Paper Citation Record · LEDGER

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis

As of 18 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2608.08362.

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

pith.paper-citation-record.v1
2608.08362 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:10:40.920937Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:10:40.788931Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-12T00:10:41.540631Z

Reference resolution

45 of 45 outbound references displayed

verified exact1
verified fuzzy12
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d3906908-4e24-4528-b219-2ec9d33f18fe · outbound

This paper cites an unresolved cited work.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:10:41.893849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7ca53c06-e6f2-47ae-b9b7-64d9808f0602 · outbound

This paper cites an unresolved cited work.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:10:41.884413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f3eb38eb-8e72-44bd-ae26-ebe1c70f1d3e · outbound

This paper cites an unresolved cited work.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:10:41.875334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 440044ac-ccbf-4749-bcf6-10ac8c78b8d1 · outbound

This paper cites an unresolved cited work.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:10:41.866574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6a494d1b-0a14-4601-98f0-8bc0bcb2ac01 · outbound

This paper cites CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-08-12T00:10:41.544806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 33dac800-e9b4-4dcf-be69-a7637841b420 · outbound

This paper cites outpainting.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis outpainting

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.856686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a0d2cb77-2aa9-4380-bf83-f557d79ce680 · outbound

This paper cites an unresolved cited work.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:10:41.846877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 097e6d95-3fde-4a8f-96ae-2401dbab8ce6 · outbound

This paper cites an unresolved cited work.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:10:41.837289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 39e83fd4-f028-4ba0-a7c9-4a397bfa4e5b · outbound

This paper cites an unresolved cited work.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:10:41.827861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation caf97688-a2fb-4f82-b633-172179f6c8d7 · outbound

This paper cites First, our experiments are mainly conducted on English speech, so the effectiveness of CTRLSPEECHfor multilingual or code-switching synthesis re- mains unexplored.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis First, our experiments are mainly conducted on English speech, so the effectiveness of CTRLSPEECHfor multilingual or code-switching synthesis re- mains unexplored

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.818313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 92c5ee93-08e0-4bad-8be0-32c56eeae2c5 · outbound

This paper cites 2D- 16003984 through the Amazon-UT Austin HUB.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis 2D- 16003984 through the Amazon-UT Austin HUB

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.807232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ee42a50d-1072-413f-9fe8-6934b39bcb0b · outbound

This paper cites All authors remain fully responsible for the con- tent of this manuscript.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis All authors remain fully responsible for the con- tent of this manuscript

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.796694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a7d6d96c-9730-46e6-bc04-c727ef0716c1 · outbound

This paper cites Ditar: Diffusion transformer autoregressive modeling for speech generation,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Ditar: Diffusion transformer autoregressive modeling for speech generation,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.816253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 027dec4c-984b-4e54-97f3-e3d7d95a6796 · outbound

This paper cites Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.819409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ffd9c1-4804-4199-b409-a07fe33fd398 · outbound

This paper cites NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.823347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dc0ab8f-49f9-4847-84ec-fe1532ef48a4 · outbound

This paper cites MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.826976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6409aaac-722e-4444-bd63-62c7de4cd51a · outbound

This paper cites F5-tts: A fairytaler that fakes fluent and faithful speech with flow matching,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis F5-tts: A fairytaler that fakes fluent and faithful speech with flow matching,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.830784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c7967d7-8218-47f1-a511-30027b4a84f4 · outbound

This paper cites V oicecraft-x: Unifying multilingual, voice- cloning speech synthesis and speech editing,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis V oicecraft-x: Unifying multilingual, voice- cloning speech synthesis and speech editing,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.781590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c025b68e-de5c-4b9f-a609-f03798ad1bf6 · outbound

This paper cites Prompttts: Control- lable text-to-speech with text descriptions,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Prompttts: Control- lable text-to-speech with text descriptions,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.838301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a09c230-013b-4930-8825-116294c725d3 · outbound

This paper cites PromptTTS 2: Describing and Generating Voices with Text Prompt.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis PromptTTS 2: Describing and Generating Voices with Text Prompt

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.841801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 084a1113-77e1-4aaf-836c-35857e15c28e · outbound

This paper cites Instructtts: Modelling expressive tts in discrete latent space with natural lan- guage style prompt,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Instructtts: Modelling expressive tts in discrete latent space with natural lan- guage style prompt,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.765506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b6a76d86-87f8-48ce-ac8e-37bd5dc32208 · outbound

This paper cites Natural language guidance of high-fidelity text-to-speech with synthetic annotations.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Natural language guidance of high-fidelity text-to-speech with synthetic annotations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.849652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02056422-fa70-46ed-b4bb-963fc2b1fe60 · outbound

This paper cites V oxinstruct: Expressive human instruction-to-speech generation with unified multilingual codec language modelling,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis V oxinstruct: Expressive human instruction-to-speech generation with unified multilingual codec language modelling,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.755234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c700938b-0062-403e-a8ce-f40cb29a6b4c · outbound

This paper cites Emovoice: Llm-based emotional text-to-speech model with freestyle text prompting,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Emovoice: Llm-based emotional text-to-speech model with freestyle text prompting,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.856918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e951b5e-af90-44a8-bb98-d41fec64bdc4 · outbound

This paper cites Scaling rich style- prompted text-to-speech datasets,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Scaling rich style- prompted text-to-speech datasets,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.739353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 79554df0-aee5-4816-9128-5e0f94e067c7 · outbound

This paper cites CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.862468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe29e582-b9c6-49c5-be71-2ed5e983fda7 · outbound

This paper cites Vevo2: A unified and controllable frame- work for speech and singing voice generation,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Vevo2: A unified and controllable frame- work for speech and singing voice generation,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.865457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77015045-1b72-499d-b93f-68edfef23e56 · outbound

This paper cites Mela-tts: Joint transformer-diffusion model with representation alignment for speech synthesis,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Mela-tts: Joint transformer-diffusion model with representation alignment for speech synthesis,

Reference 28

Resolution: verified exact; raw_fallback, observed 2026-08-12T00:10:41.326818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 737ebbf5-97a5-4e61-babd-a06700e970b1 · outbound

This paper cites Streammel: Real-time zero-shot text-to-speech via interleaved continuous autoregressive model- ing,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Streammel: Real-time zero-shot text-to-speech via interleaved continuous autoregressive model- ing,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.728008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation da98a471-810b-4dd6-bc07-a3d615f58348 · outbound

This paper cites High-fidelity audio compression with improved rvqgan,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis High-fidelity audio compression with improved rvqgan,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.873950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ff38436-b674-4f67-bf61-c21289a03c4c · outbound

This paper cites BigVGAN: A Universal Neural Vocoder with Large-Scale Training.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis BigVGAN: A Universal Neural Vocoder with Large-Scale Training

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.876765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beed7ec7-66d0-4a8d-bd5d-29038c9034eb · outbound

This paper cites CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.880326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0755047a-85de-4b8a-bc6b-0994e4d246ff · outbound

This paper cites CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.883298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ff20da-d32e-4471-a84a-e20044149be6 · outbound

This paper cites World: a vocoder-based high-quality speech synthesis system for real-time applications,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis World: a vocoder-based high-quality speech synthesis system for real-time applications,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.605365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 189bfeb3-c9ad-4c0e-8c7e-ef64b20f164f · outbound

This paper cites Fast and reliable f0 estimation method based on the period extraction of vocal fold vi- bration of singing voice and speech,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Fast and reliable f0 estimation method based on the period extraction of vocal fold vi- bration of singing voice and speech,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.594371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b72ed2be-5ade-4a44-acc6-a08a36515fb1 · outbound

This paper cites Continuous-token diffu- sion for speaker-referenced tts in multimodal llms,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Continuous-token diffu- sion for speaker-referenced tts in multimodal llms,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.892028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c808d725-d472-4221-8b5e-224e44c2a1e5 · outbound

This paper cites Emilia: An extensive, multilingual, and diverse speech dataset for large-scale speech generation,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Emilia: An extensive, multilingual, and diverse speech dataset for large-scale speech generation,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.895164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8b16eb8-10f0-4ab0-b52d-b78e3a58f35a · outbound

This paper cites GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.898571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddd65d55-f795-4692-8566-41c299c3f5cd · outbound

This paper cites Seed-TTS: A Family of High-Quality Versatile Speech Generation Models.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.901548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8e17983-8473-41d0-9f8d-acb9088a8536 · outbound

This paper cites The lj speech dataset,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis The lj speech dataset,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.904905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f85e8df-6a19-498c-bf75-d4205c79f7bd · outbound

This paper cites Semantic-vae: Semantic- alignment latent representation for better speech synthesis,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Semantic-vae: Semantic- alignment latent representation for better speech synthesis,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.907818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da8fe183-b02b-44f7-a098-089abdda655d · outbound

This paper cites Classifier-Free Diffusion Guidance.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Classifier-Free Diffusion Guidance

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.910596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 306d53bf-9ffc-46cf-bb8f-106d97ccf6a7 · outbound

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

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Robust speech recognition via large-scale weak supervision,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.913810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d0016ae-58fc-4a76-b7b2-9bf848779e45 · outbound

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

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Wavlm: Large-scale self- supervised pre-training for full stack speech processing,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T00:10:40.917178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ed6a26b-8b9c-4c3b-901a-7ed2ba1a11a2 · outbound

This paper cites Drawspeech: Expressive speech synthesis using prosodic sketches as control conditions,.

CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis Drawspeech: Expressive speech synthesis using prosodic sketches as control conditions,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:10:41.556446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 6a494d1b-0a14-4601-98f0-8bc0bcb2ac01 · inbound