.14151
-
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech 8 Jun 2020 · 37 repositories · arXiv:2006.04558Syntology ran 73 of 119 samples · 46 unverified · 33 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 36 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections