SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.05457 · ICLR · 2024

It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition

Pin-Yu Chen, Chen Chen, Chao-Han Huck, Yuchen Hu, Sabato Siniscalchi, Eng Siong Chng, Ruizhe Li

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; 1 honoured the contract we drafted, 0 violated it and 1 has 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/2402.05457.json · badge: /api/ran/2402.05457.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
Hypotheses-Paradise/UADF community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
build_rope_cache Ran
ran, honoured the contract we drafted
Hypotheses-Paradise/UADF/lit_llama/model.py
code served (permissive licence) · get_code("8a187cb05b43141d")
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 Tensor, ndim 3, dtype family float, shape (8, 2, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

ARGS = {
    "seq_len": 8,
    "n_elem": 4,
    "dtype": torch.float32,
    "device": torch.device("cpu"),
    "base": 10000,
}
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 Tensor, ndim 3, dtype family float, shape (8, 2, 2) — shape (8, 2, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
loss_fn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Hypotheses-Paradise/UADF/finetune/adapter.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Gary3410/TaPA, is pointer only (licence: NONE) · get_code("b3207d2a276b9a79")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Gary3410/TaPA, 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.

mask_nan Ran
ran on a synthesized input
Hypotheses-Paradise/UADF/generate_uadf.py
code served (permissive licence) · get_code("300525ba88b085e0")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create a tensor with some NaN values
x = torch.tensor([
    [1.0, float('nan'), 3.0, 4.0],
    [float('nan'), 2.0, float('nan'), 5.0]
])

ARGS = {
    "x": x
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
apply_rope Not yet run
unverified (harvested, no recorded run)
Hypotheses-Paradise/UADF/lit_llama/model.py
code served (permissive licence) · get_code("7137105772c52074")
How it ran

no invocation recorded.

compute_confidence Not yet run
unverified (harvested, no recorded run)
Hypotheses-Paradise/UADF/generate_uadf.py
code served (permissive licence) · get_code("c8644d93f21cdf49")
How it ran

no invocation recorded.

load_eval_data Not yet run
unverified (harvested, no recorded run)
Hypotheses-Paradise/UADF/evaluate/adapter.py
code served (permissive licence) · get_code("854aeb584ed6b2b0")
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, 3 are also present in other papers whose code we hold (3 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
apply_rope 3 other papers
3 dated earlier
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
2310.06434 (2023-10)
Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition
2310.08581 (2023-10)
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
build_rope_cache 3 other papers
3 dated earlier
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
2310.06434 (2023-10)
Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition
2310.08581 (2023-10)
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
loss_fn 1 other paper
1 dated earlier
2307.01848 (2023-07)
Embodied Task Planning with Large Language Models

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

Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. Specifically, an LLM is utilized to carry out a direct mapping from the N-best hypotheses list generated by an ASR system to the predicted output transcription. However, despite its effectiveness, GER introduces extra data uncertainty since the LLM is trained without taking into account acoustic information available in the speech signal. In this work, we aim to overcome such a limitation by infusing acoustic information before generating the predicted transcription through a novel late fusion solution termed Uncertainty-Aware Dynamic Fusion (UADF). UADF is a multimodal fusion approach implemented into an auto-regressive decoding process and works in two stages: (i) It first analyzes and calibrates the token-level LLM decision, and (ii) it then dynamically assimilates the information from the acoustic modality. Experimental evidence collected from various ASR tasks shows that UADF surpasses existing fusion mechanisms in several ways. It yields significant improvements in word error rate (WER) while mitigating data uncertainty issues in LLM and addressing the poor generalization relied with sole modality during fusion. We also demonstrate that UADF seamlessly adapts to audio-visual speech recognition.

For agents

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

get_harvested_code_for_paper("2402.05457")
get_code_for_paper("2402.05457")
have("2402.05457")

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

curl https://syntology.ai/api/ran/2402.05457.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.05457.svg)](https://syntology.ai/paper/2402.05457)

Connect an agent — have() is free.