Papers › Word Segmentation on Discovered Phone Units with Dynamic Programming and...

Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring

24 Feb 2022arXiv:2202.11929archive 2025-07-28

Herman Kamper

Recent work on unsupervised speech segmentation has used self-supervised models with phone and word segmentation modules that are trained jointly. This paper instead revisits an older approach to word segmentation: bottom-up phone-like unit discovery is performed first, and symbolic word segmentation is then performed on top of the discovered units (without influencing the lower level). To do this, I propose a new unit discovery model, a new symbolic word segmentation model, and then chain the two models to segment speech. Both models use dynamic programming to minimize segment costs from a self-supervised network with an additional duration penalty that encourages longer units. Concretely, for acoustic unit discovery, duration-penalized dynamic programming (DPDP) is used with a contrastive predictive coding model as the scoring network. For word segmentation, DPDP is applied with an autoencoding recurrent neural as the scoring network. The two models are chained in order to segment speech. This approach gives comparable word segmentation results to state-of-the-art joint self-supervised segmentation models on an English benchmark. On French, Mandarin, German and Wolof data, it outperforms previous systems on the ZeroSpeech benchmarks. Analysis shows that the chained DPDP system segments shorter filler words well, but longer words might require some external top-down signal.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2202.11929")

Code

Syntology Ran 12 of 19 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 4 ran · honoured contract; 3 ran · our draft was wrong; 2 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 5 samples from 2 repositories, 5 ran; community (archive-listed): 14 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kamperh/dpdp_aernn officialmentioned in papermentioned on GitHubpytorch report
kamperh/vqwordseg officialmentioned in papermentioned on GitHubpytorch report
jasonppy/word-discovery mentioned on GitHubpytorchBSD-3-Clause 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.

Code Syntology ran Syntology

19 samples harvested; 12 ran; 4 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · honoured contract
3ran · our draft was wrong
2ran · fixture could not drive it
3ran
7unverified

Licence: 0 of the 19 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

boundaries_to_intervals kamperh/vqwordseg/eval_segmentation.py official repository ran · honoured contract fingerprinted MIT (permissive) · 5cf9b5e522af96d5 · report
get_intervals_from_dir kamperh/vqwordseg/eval_segmentation.py official repository ran · our draft was wrong MIT (permissive) · 5d99453f8b60341d · report
get_segmented_sentence kamperh/dpdp_aernn/run_brent.py official repository ran · fixture could not drive it MIT (permissive) · 6697d0657e11e88f · report
intervals_to_boundaries kamperh/vqwordseg/eval_segmentation.py official repository ran · our draft was wrong MIT (permissive) · bdd3717607f29767 · report
neg_log_psuedo_geometric kamperh/dpdp_aernn/run_brent.py official repository ran · honoured contract MIT (permissive) · 77e3e9a881b530dc · report
swish jasonppy/word-discovery/models/utils.py community (archive-listed) ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 0f786c407fb1ee4c · report
bool_flag jasonppy/word-discovery/models/vit_utils.py community (archive-listed) ran BSD-3-Clause (permissive) · 4d25be8ebf17fde1 · report
clip_gradients jasonppy/word-discovery/models/vit_utils.py community (archive-listed) ran BSD-3-Clause (permissive) · 2b5489053b222e00 · report
cosine_scheduler jasonppy/word-discovery/models/vit_utils.py community (archive-listed) ran · honoured contract fingerprinted BSD-3-Clause (permissive) · 361a6b24f11fc50a · report
drop_path jasonppy/word-discovery/models/vision_transformer.py community (archive-listed) ran · fixture could not drive it fingerprinted BSD-3-Clause (permissive) · 55120f2026b56aa2 · report
gelu jasonppy/word-discovery/models/utils.py community (archive-listed) ran · honoured contract fingerprinted BSD-3-Clause (permissive) · c2f0705ed8e6f7e6 · report
get_intervals_from_dir jasonppy/word-discovery/buckeye_eval.py community (archive-listed) ran BSD-3-Clause (permissive) · 54dbd7b3ecbb6448 · report
Margin_InfoNCE_loss jasonppy/word-discovery/models/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · 05ead5734e7a624a · report
cls_attn_seg_feats jasonppy/word-discovery/save_seg_feats.py community (archive-listed) unverified BSD-3-Clause (permissive) · 8de801ce80b0728a · report
cls_attn_seg_feats jasonppy/word-discovery/save_seg_feats_buckeye.py community (archive-listed) unverified BSD-3-Clause (permissive) · f2fd30826872a75d · report
force_align_seg_feats jasonppy/word-discovery/save_seg_feats.py community (archive-listed) unverified BSD-3-Clause (permissive) · ae600d378be4e580 · report
parse_faiss_specs jasonppy/word-discovery/run_kmeans.py community (archive-listed) unverified BSD-3-Clause (permissive) · 35070d2f37830ca3 · report
vit_small jasonppy/word-discovery/models/vision_transformer.py community (archive-listed) unverified BSD-3-Clause (permissive) · 3aae9623741abc40 · report
vit_tiny jasonppy/word-discovery/models/vision_transformer.py community (archive-listed) unverified BSD-3-Clause (permissive) · 7d962f3bf8a0e816 · report

Tasks

Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Predictive CodingInfoNCE

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