Paper Citation Record · LEDGER

Differentiable K-means for Fully-optimized Discrete Token-based ASR

As of 21 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2505.16207.

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

pith.paper-citation-record.v1
2505.16207 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:10:55.387892Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:10:52.835278Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T15:10:55.683469Z

Reference resolution

41 of 41 outbound references displayed

verified exact2
verified fuzzy31
unresolved7
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f1cfce28-0f52-4773-be74-502355752e03 · outbound

This paper cites Differentiable K-means for Fully-optimized Discrete Token-based ASR.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Differentiable K-means for Fully-optimized Discrete Token-based ASR

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:10:55.770093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 928ddb08-67b1-4428-b947-e4d4642a4bdf · outbound

This paper cites text-like.

Differentiable K-means for Fully-optimized Discrete Token-based ASR text-like

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:11:01.223458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 52ee6ffb-43c4-44f5-a162-0ba8fff96a0a · outbound

This paper cites Experimental Setup Our experiments were conducted using ESPnet [24], follow- ing the basic configurations described in [11, 12].

Differentiable K-means for Fully-optimized Discrete Token-based ASR Experimental Setup Our experiments were conducted using ESPnet [24], follow- ing the basic configurations described in [11, 12]

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T15:11:01.109058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c3693fa1-7ab1-414d-87cb-91c77c021b21 · outbound

This paper cites Since SSL fea- ture spaces are changed by finetuning, they are divided by the averaged L2 norm for normalization.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Since SSL fea- ture spaces are changed by finetuning, they are divided by the averaged L2 norm for normalization

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:11:00.947796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation db5454fc-05f2-4791-b01f-603eb1be61ca · outbound

This paper cites If the tokens are robust to sub- tle pronunciation variations and represent more phoneme-like symbols, the sequence increases the repetition and TSL will be shorter.

Differentiable K-means for Fully-optimized Discrete Token-based ASR If the tokens are robust to sub- tle pronunciation variations and represent more phoneme-like symbols, the sequence increases the repetition and TSL will be shorter

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:11:00.761096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d6ec492a-7324-409f-8ec9-34b1710e5d41 · outbound

This paper cites A lower value indicates the robustness of discrete tokens to non-linguistic information.

Differentiable K-means for Fully-optimized Discrete Token-based ASR A lower value indicates the robustness of discrete tokens to non-linguistic information

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:11:00.636731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cc51e29c-a7be-4e72-a5a1-cbdf16791131 · outbound

This paper cites As a result, ASR performance improved and the obtained tokens exhibited more phonetic characteristics with purer linguistic information.

Differentiable K-means for Fully-optimized Discrete Token-based ASR As a result, ASR performance improved and the obtained tokens exhibited more phonetic characteristics with purer linguistic information

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:11:00.480261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 227f0549-601a-44d6-abdf-62c6e8b33aa7 · outbound

This paper cites Self-supervised speech representation learning: A review,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Self-supervised speech representation learning: A review,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:11:00.386016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2f98c313-ca16-4d1e-9dd3-470326a12abc · outbound

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

Differentiable K-means for Fully-optimized Discrete Token-based ASR HuBERT: Self- supervised speech representation learning by masked prediction of hidden units,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:11:00.216651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7e99129f-e404-41d3-bc2b-c1ee42d8ed7a · outbound

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

Differentiable K-means for Fully-optimized Discrete Token-based ASR wav2vec 2.0: A framework for self-supervised learning of speech representa- tions,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:11:00.100231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f6ee3d29-918c-4b18-860d-9746aaa49d3e · outbound

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

Differentiable K-means for Fully-optimized Discrete Token-based ASR WavLM: Large-scale self-supervised pre-training for full stack speech process- ing,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:59.882795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1518c7c8-41f0-4d4a-bef7-e7267c39e4be · outbound

This paper cites w2v-BERT: Combining contrastive learning and masked language modeling for self- supervised speech pre-training,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR w2v-BERT: Combining contrastive learning and masked language modeling for self- supervised speech pre-training,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:59.635877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f36e9891-ffdb-487d-9e99-9fab34ab8abb · outbound

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

Differentiable K-means for Fully-optimized Discrete Token-based ASR SUPERB: Speech processing universal performance benchmark,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:59.398067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dd2be09d-4af9-4fb7-8e1a-bcb50e4ea8e1 · outbound

This paper cites The Interspeech 2024 challenge on speech processing using discrete units,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR The Interspeech 2024 challenge on speech processing using discrete units,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:59.182121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7681dfc2-b7c0-4d01-a47e-64f51a05f780 · outbound

This paper cites Speechgpt: Empowering large language models with intrinsic cross-modal conversational abili- ties,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Speechgpt: Empowering large language models with intrinsic cross-modal conversational abili- ties,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:58.971469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a7c0a7f9-76ed-4f7e-bb05-13caa0df2fb5 · outbound

This paper cites V oxtlm: Unified decoder- only models for consolidating speech recognition, synthesis and speech, text continuation tasks,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR V oxtlm: Unified decoder- only models for consolidating speech recognition, synthesis and speech, text continuation tasks,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:58.737889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9f92d21a-5a7b-491f-8171-acc4d3eddcec · outbound

This paper cites AudioPaLM: A Large Language Model That Can Speak and Listen.

Differentiable K-means for Fully-optimized Discrete Token-based ASR AudioPaLM: A Large Language Model That Can Speak and Listen

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:53.895183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26fc4fb4-a03b-4697-951a-01522e8b6a29 · outbound

This paper cites Ex- ploration of efficient end-to-end ASR using discretized input from self-supervised learning,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Ex- ploration of efficient end-to-end ASR using discretized input from self-supervised learning,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:54.009045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d493f9cb-5ea7-4bff-8328-4e08260d25a1 · outbound

This paper cites Exploring speech recognition, translation, and understanding with discrete speech units: A com- parative study,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Exploring speech recognition, translation, and understanding with discrete speech units: A com- parative study,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:58.551490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ec1ca78a-c709-446f-ab53-2c17e4b99dab · outbound

This paper cites Towards universal speech discrete tokens: A case study for ASR and TTS,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Towards universal speech discrete tokens: A case study for ASR and TTS,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:58.329663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3085bb31-4c5e-4d55-975c-5bc8f7d14021 · outbound

This paper cites Estimating the completeness of discrete speech units,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Estimating the completeness of discrete speech units,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:58.109481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 36be1581-0257-4491-9082-9dc116de05aa · outbound

This paper cites Deep clus- tering with concrete k-means,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Deep clus- tering with concrete k-means,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:57.876285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8004c3a5-aa60-40c5-b3c0-58d9a083e9ba · outbound

This paper cites Neural discrete represen- tation learning,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Neural discrete represen- tation learning,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:57.726262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 629bab09-6ffe-4300-a63e-cd0736cb34aa · outbound

This paper cites How should we extract dis- crete audio tokens from self-supervised models?.

Differentiable K-means for Fully-optimized Discrete Token-based ASR How should we extract dis- crete audio tokens from self-supervised models?

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:57.535744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b8d2a27f-2b09-4095-a9e6-e51c4f73be12 · outbound

This paper cites MMM: Multi-layer multi-residual multi-stream discrete speech represen- tation from self-supervised learning model,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR MMM: Multi-layer multi-residual multi-stream discrete speech represen- tation from self-supervised learning model,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:54.504219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f377d43-3815-4020-87b3-da3059c3f78f · outbound

This paper cites Joint CTC-attention based end-to-end speech recognition using multi-task learning,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Joint CTC-attention based end-to-end speech recognition using multi-task learning,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:54.517916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ff2eebf-bd59-4945-8472-38db5cdac336 · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Sequence Transduction with Recurrent Neural Networks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:54.588280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9599407a-c585-4869-aed8-c3c127a52b0f · outbound

This paper cites Owsm v3.1: Better and faster open whisper-style speech models based on e-branchformer,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Owsm v3.1: Better and faster open whisper-style speech models based on e-branchformer,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:57.378971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 277b2d82-4125-493b-bfb8-3142d859fde0 · outbound

This paper cites Comparing discrete and continuous space llms for speech recognition,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Comparing discrete and continuous space llms for speech recognition,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:57.281794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ab6c8e5b-b829-4c12-b934-30680781e62e · outbound

This paper cites Categorical reparameterization with gumbel-softmax,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Categorical reparameterization with gumbel-softmax,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:57.105007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f249e5c0-c45e-4807-8205-89182a142208 · outbound

This paper cites ESPnet: End-to-end speech processing toolkit,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR ESPnet: End-to-end speech processing toolkit,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:56.922623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dfa20a09-c8f3-4312-aac6-be7aaa8c6130 · outbound

This paper cites Lib- rispeech: An asr corpus based on public domain audio books,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Lib- rispeech: An asr corpus based on public domain audio books,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:54.889744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1087512b-a9a1-46a3-9d84-970ef88badac · outbound

This paper cites On generative spoken language modeling from raw audio,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR On generative spoken language modeling from raw audio,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:56.726453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6ecf95b6-9f5e-40f1-a94b-36e200fe3efc · outbound

This paper cites TIMIT acoustic-phonetic continuous speech corpus,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR TIMIT acoustic-phonetic continuous speech corpus,

Reference 34

Resolution: verified exact; raw_fallback, observed 2026-08-07T15:10:55.625579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 28e8532e-1a2d-4471-9da4-a9ad12654439 · outbound

This paper cites Natural TTS synthesis by con- ditioning wavenet on mel spectrogram predictions,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Natural TTS synthesis by con- ditioning wavenet on mel spectrogram predictions,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:56.580418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 31fe7b07-04ea-4942-91ac-be3e41bf9b71 · outbound

This paper cites The LJ speech dataset,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR The LJ speech dataset,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:55.099028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24874937-ce16-4351-8098-07bc72a7194b · outbound

This paper cites Parallel wavegan: A fast waveform generation model based on generative adversarial net- works with multi-resolution spectrogram,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Parallel wavegan: A fast waveform generation model based on generative adversarial net- works with multi-resolution spectrogram,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:56.413190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c8b70b88-a058-4d89-866a-3c1def88f3a0 · outbound

This paper cites Robust speech recognition via large-scale weak supervision,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR Robust speech recognition via large-scale weak supervision,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:56.304037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5b488939-e834-456e-9b6d-aee5774e51b4 · outbound

This paper cites CSTR VCTK cor- pus: English multi-speaker corpus for cstr voice cloning toolkit,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR CSTR VCTK cor- pus: English multi-speaker corpus for cstr voice cloning toolkit,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:56.118434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3b701dad-5d7f-48c5-8cb9-26126bf63447 · outbound

This paper cites UTMOS: UTokyo-SaruLab system for V oiceMOS challenge 2022,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR UTMOS: UTokyo-SaruLab system for V oiceMOS challenge 2022,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:56.004267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b4ffa12a-f856-4eef-afc2-87f659bfdc5b · outbound

This paper cites ML-SUPERB: Multilingual speech universal performance benchmark,.

Differentiable K-means for Fully-optimized Discrete Token-based ASR ML-SUPERB: Multilingual speech universal performance benchmark,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:55.864629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation f1cfce28-0f52-4773-be74-502355752e03 · inbound