Papers › PortaSpeech: Portable and High-Quality Generative Text-to-Speech

PortaSpeech: Portable and High-Quality Generative Text-to-Speech

30 Sep 2021NeurIPS 2021 12arXiv:2109.15166archive 2025-07-28

Yi Ren, Jinglin Liu, Zhou Zhao

Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we find that: VAE is good at capturing the long-range semantics features (e.g., prosody) even with small model size but suffers from blurry and unnatural results; and normalizing flow is good at reconstructing the frequency bin-wise details but performs poorly when the number of model parameters is limited. Inspired by these observations, to generate diverse speech with natural details and rich prosody using a lightweight architecture, we propose PortaSpeech, a portable and high-quality generative text-to-speech model. Specifically, 1) to model both the prosody and mel-spectrogram details accurately, we adopt a lightweight VAE with an enhanced prior followed by a flow-based post-net with strong conditional inputs as the main architecture. 2) To further compress the model size and memory footprint, we introduce the grouped parameter sharing mechanism to the affine coupling layers in the post-net. 3) To improve the expressiveness of synthesized speech and reduce the dependency on accurate fine-grained alignment between text and speech, we propose a linguistic encoder with mixture alignment combining hard inter-word alignment and soft intra-word alignment, which explicitly extracts word-level semantic information. Experimental results show that PortaSpeech outperforms other TTS models in both voice quality and prosody modeling in terms of subjective and objective evaluation metrics, and shows only a slight performance degradation when reducing the model parameters to 6.7M (about 4x model size and 3x runtime memory compression ratio compared with FastSpeech 2). Our extensive ablation studies demonstrate that each design in PortaSpeech is effective.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples: 11 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 12: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 7 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

natspeech/natspeech officialmentioned in paperpytorchMITSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
MoonInTheRiver/DiffSinger mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning the Beauty in Songs: Neural Singing Voice Beautifier (arXiv:2202.13277; that paper's own run record: 13 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
RayeRen/RayeRen mentioned on GitHubSyntology: not harvested report
keonlee9420/PortaSpeech mentioned on GitHubpytorchMITSyntology: 7 samples, 7 ran (1 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
6ran

Licence: 6 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

natspeech/natspeech official repository 4 samples, 4 ran (1 instrument-failed) · 0 unverified
Embedding in 90 papers modules/commons/layers.py ran MIT (permissive) · a025408166aaff26 · report fixture: signature num_embeddings:int/0/int, embedding_dim:int/0/int, padding_idx:NoneType/0/? · returned Embedding · level recorded 2026-09-25
fused_add_tanh_sigmoid_multiply in 11 papers modules/commons/wavenet.py ran MIT (permissive) · 03f2c896fd1d86dc · report fixture: signature input_a:Tensor/3/float, input_b:Tensor/3/float, n_channels:list/1/int · returned Tensor · level recorded 2026-09-24
sequence_mask in 55 papers
census: 12 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
modules/commons/rel_transformer.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 88bf809d1bc9db4c · report fixture: signature length:Tensor/1/int, max_length:NoneType/0/? · returned Tensor · level recorded 2026-09-22
shift_1d modules/commons/rel_transformer.py ran fingerprinted MIT (permissive) · 2173110241f356ce · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
keonlee9420/PortaSpeech community (archive-listed) 7 samples, 7 ran (1 instrument-failed) · 0 unverified
convert_pad_shape in 15 papers model/blocks.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 59ae0708b1e8d94b · report fixture: signature pad_shape:list/1/list · returned list · level recorded 2026-09-22
fused_add_tanh_sigmoid_multiply in 11 papers model/blocks.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · b38f9c28c5117398 · report fixture: returned Tensor · level recorded 2026-09-22
get_padding in 84 papers hifigan/models.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · a26f85d7c72ef39a · report fixture: signature kernel_size:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
get_sinusoid_encoding_table in 51 papers model/linguistic_encoder.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 0f8f22937463d3c5 · report fixture: signature n_position:int/0/int, d_hid:int/0/int, padding_idx:int/0/int · returned Tensor · level recorded 2026-09-22
pad_input in 16 papers model/postnet.py ran MIT (permissive) · ee17504855eec917 · report fixture: signature x:Tensor/3/float, x_mask:Tensor/3/float, g:Tensor/3/float, n_sqz:int/0/int · returned tuple · level recorded 2026-09-24
squeeze in 92 papers model/postnet.py ran MIT (permissive) · 3feb059fe1daeee2 · report fixture: signature x:Tensor/3/float, x_mask:Tensor/3/float, g:Tensor/3/float, n_sqz:int/0/int · returned tuple · level recorded 2026-09-24
unsqueeze in 8 papers model/postnet.py ran MIT (permissive) · c058572344c8f736 · report fixture: signature x:Tensor/3/float, x_mask:Tensor/3/float, g:Tensor/3/float, n_sqz:int/0/int, pad_size:int/0/int · returned tuple · level recorded 2026-09-24
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
read_lexicon in 16 papers repository not located ran · our draft was wrong licence of this copy not recorded · 2b5c06c1ba593c3c · report fixture: signature lex_path:str/0/str · returned dict · level recorded, date not recorded

Tasks

Text to SpeechText-To-Speech SynthesisVocal Bursts Intensity PredictionWord Alignmenttext-to-speech

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Activation NormalizationAffine CouplingAttentionDense ConnectionsDropoutFastSpeech 2GLOWGlow-TTSInvertible 1x1 ConvolutionLayer NormalizationLinear LayerMulti-Head AttentionNormalizing FlowsPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmax

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