SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.02256 · NeurIPS · 2024

Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs

Stavros Petridis, Maja Pantic, Zoe Landgraf, Alexandros Haliassos, Rodrigo Mira, Honglie Chen

arXiv · PDF · Open in the Atlas

Code that ran

3 of 9 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 6 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/2411.02256.json · badge: /api/ran/2411.02256.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
ahaliassos/usr canonical (classifier label)
classifier basis: census
3 ran · 6 no recorded run
FunctionStatusWhere it lives
get_cer Ran
ran, honoured the contract we drafted
ahaliassos/usr/metrics.py
pointer only (licence: NONE) · get_code("c97dab612dfcc0bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

get_er Ran
ran, honoured the contract we drafted
ahaliassos/usr/metrics.py
pointer only (licence: NONE) · get_code("f646df9b796b4337")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

get_wer Ran
ran, honoured the contract we drafted
ahaliassos/usr/metrics.py
pointer only (licence: NONE) · get_code("f0ad236b3b39fdaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

adadelta_eps_decay Not yet run
unverified (harvested, no recorded run)
ahaliassos/usr/espnet/asr/asr_utils.py
pointer only (licence: NONE) · get_code("bb3665ddb6b8dd2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

adam_lr_decay Not yet run
unverified (harvested, no recorded run)
ahaliassos/usr/espnet/asr/asr_utils.py
pointer only (licence: NONE) · get_code("1fa5ca494ed9750a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

batch_shuffle_ddp Not yet run
unverified (harvested, no recorded run)
ahaliassos/usr/models/utils.py
pointer only (licence: NONE) · get_code("c844dae8bf36cb0d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

batch_unshuffle_ddp Not yet run
unverified (harvested, no recorded run)
ahaliassos/usr/models/utils.py
pointer only (licence: NONE) · get_code("1ac98ef4b97d4dfc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

concat_all_gather Not yet run
unverified (harvested, no recorded run)
ahaliassos/usr/models/utils.py
pointer only (licence: NONE) · get_code("63d6be75146d60ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

restore_snapshot Not yet run
unverified (harvested, no recorded run)
ahaliassos/usr/espnet/asr/asr_utils.py
pointer only (licence: NONE) · get_code("96081a60369c59e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahaliassos/usr 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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
adadelta_eps_decay 7 other papers
6 dated earlier, 1 later
2007.09127 (2020-07)
CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition
2010.11148 (2020-10)
FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
2022.findings-emnlp.402 (2022 (year only))
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
and 4 more not named here
adam_lr_decay 7 other papers
6 dated earlier, 1 later
2007.09127 (2020-07)
CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition
2010.11148 (2020-10)
FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
2022.findings-emnlp.402 (2022 (year only))
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
and 4 more not named here
restore_snapshot 7 other papers
6 dated earlier, 1 later
2007.09127 (2020-07)
CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition
2010.11148 (2020-10)
FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
2022.findings-emnlp.402 (2022 (year only))
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
and 4 more not named here
batch_unshuffle_ddp 2 other papers
2 dated earlier
2103.16607 (2021-03)
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data
2211.15059 (2022-11)
Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
get_er 2 other papers
2 dated earlier
2308.06112 (2023-08)
Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
2404.02098 (2024-04)
BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition
get_wer 2 other papers
2 dated earlier
2308.06112 (2023-08)
Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
2404.02098 (2024-04)
BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition
concat_all_gather 1 other paper
1 dated earlier
2201.07131 (2022-01)
Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
get_cer 1 other paper
1 dated earlier
2404.02098 (2024-04)
BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory 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

Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to yield separate models, leading to disjoint inference pipelines with increased memory requirements and redundancies. This paper proposes unified training strategies for these systems. We demonstrate that training a single model for all three tasks enhances VSR and AVSR performance, overcoming typical optimisation challenges when training from scratch. Moreover, we introduce a greedy pseudo-labelling approach to more effectively leverage unlabelled samples, addressing shortcomings in related self-supervised methods. Finally, we develop a self-supervised pretraining method within our framework, proving its effectiveness alongside our semi-supervised approach. Despite using a single model for all tasks, our unified approach achieves state-of-the-art performance compared to recent methods on LRS3 and LRS2 for ASR, VSR, and AVSR, as well as on the newly released WildVSR dataset. Code and models are available at https://github.com/ ahaliassos/usr.

For agents

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

get_harvested_code_for_paper("2411.02256")
get_code_for_paper("2411.02256")
have("2411.02256")

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

curl https://syntology.ai/api/ran/2411.02256.json

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

[![Syntology run record](https://syntology.ai/api/ran/2411.02256.svg)](https://syntology.ai/paper/2411.02256)

Connect an agent — have() is free.