Papers › Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning

Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning

21 Sep 2016arXiv:1609.06773archive 2025-07-28

Suyoun Kim, Takaaki Hori, Shinji Watanabe

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping between variable-length input and output sequences in one step using a purely data-driven method. The attention model has often been shown to improve the performance over another end-to-end approach, the Connectionist Temporal Classification (CTC), mainly because it explicitly uses the history of the target character without any conditional independence assumptions. However, we observed that the performance of the attention has shown poor results in noisy condition and is hard to learn in the initial training stage with long input sequences. This is because the attention model is too flexible to predict proper alignments in such cases due to the lack of left-to-right constraints as used in CTC. This paper presents a novel method for end-to-end speech recognition to improve robustness and achieve fast convergence by using a joint CTC-attention model within the multi-task learning framework, thereby mitigating the alignment issue. An experiment on the WSJ and CHiME-4 tasks demonstrates its advantages over both the CTC and attention-based encoder-decoder baselines, showing 5.4-14.6% relative improvements in Character Error Rate (CER).

PaperPDFCodeCode 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 10 code samples harvested from 3 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 10 samples from 3 repositories, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed). 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 on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Alexander-H-Liu/End-to-end-ASR-Pytorch mentioned on GitHubpytorchMITSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
aaaceo890/Attention mentioned on GitHubpytorchSyntology: not harvested report
mnm-rnd/elsa-voice-asr mentioned on GitHubpytorchMITSyntology: not harvested report
neil-zeng/asr mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
s3prl/End-to-end-ASR-Pytorch mentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
sooftware/OpenSpeech mentioned on GitHubpytorchMITSyntology: not harvested report
PaddlePaddle/PaddleSpeech paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
mindspore-courses/heads-on-mindspore mindsporeSyntology: not harvested 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

10 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 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
7unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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. “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.

Alexander-H-Liu/End-to-end-ASR-Pytorch community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
collect_audio_batch src/data.py ran MIT (permissive) · 340cb8273953e493 · report fixture: returned tuple · level recorded 2026-09-26
collect_text_batch src/data.py unverified MIT (permissive) · ca15b9ec596a30d0 · report
create_dataset in 47 papers src/data.py unverified MIT (permissive) · e2ec1a4e3221772d · report
generate_embedding src/bert_embedding.py unverified MIT (permissive) · a7310a3d1f046472 · report
speech_aug_scheduler src/optim.py unverified MIT (permissive) · 90a0a3f3574b92a6 · report
neil-zeng/asr community (archive-listed) 1 sample, 0 ran · 1 unverified
create_dataset in 47 papers src/data.py unverified MIT (permissive) · 3929b38d6fca37e2 · report
s3prl/End-to-end-ASR-Pytorch community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
collect_text_batch src/data.py ran MIT (permissive) · c4ec9d88dda3f211 · report fixture: signature batch:list/1/list, mode:str/0/str · returned Tensor · level recorded 2026-09-26
create_dataset in 47 papers src/data.py ran MIT (permissive) · ac71d8ab36c2fae0 · report fixture: signature tokenizer:SimpleTokenizer/0/?, ascending:bool/0/bool, name:str/0/str, path:str/0/str, bucketing:bool/0/bool, batch_size:int/0/int, eval_batch_size:int/0/int, train_split:list/1/str, dev_split:list/1/str, test_split:list/1/str, text_mode:str/0/str · returned tuple · level recorded 2026-09-26
collect_audio_batch src/data.py unverified MIT (permissive) · bded34b0a51d533c · report
get_testcases slot_evaluate.py unverified MIT (permissive) · 9a8e285c706f7fe8 · report

Tasks

DecoderMulti-Task LearningSpeech RecognitionSpeech-to-Text

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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