Paper Citation Record · LEDGER

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers

As of 9 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2506.21712.

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

pith.paper-citation-record.v1
2506.21712 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:25:28.605102Z

measured 32 of 32 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy29
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 309ee90f-0bb9-4dd5-91ac-7cbbfd341046 · outbound

This paper cites Effec- tiveness of Self-Supervised Pre-Training for ASR.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Effec- tiveness of Self-Supervised Pre-Training for ASR

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:34.695109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3ddf8954-34c3-4fa8-a90a-dc46b61fb615 · outbound

This paper cites data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:34.481655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 68ed416b-399e-4e94-9bfb-0ae96881ba0d · outbound

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

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers wav2vec 2.0: A framework for self-supervised learning of speech representations

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:34.273477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7222a896-e7be-4a43-9e46-bc8c1cde2a48 · outbound

This paper cites Information-Theoretic Understanding of Population Risk Improvement with Model Com- pression.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Information-Theoretic Understanding of Population Risk Improvement with Model Com- pression

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:34.029574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64d61391-68ae-42b2-8eb7-7f1c9d6fefc5 · outbound

This paper cites WavLM: Large-scale self- supervised pre-training for full stack speech process- ing.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers WavLM: Large-scale self- supervised pre-training for full stack speech process- ing

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:33.865763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ffe9b5ed-b656-43ca-94de-cbe2ae68bf94 · outbound

This paper cites Large-scale self-supervised speech representation learning for automatic speaker verification.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Large-scale self-supervised speech representation learning for automatic speaker verification

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:33.639412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dc7f348d-a99a-482b-bc40-33fb7ae902e1 · outbound

This paper cites Self-Supervised Speech Rep- resentations are More Phonetic than Semantic.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Self-Supervised Speech Rep- resentations are More Phonetic than Semantic

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:33.454549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3cf3216e-e0d4-41a9-a62c-df6d1a535d66 · outbound

This paper cites What do end-to-end speech models learn about speaker, language and channel information? A layer- wise and neuron-level analysis.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers What do end-to-end speech models learn about speaker, language and channel information? A layer- wise and neuron-level analysis

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:33.210026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b3a7cc86-5281-4db4-aaa1-da37c3604975 · outbound

This paper cites An unsupervised autoregressive model for speech representation learning.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers An unsupervised autoregressive model for speech representation learning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:32.970654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9ebbc98f-483c-46b0-9fbd-b49d5e49653d · outbound

This paper cites Front-End Factor Analysis for Speaker Verification.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Front-End Factor Analysis for Speaker Verification

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:32.807836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8ceeafcb-5853-424c-ac2b-397d8e6d7bbc · outbound

This paper cites Exploring wav2vec 2.0 on speaker verification and language identification.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Exploring wav2vec 2.0 on speaker verification and language identification

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:32.617615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 07ba2303-83fc-444c-8ce9-dabb139b775e · outbound

This paper cites The lottery ticket hypothesis: Finding sparse, trainable neural net- works.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers The lottery ticket hypothesis: Finding sparse, trainable neural net- works

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:32.444932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 13dede3f-60be-42ca-b2fe-796140333089 · outbound

This paper cites Self-supervised pre-training for attention-based encoder-decoder asr model.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Self-supervised pre-training for attention-based encoder-decoder asr model

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:32.200397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0986ef52-c63b-48b5-85b9-eafa5f65e781 · outbound

This paper cites Transformer feed-forward layers are key-value memories.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Transformer feed-forward layers are key-value memories

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:31.989063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b4074e4b-03e7-43cb-bba9-0ee889ef45ed · outbound

This paper cites Learning both Weights and Connec- tions for Efficient Neural Network.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Learning both Weights and Connec- tions for Efficient Neural Network

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:31.765812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a19828d9-e5df-428f-a2bf-e6a783218b50 · outbound

This paper cites HuBERT: Self-supervised speech representation learning by masked prediction of hidden units.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers HuBERT: Self-supervised speech representation learning by masked prediction of hidden units

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:31.562831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f1f97ec8-0a38-4470-9fa6-864f987b4e8c · outbound

This paper cites SNIP: Single-shot Network Pruning based on Connection Sensitivity.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers SNIP: Single-shot Network Pruning based on Connection Sensitivity

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:31.356232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f50e7c19-32fa-48f0-b194-f0a7be1052f6 · outbound

This paper cites MelHu- BERT: A simplified HuBERT on Mel spectrograms.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers MelHu- BERT: A simplified HuBERT on Mel spectrograms

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:31.197081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a3dfc27b-f5da-47c9-bbfd-bf9722da0206 · outbound

This paper cites Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T22:25:27.612020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7c75aa7-13d6-48b2-8623-056e24c84396 · outbound

This paper cites Property Neurons in Self- Supervised Speech Transformers.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Property Neurons in Self- Supervised Speech Transformers

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:31.015998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ebc7b7de-f594-46cd-9f0d-a05eb86275a0 · outbound

This paper cites DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T22:25:27.747596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d562693-ff0a-4a8f-bb98-cc2fff0492bc · outbound

This paper cites DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Represen- tation Learning.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Represen- tation Learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:30.860601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ddfb904e-523e-4e91-9581-d6612894ffe4 · outbound

This paper cites TERA: Self-Supervised Learning of Transformer Encoder Rep- resentation for Speech.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers TERA: Self-Supervised Learning of Transformer Encoder Rep- resentation for Speech

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:30.673851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64e2457b-a11c-4e53-9ae8-099756df9ba0 · outbound

This paper cites Introducing phonetic information to speaker embedding for speaker verification.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Introducing phonetic information to speaker embedding for speaker verification

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:30.483418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c86fa06b-c217-4c73-9c42-ce5bd79f5706 · outbound

This paper cites Speaker embedding extraction with pho- netic information.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Speaker embedding extraction with pho- netic information

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:30.292776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation aa943e3d-74b7-4ca0-885d-a4344b5a9330 · outbound

This paper cites Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:30.107050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c6667708-0aee-4183-8c1f-7c638c3b8602 · outbound

This paper cites Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:29.895646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 91ea8285-57f5-4b53-89e4-15c1d0ee3a42 · outbound

This paper cites Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:29.629155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation de6d4b23-0ae2-4c9d-8705-d10d5bd3bf4c · outbound

This paper cites X-vectors: Robust dnn embeddings for speaker recognition.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers X-vectors: Robust dnn embeddings for speaker recognition

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:29.294991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8d87a066-029c-4c5f-908a-7b80a81e2f22 · outbound

This paper cites A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T22:25:28.434258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae911fe-2c5e-4d70-a2b7-c9696eb18e3a · outbound

This paper cites Phonetic analysis of self-supervised representations of english speech.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers Phonetic analysis of self-supervised representations of english speech

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:28.985298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c7a6832a-d7b6-4b86-8040-7b8a2a746618 · outbound

This paper cites SUPERB: Speech processing Universal PERformance Benchmark.

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers SUPERB: Speech processing Universal PERformance Benchmark

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:25:28.837619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.