Paper Citation Record · LEDGER

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models

As of 8 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2506.00832.

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

pith.paper-citation-record.v1
2506.00832 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:00:12.519114Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:00:09.374265Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T12:00:13.204804Z

Reference resolution

42 of 42 outbound references displayed

verified exact2
verified fuzzy21
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 02f6f1f8-c1ca-42de-870b-2c079d7d87b2 · outbound

This paper cites What would the internal representation look like if the model aimed for a higher pitch rather than the current, lower one?.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models What would the internal representation look like if the model aimed for a higher pitch rather than the current, lower one?

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:18.318653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5638f2c9-2732-4a60-a3ac-02461578072a · outbound

This paper cites Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:00:13.248560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7241112a-e882-4420-8835-0c7fb9c7aefb · outbound

This paper cites What would the internal representation look like if the synthesized speech had a higher pitch rather than a lower pitch?.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models What would the internal representation look like if the synthesized speech had a higher pitch rather than a lower pitch?

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:18.062228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3590fff4-d059-4644-a4e7-015aed35fa08 · outbound

This paper cites an unresolved cited work.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:00:17.902086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 37349320-eb49-4298-81b1-7a3994aa0f7b · outbound

This paper cites In planning its data processing techniques.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models In planning its data processing techniques

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:17.722710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 44d11211-003e-41f0-8d42-4ce76193197d · outbound

This paper cites an unresolved cited work.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:00:17.633955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1003b833-5259-4b16-bc68-dfe11d55928d · outbound

This paper cites 2022-0-00984, Devel- opment of Artificial Intelligence Technology for Personalized Plug-and-Play Explanation and Verification of Explanation; No.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models 2022-0-00984, Devel- opment of Artificial Intelligence Technology for Personalized Plug-and-Play Explanation and Verification of Explanation; No

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:17.417830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2b339be2-3a3e-42ca-a3fb-9dd0a901e141 · outbound

This paper cites Tacotron: Towards End-to-End Speech Synthesis.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Tacotron: Towards End-to-End Speech Synthesis

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:09.959311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7419863-81a5-4109-a059-61c5e407d01b · outbound

This paper cites Natural tts synthesis by conditioning wavenet on mel spectrogram predic- tions,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Natural tts synthesis by conditioning wavenet on mel spectrogram predic- tions,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:17.294685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 24f6eeb6-59af-4911-b21b-dd9f13ab3f56 · outbound

This paper cites Neural speech synthe- sis with transformer network,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Neural speech synthe- sis with transformer network,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:17.049983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 508dffc0-9d53-459f-ba21-77ad334033e4 · outbound

This paper cites Fastspeech: Fast, robust and controllable text to speech,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Fastspeech: Fast, robust and controllable text to speech,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:10.220550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc3de9b6-9a65-4842-a3ef-4433dcddfc69 · outbound

This paper cites FastSpeech 2: Fast and High-Quality End-to-End Text to Speech.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:10.317617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8bfe558-57ec-4f69-82b4-b383d3bf917b · outbound

This paper cites WaveNet: A Generative Model for Raw Audio.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models WaveNet: A Generative Model for Raw Audio

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:10.368822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a44eca22-eeaf-46c1-9a54-1f7da6dacf01 · outbound

This paper cites Waveglow: A flow-based generative network for speech synthesis,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Waveglow: A flow-based generative network for speech synthesis,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:16.909764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3bff5da7-4ba2-473e-86e7-8a80941dfa07 · outbound

This paper cites Mel- gan: Generative adversarial networks for conditional waveform synthesis,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Mel- gan: Generative adversarial networks for conditional waveform synthesis,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:16.716059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4337127c-beb1-442c-8cd1-27d4b13c3992 · outbound

This paper cites Hifi-gan: Generative adversarial net- works for efficient and high fidelity speech synthesis,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Hifi-gan: Generative adversarial net- works for efficient and high fidelity speech synthesis,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:16.447390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cb462432-b81c-4d94-a303-910b17317d71 · outbound

This paper cites Style tokens: Un- supervised style modeling, control and transfer in end-to-end speech synthesis,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Style tokens: Un- supervised style modeling, control and transfer in end-to-end speech synthesis,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:10.682549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b54d476-2d76-49c6-aa5d-b571d2f94059 · outbound

This paper cites To- wards end-to-end prosody transfer for expressive speech synthesis with tacotron,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models To- wards end-to-end prosody transfer for expressive speech synthesis with tacotron,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:10.754568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd643ee-44fa-46ab-a53d-8e9ccab5cb3a · outbound

This paper cites Hierarchical Generative Modeling for Controllable Speech Synthesis.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Hierarchical Generative Modeling for Controllable Speech Synthesis

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:10.808080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 004539f0-2355-42fe-9072-d05e53e7391b · outbound

This paper cites Prosody under con- trol: Controlling prosody in text-to-speech synthesis by adjust- ments in latent reference space,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Prosody under con- trol: Controlling prosody in text-to-speech synthesis by adjust- ments in latent reference space,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:15.506225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 86511840-7bf2-40cd-b188-343e069a30e6 · outbound

This paper cites Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:00:13.054479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f3586622-df59-4260-90dd-f93722557864 · outbound

This paper cites Hierarchical prosody modeling and control in non-autoregressive parallel neural tts,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Hierarchical prosody modeling and control in non-autoregressive parallel neural tts,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:15.025126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1d4052e0-cd1c-4850-990a-bdb2b00d5acb · outbound

This paper cites Analysis of pronunciation learning in end-to-end speech synthesis.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Analysis of pronunciation learning in end-to-end speech synthesis

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:14.866577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a4613d82-41a0-40cc-ab7b-439523ce1418 · outbound

This paper cites Expressive prosody for unit- selection speech synthesis.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Expressive prosody for unit- selection speech synthesis

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:14.657076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 68cf2e50-5554-4ae8-9655-447e62ecce8d · outbound

This paper cites Speaking rate attention-based duration prediction for speed control TTS.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Speaking rate attention-based duration prediction for speed control TTS

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:00:12.835344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 445b59ed-41b1-4406-9923-d6d1812161ea · outbound

This paper cites Speaking rate control of end-to-end tts models by direct manipulation of the encoder’s out- put embeddings,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Speaking rate control of end-to-end tts models by direct manipulation of the encoder’s out- put embeddings,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:14.461220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b83458a-f700-4ac0-ad80-36057ab40fb3 · outbound

This paper cites Unified Mandarin TTS Front-end Based on Distilled BERT Model.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Unified Mandarin TTS Front-end Based on Distilled BERT Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:11.440776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1e7c6ee-5379-450d-b595-528859d2db11 · outbound

This paper cites Speech audio corrector: using speech from non-target speakers for one- off correction of mispronunciations in grapheme-input text-to- speech,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Speech audio corrector: using speech from non-target speakers for one- off correction of mispronunciations in grapheme-input text-to- speech,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:14.256621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e376def8-8962-4098-8b46-8ebfe1c77cba · outbound

This paper cites Exact prosody cloning in zero- shot multispeaker text-to-speech,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Exact prosody cloning in zero- shot multispeaker text-to-speech,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:14.115182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f68dbea8-097f-45fe-9527-0df732a749dd · outbound

This paper cites Hubert: Self-supervised speech rep- resentation learning by masked prediction of hidden units,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Hubert: Self-supervised speech rep- resentation learning by masked prediction of hidden units,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:11.667468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d2ce58f-ac88-44b7-bbdd-7403a9ea9228 · outbound

This paper cites Predicting within and across language phoneme recognition performance of self-supervised learning speech pre-trained models.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Predicting within and across language phoneme recognition performance of self-supervised learning speech pre-trained models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:11.722250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1e1493a-f485-411c-97f1-fc0529edeae0 · outbound

This paper cites What do Neural Machine Translation Models Learn about Morphology?.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models What do Neural Machine Translation Models Learn about Morphology?

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:11.782293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b48f0f9-6544-478c-b1d1-0d2c492e11bc · outbound

This paper cites What is one grain of sand in the desert? analyzing individual neu- rons in deep nlp models,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models What is one grain of sand in the desert? analyzing individual neu- rons in deep nlp models,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:14.001445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7e3f52dc-1e90-4081-86ad-cb68208c4814 · outbound

This paper cites Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:11.931116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1952a89f-b8e6-4015-b9a0-e0f5dc6cdf65 · outbound

This paper cites Diffeomorphic counterfactuals with generative models,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Diffeomorphic counterfactuals with generative models,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:13.854760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1db4c802-4710-465f-bea5-b579d3e189c3 · outbound

This paper cites beta-vae: Learning basic visual concepts with a constrained variational framework,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models beta-vae: Learning basic visual concepts with a constrained variational framework,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:13.742857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fd3bb7e5-c28d-4611-ad1d-542c4bbf2e2f · outbound

This paper cites Neural discrete represen- tation learning,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Neural discrete represen- tation learning,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:13.586825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 861b9cab-a2b4-4017-8617-33324a2c61ab · outbound

This paper cites The lj speech dataset,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models The lj speech dataset,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:12.209634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8e062e2-2d29-4f38-bb32-edd9b8a6d929 · outbound

This paper cites Large Scale GAN Training for High Fidelity Natural Image Synthesis.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Large Scale GAN Training for High Fidelity Natural Image Synthesis

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:12.264666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c22909a4-cdd4-41c5-a5c2-13d369506f8e · outbound

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

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Robust speech recognition via large-scale weak su- pervision,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:12.370607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a972daaa-7f52-4136-8cb9-cfa7279a8627 · outbound

This paper cites Language models are unsupervised multitask learners,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Language models are unsupervised multitask learners,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T12:00:12.455556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3363bde7-799e-4e73-8c61-0ef606ae6fa3 · outbound

This paper cites Speech quality assessment,.

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Speech quality assessment,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:00:13.409116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 5638f2c9-2732-4a60-a3ac-02461578072a · inbound