Methods › Audio › Text-to-Speech Models › FastSpeech 2s
FastSpeech 2s
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.
FastSpeech 2s is a text-to-speech model that abandons mel-spectrograms as intermediate output completely and directly generates speech waveform from text during inference. In other words there is no cascaded mel-spectrogram generation (acoustic model) and waveform generation (vocoder). FastSpeech 2s generates waveform conditioning on intermediate hidden, which makes it more compact in inference by discarding the mel-spectrogram decoder.
Two main design changes are made to the waveform decoder.
First, considering that the phase information is difficult to predict using a variance predictor, adversarial training is used in the waveform decoder to force it to implicitly recover the phase information by itself.
Secondly, the mel-spectrogram decoder of FastSpeech 2 is leveraged, which is trained on the full text sequence to help on the text feature extraction. As shown in the Figure, the waveform decoder is based on the structure of WaveNet including non-causal convolutions and gated activation. The waveform decoder takes a sliced hidden sequence corresponding to a short audio clip as input and upsamples it with transposed 1D-convolution to match the length of audio clip. The discriminator in the adversarial training adopts the same structure in Parallel WaveGAN, which consists of ten layers of non-causal dilated 1-D convolutions with leaky ReLU activation function. The waveform decoder is optimized by the multi-resolution STFT loss and the LSGAN discriminator loss following Parallel WaveGAN.
In inference, the mel-spectrogram decoder is discarded and only the waveform decoder is used to synthesize speech audio.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 37 in the graph, strongest link: mentioned on GitHub). This answer is about arXiv:2006.04558, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2006.04558 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified (of 119 harvested samples) · 40 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 1 · with a code link: 1 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 1 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: paper 1 of 1, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech 8 Jun 2020 · 37 repositories · arXiv:2006.04558Syntology 83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified (of 119 harvested samples) · 40 pointer-only (licence)
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Knowledge Distillation | 1 |
| Speech Synthesis | 1 |
| Text to Speech | 1 |
| Text-To-Speech Synthesis | 1 |
| text-to-speech | 1 |
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