Papers › An embedded segmental K-means model for unsupervised segmentation and clustering of speech

An embedded segmental K-means model for unsupervised segmentation and clustering of speech

23 Mar 2017arXiv:1703.08135archive 2025-07-28

Herman Kamper, Karen Livescu, Sharon Goldwater

Unsupervised segmentation and clustering of unlabelled speech are core problems in zero-resource speech processing. Most approaches lie at methodological extremes: some use probabilistic Bayesian models with convergence guarantees, while others opt for more efficient heuristic techniques. Despite competitive performance in previous work, the full Bayesian approach is difficult to scale to large speech corpora. We introduce an approximation to a recent Bayesian model that still has a clear objective function but improves efficiency by using hard clustering and segmentation rather than full Bayesian inference. Like its Bayesian counterpart, this embedded segmental K-means model (ES-KMeans) represents arbitrary-length word segments as fixed-dimensional acoustic word embeddings. We first compare ES-KMeans to previous approaches on common English and Xitsonga data sets (5 and 2.5 hours of speech): ES-KMeans outperforms a leading heuristic method in word segmentation, giving similar scores to the Bayesian model while being 5 times faster with fewer hyperparameters. However, its clusters are less pure than those of the other models. We then show that ES-KMeans scales to larger corpora by applying it to the 5 languages of the Zero Resource Speech Challenge 2017 (up to 45 hours), where it performs competitively compared to the challenge baseline.

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 15 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 2 repositories, 13 ran (10 with no instrument failure; 3 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.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

kamperh/bucktsong_eskmeans mentioned on GitHubMITSyntology: 12 samples, 10 ran (0 instrument-failed) · 2 unverified report
kamperh/eskmeans mentioned on GitHubSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified 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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 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.

2ran · our draft was wrong
1ran; the contract check could not run
10ran
2unverified

Licence: 3 of the 15 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 2 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.

kamperh/bucktsong_eskmeans community (archive-listed) 12 samples, 10 ran (0 instrument-failed) · 2 unverified
average_precision in 38 papers downsample/samediff.py ran MIT (permissive) · 9acae200c1954ee9 · report fixture: signature pos_distances:ndarray/1/float, neg_distances:ndarray/1/float, show_plot:bool/0/bool · returned tuple · level recorded 2026-09-26
downsample_utterance downsample/downsample_dense.py ran MIT (permissive) · 744a7b79ce29df7b · report fixture: signature features:ndarray/2/float, seglist:list/1/tuple, n:int/0/int · returned ndarray · level recorded 2026-09-26
extract_vad features/features.py ran MIT (permissive) · f42377be880d15f6 · report fixture: signature feat_dict:dict/0/?, vad_dict:dict/0/? · returned dict · level recorded 2026-09-26
generate_matches_array downsample/samediff.py ran MIT (permissive) · 76167a80296f74b2 · report fixture: signature labels:ndarray/1/int · returned ndarray · level recorded 2026-09-26
get_durations_dict segmentation/get_data_downsample.py ran MIT (permissive) · bd4d693115d65d6a · report fixture: signature landmarks_dict:dict/0/?, n_landmarks_max:int/0/int · returned dict · level recorded 2026-09-26
get_seglist_from_landmarks downsample/get_seglist.py ran fingerprinted MIT (permissive) · e263a5f1a087512f · report fixture: signature landmarks:list/1/int, n_landmarks_max:int/0/int · returned list · level recorded 2026-09-26
get_vec_ids_dict segmentation/get_data_downsample.py ran MIT (permissive) · c03ab624cd19df94 · report fixture: signature lengths_dict:dict/0/?, n_landmarks_max:int/0/int · returned dict · level recorded 2026-09-26
read_vad_from_fa features/utils.py ran MIT (permissive) · fa13b362a551768b · report fixture: signature fa_fn:str/0/str, frame_indices:bool/0/bool · returned dict · level recorded 2026-09-26
strip_nonvad features/utils.py ran MIT (permissive) · 38722d202e76b2cb · report fixture: signature utt:str/0/str, start:int/0/int, end:int/0/int, vads:list/1/tuple · returned tuple · level recorded 2026-09-26
uttlabel_to_uttkey features/utils.py ran fingerprinted MIT (permissive) · eaa884c8ef9ed624 · report fixture: signature utterance:str/0/str · returned str · level recorded 2026-09-26
get_tokens_from_fa segmentation/get_data_downsample.py unverified MIT (permissive) · 0bfe2243a58f7b18 · report
mean_average_precision in 15 papers downsample/samediff.py unverified MIT (permissive) · e09ac618a9f85288 · report
kamperh/eskmeans community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
forward_backward_kmeans_viterbi eskmeans/eskmeans_wordseg.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 49bb6e6331d17d66 · report fixture: signature vec_embed_neg_len_sqrd_norms:ndarray/1/float, N:int/0/int, n_slices_min:int/0/int, n_slices_max:int/0/int, i_utt:NoneType/0/? · returned tuple · level recorded 2026-09-22
local_segment_only_utts eskmeans/eskmeans_wordseg.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 5d35604b2fba6f41 · report fixture: signature this:callable/0/?, utterances:list/1/Tensor · returned list · level recorded 2026-09-22
process_embeddings eskmeans/eskmeans_wordseg.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 3c99df048b9ea79d · report fixture: signature embedding_mats:dict/0/?, vec_ids_dict:dict/0/? · returned tuple · level recorded 2026-09-22

Tasks

Bayesian InferenceClusteringSegmentationWord Embeddings

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