Paper Citation Record · LEDGER

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings

As of 9 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 4 inbound Pith citation observations for arXiv:2509.15001.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.15001 v3

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T16:17:18.443046Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T16:17:14.961641Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-01T21:36:15.429731Z

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy0
unresolved34
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7de6dd56-37e1-4350-8836-46d899941921 · outbound

This paper cites an unresolved cited work.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:14.871859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197a8495-d4f5-40e1-b4bf-2d54ab5e1cd0 · outbound

This paper cites BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:14.961641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation face384d-4aea-4164-912d-416f698c3169 · outbound

This paper cites Datasets Our pre-training dataset comprises 19 diverse datasets spanning mul- tiple continents over 40 languages (see Table 1).

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Datasets Our pre-training dataset comprises 19 diverse datasets spanning mul- tiple continents over 40 languages (see Table 1)

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.025234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510ceb85-f257-4c63-b636-4d5d40e6f4d3 · outbound

This paper cites BabyHuBERT-2 achieves 64.0% average F-score, substan- tially outperforming both W2V2-LL4300 (58.7%) and HuBERT base (51.4%).

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings BabyHuBERT-2 achieves 64.0% average F-score, substan- tially outperforming both W2V2-LL4300 (58.7%) and HuBERT base (51.4%)

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-08-04T16:17:15.173475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b1683b2-2c2b-424a-85c5-e4e61d791237 · outbound

This paper cites an unresolved cited work.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.251303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f79fc0c0-83aa-40a2-8a68-5c153a43870c · outbound

This paper cites ED: ERC (InfantSimulator); AC and TK: ERC (ExELang, 101001095).

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings ED: ERC (InfantSimulator); AC and TK: ERC (ExELang, 101001095)

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.319899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c306f31-f294-46c4-b7e2-7497abf74319 · outbound

This paper cites Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.909983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ebe4f6e-9d68-4e01-9ef2-c39762f82b1d · outbound

This paper cites Long-form recordings to study children’s language input and output in under-resourced contexts,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Long-form recordings to study children’s language input and output in under-resourced contexts,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.375905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 202ab127-9cbc-4509-b055-e5bc040dff58 · outbound

This paper cites Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.475230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c07514-1220-41b0-a806-cedd3c2526c1 · outbound

This paper cites Acoustics of children’s speech: Developmental changes of temporal and spectral parameters,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Acoustics of children’s speech: Developmental changes of temporal and spectral parameters,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.594105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fce2812-16b9-47ff-a12f-dd9e1ec3d8cb · outbound

This paper cites Acous- tic variability and automatic recognition of children’s speech,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Acous- tic variability and automatic recognition of children’s speech,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.686273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0300132c-f066-434f-b5b7-a68eba132b49 · outbound

This paper cites Systematic Inequalities in Language Technology Performance across the World's Languages.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Systematic Inequalities in Language Technology Performance across the World's Languages

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.777749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 988e1431-a2c6-4edc-8a5e-6a8d7b2284f9 · outbound

This paper cites Introduction To Partial Fine-tuning: A Comprehensive Evaluation Of End-to-end Chil- dren’s Automatic Speech Recognition Adaptation,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Introduction To Partial Fine-tuning: A Comprehensive Evaluation Of End-to-end Chil- dren’s Automatic Speech Recognition Adaptation,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.846220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08868511-8a62-416a-969a-e319ae95028c · outbound

This paper cites A thorough eval- uation of the language environment analysis (lena) system,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings A thorough eval- uation of the language environment analysis (lena) system,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.645092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfa272ec-0ca2-46d5-aed5-fba243dff1c1 · outbound

This paper cites Towards robust family-infant audio analysis based on unsu- pervised pretraining of wav2vec 2.0 on large-scale unlabeled family audio,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Towards robust family-infant audio analysis based on unsu- pervised pretraining of wav2vec 2.0 on large-scale unlabeled family audio,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.065134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feb48427-a221-43cd-8f5f-8576c170fbf7 · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learning of speech representa- tions,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings wav2vec 2.0: A framework for self-supervised learning of speech representa- tions,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.163714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 029aa4a9-e35c-4fa9-8e01-6fa19d4b96bb · outbound

This paper cites Employing self- supervised learning models for cross-linguistic child speech maturity classification,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Employing self- supervised learning models for cross-linguistic child speech maturity classification,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.231220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f172a12f-aa0d-43f6-9edf-0b122c1bb1eb · outbound

This paper cites Reverse en- gineering language acquisition with child-centered long-form recordings,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Reverse en- gineering language acquisition with child-centered long-form recordings,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.293783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1b580f4-1acc-4e78-97cf-280634a1b5f1 · outbound

This paper cites an unresolved cited work.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.386578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55a9fde8-e000-4f5a-afb9-a854368c5971 · outbound

This paper cites Homebank: An online repository of daylong child-centered audio recordings,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Homebank: An online repository of daylong child-centered audio recordings,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.495794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8107da7c-5f4f-41db-9645-9e8d97f94e3e · outbound

This paper cites mhubert-147: A compact multilingual hubert model,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings mhubert-147: A compact multilingual hubert model,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:17.549676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f06c87-4cdd-4cb6-81b1-981995ff4aaa · outbound

This paper cites For BabyHuBERT-1, we extract features from the 6th layer of WavLM-base-plus.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings For BabyHuBERT-1, we extract features from the 6th layer of WavLM-base-plus

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:15.089461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c04219f6-2123-4d13-b872-af115a88c0bb · outbound

This paper cites An open-source voice type classifier for child-centered daylong recordings,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings An open-source voice type classifier for child-centered daylong recordings,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.766857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22b0a1c0-bf6b-4fda-91a7-6d7c4f6bed64 · outbound

This paper cites Signal processing for young child speech language development.,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Signal processing for young child speech language development.,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:16.859633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2eca15-1ff9-4885-ba3a-68295aecf0e3 · outbound

This paper cites Speaker recognition from raw waveform with sincnet,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Speaker recognition from raw waveform with sincnet,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:17.009526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65504122-2325-4306-89d8-5b34d2807105 · outbound

This paper cites Challenges in Automated Processing of Speech from Child Wearables: The Case of V oice Type Classifier,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Challenges in Automated Processing of Speech from Child Wearables: The Case of V oice Type Classifier,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:17.129113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5ff6c42-0ded-4034-9da0-f17e535428c1 · outbound

This paper cites Developing a cross-cultural annotation system and metacorpus for studying infants’ real world language experience,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Developing a cross-cultural annotation system and metacorpus for studying infants’ real world language experience,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:17.275963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55f4bc48-c8bd-4414-895d-46353011723e · outbound

This paper cites Wavlm: Large-scale self-supervised pre-training for full stack speech processing,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Wavlm: Large-scale self-supervised pre-training for full stack speech processing,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:17.359917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16dfa19a-e731-410e-bb84-cf5f3b0f51f1 · outbound

This paper cites Hubert: Self-supervised speech representation learning by masked prediction of hid- den units,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Hubert: Self-supervised speech representation learning by masked prediction of hid- den units,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:17.785559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfe825c6-7bba-418e-8b32-d845b1e1b0be · outbound

This paper cites Superb: Speech processing universal performance benchmark,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Superb: Speech processing universal performance benchmark,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:17.961650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe15651-fce5-4a50-9d6b-31680f076f1f · outbound

This paper cites pyannote. metrics: A toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems.,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings pyannote. metrics: A toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems.,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:18.159359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cdeb22e-d547-4360-b9d4-1469b816b4a0 · outbound

This paper cites Torchaudio 2.1: Advancing speech recognition, self-supervised learning, and audio process- ing components for pytorch,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Torchaudio 2.1: Advancing speech recognition, self-supervised learning, and audio process- ing components for pytorch,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:18.216118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ac68a9b-1902-4b7b-8171-71b48a6242cb · outbound

This paper cites Scikit-learn: Machine learning in Python,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Scikit-learn: Machine learning in Python,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:18.319135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e801bbe-5292-40a0-b279-9a4ff93a2c25 · outbound

This paper cites Child-directed and overheard input from different speakers in two distinct cultures,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Child-directed and overheard input from different speakers in two distinct cultures,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:18.361461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6fc1119-c1c3-47ca-9202-f2741eb1efff · outbound

This paper cites Putting the child in the driver’s seat: insights into language development from children’s interactions in preschool classrooms,.

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings Putting the child in the driver’s seat: insights into language development from children’s interactions in preschool classrooms,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T16:17:18.443046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 197a8495-d4f5-40e1-b4bf-2d54ab5e1cd0 · inbound