SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.04664 · 2020

MultiSpeech: Multi-Speaker Text to Speech with Transformer

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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 0 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; 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/2006.04664.json · badge: /api/ran/2006.04664.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
msalhab96/MultiSpeech community (classifier label)
classifier basis not recorded on the link
1 ran · 3 no recorded run
FunctionStatusWhere it lives
check_token Ran
ran; our contract draft was wrong, not the code
msalhab96/MultiSpeech/decorators.py
code served (permissive licence) · get_code("d628d5db04cc8d70")
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 torch
from functools import wraps
from typing import Callable

# Create a stand-in object that has the _token_to_id attribute
class TokenContainer:
    def __init__(self, token_to_id):
        self._token_to_id = token_to_id
    
    def some_fallback_method(self, token):
        """Fallback method that would be called if token not in _token_to_id"""
        return f"processed_{token}"

# Create test data
token_to_id_dict = {
    "hello": 0,
    "world": 1,
    "test": 2
}

test_obj = TokenContainer(token_to_id_dict)
test_token = "hello"

ARGS = {
    "token": test_token
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — 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
get_loss_args Not yet run
unverified (harvested, no recorded run)
msalhab96/MultiSpeech/args.py
code served (permissive licence) · get_code("26de4b25e88f447f")
How it ran

no invocation recorded.

get_model_args Not yet run
unverified (harvested, no recorded run)
msalhab96/MultiSpeech/args.py
code served (permissive licence) · get_code("615a08d96f9d874b")
How it ran

no invocation recorded.

get_optim_args Not yet run
unverified (harvested, no recorded run)
msalhab96/MultiSpeech/args.py
code served (permissive licence) · get_code("9eee3124c66ae10d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
check_token 1 other paper
1 dated earlier
2005.08100 (2020-05)
Conformer: Convolution-augmented Transformer for Speech Recognition

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 2026-11-22.

Repositories linked to this paper

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

Abstract

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., Tacotron~\cite{shen2018natural}) due to its parallel computation in training and/or inference. However, the parallel computation increases the difficulty while learning the alignment between text and speech in Transformer, which is further magnified in the multi-speaker scenario with noisy data and diverse speakers, and hinders the applicability of Transformer for multi-speaker TTS. In this paper, we develop a robust and high-quality multi-speaker Transformer TTS system called MultiSpeech, with several specially designed components/techniques to improve text-to-speech alignment: 1) a diagonal constraint on the weight matrix of encoder-decoder attention in both training and inference; 2) layer normalization on phoneme embedding in encoder to better preserve position information; 3) a bottleneck in decoder pre-net to prevent copy between consecutive speech frames. Experiments on VCTK and LibriTTS multi-speaker datasets demonstrate the effectiveness of MultiSpeech: 1) it synthesizes more robust and better quality multi-speaker voice than naive Transformer based TTS; 2) with a MutiSpeech model as the teacher, we obtain a strong multi-speaker FastSpeech model with almost zero quality degradation while enjoying extremely fast inference speed.

For agents

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

get_harvested_code_for_paper("2006.04664")
get_code_for_paper("2006.04664")
have("2006.04664")

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

curl https://syntology.ai/api/ran/2006.04664.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.04664.svg)](https://syntology.ai/paper/2006.04664)

Connect an agent — have() is free.