SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.01950 · 2020

AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2003.01950.json · badge: /api/ran/2003.01950.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mangushev/aligntts community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
dropout Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mangushev/aligntts/model.py
pointer only (licence: MIT); the stored copy get_code serves, from huawei-noah/Pretrained-Language-Model, is pointer only (licence: NONE) · get_code("873e08c3f15eb1e4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from huawei-noah/Pretrained-Language-Model, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_input_fn Ran
ran on a synthesized input
mangushev/aligntts/training.py
code served (permissive licence) · get_code("4d570a07b66b39b3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import tempfile
import os

# Create a minimal FLAGS object with required attributes
class FLAGS:
    max_input_length = 10
    max_mel_length = 8
    num_mels = 5
    dataset_reader_buffer_size = 100
    shuffle_buffer_size = 50

# Create a temporary TFRecord file with sample data
def create_sample_tfrecord(filename):
    writer = tf.io.TFRecordWriter(filename)
    
    for i in range(2):
        # Create sample data matching the expected schema
        input_data = [1, 2, 3, 4, 5, 0, 0, 0, 0, 0]  # max_input_length = 10
        input_length = 5
        input_mask = [1, 1, 1, 1, 1, 0, 0, 0, 0, 0]
        input_durations = [1, 1, 1, 1, 1, 0, 0, 0, 0, 0]
        mel_data = [[0.1] * 5 for _ in range(8)]  # max_mel_length=8, num_mels=5
        mel_length = 8
        guid = i
        
        feature = {
            'input': tf.train.Feature(int64_list=tf.train.Int64List(value=input_data)),
            'input_length': tf.train.Feature(int64_list=tf.train.Int64List(value=[input_length])),
            'input_mask': tf.train.Feature(int64_list=tf.train.Int64List(value=input_mask)),
            'input_durations': tf.train.Feature(int64_list=tf.train.Int64List(value=input_durations)),
            'mel': tf.train.Feature(float_list=tf.train.FloatList(value=[item for sublist in mel_data for item in sublist])),
            'mel_length': tf.train.Feature(int64_list=tf.train.Int64List(value=[mel_length])),
            'guid': tf.train.Feature(int64_list=tf.train.Int64List(value=[guid])),
        }
        
        example = tf.train.Example(features=tf.train.Features(feature=feature))
        writer.write(example.SerializeToString())
    
    writer.close()

# Create temporary file
temp_dir = tempfile.gettempdir()
tfrecord_file = os.path.join(temp_dir, "sample.tfrecord")
create_sample_tfrecord(tfrecord_file)

ARGS = {
    "filename": [tfrecord_file],
    "is_training": True,
    "drop_reminder": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reshape_to_matrix Ran
ran; our contract draft was wrong, not the code
mangushev/aligntts/model.py
pointer only (licence: MIT); the stored copy get_code serves, from huawei-noah/Pretrained-Language-Model, is pointer only (licence: NONE) · get_code("7b84f3e6a96584b4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from huawei-noah/Pretrained-Language-Model, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

audio_example Not yet run
unverified (harvested, no recorded run)
mangushev/aligntts/prepare_data.py
code served (permissive licence) · get_code("8e282dee546609ce")
How it ran

no invocation recorded.

get_assignment_map_from_checkpoint Not yet run
unverified (harvested, no recorded run)
mangushev/aligntts/training.py
pointer only (licence: MIT); the stored copy get_code serves, from toggle1995/RIS-DMMI, is pointer only (licence: NONE) · get_code("50958618b65e514e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from toggle1995/RIS-DMMI, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

reshape_from_matrix Not yet run
unverified (harvested, no recorded run)
mangushev/aligntts/model.py
code served (permissive licence) · get_code("3370499aacadb239")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_assignment_map_from_checkpoint 26 other papers
16 dated earlier, 10 later
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1808.09781 (2018-08)
Self-Attentive Sequential Recommendation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 23 more not named here
dropout 9 other papers
3 dated earlier, 6 later · 4 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1808.09781 (2018-08)
Self-Attentive Sequential Recommendation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 6 more not named here
reshape_from_matrix 8 other papers
3 dated earlier, 5 later · 2 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1808.09781 (2018-08)
Self-Attentive Sequential Recommendation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 5 more not named here
reshape_to_matrix 7 other papers
3 dated earlier, 4 later · 4 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1808.09781 (2018-08)
Self-Attentive Sequential Recommendation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 4 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor.Instead of adopting the attention mechanism in Transformer TTS to align text to mel-spectrum, the alignment loss is presented to consider all possible alignments in training by use of dynamic programming. Experiments on the LJSpeech dataset show that our model achieves not only state-of-the-art performance which outperforms Transformer TTS by 0.03 in mean option score (MOS), but also a high efficiency which is more than 50 times faster than real-time.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.01950")
get_code_for_paper("2003.01950")
have("2003.01950")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2003.01950.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2003.01950.svg)](https://syntology.ai/paper/2003.01950)

Connect an agent — have() is free.