Paper Citation Record · LEDGER

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation

As of 17 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2608.00545.

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

pith.paper-citation-record.v1
2608.00545 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T00:43:27.497465Z

measured 41 of 41 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 2026-08-05T00:43:24.605598Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T00:43:28.653584Z

Reference resolution

40 of 40 outbound references displayed

verified exact5
verified fuzzy24
unresolved8
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f2c67c2c-2d77-4bdf-84b3-e3939f851936 · outbound

This paper cites Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-05T00:43:28.743868Z

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 1af93a5b-9a40-4083-b75d-02b864f15360 · outbound

This paper cites Natural-language control of speech Controllable speech generation has traditionally relied on either global style representations or explicitly defined acoustic factors.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Natural-language control of speech Controllable speech generation has traditionally relied on either global style representations or explicitly defined acoustic factors

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:34.011411Z

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 6db9e2a1-44e4-4da9-90bc-5cf3904900c8 · outbound

This paper cites Systems and generation matrix We evaluate CosyV oice3, V oxCPM2, and Fish-Speech-S2, three in- dependently developed reference-conditioned speech-generation sys- tems.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Systems and generation matrix We evaluate CosyV oice3, V oxCPM2, and Fish-Speech-S2, three in- dependently developed reference-conditioned speech-generation sys- tems

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:33.995825Z

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 f101efea-c6d6-4bf3-a55e-bb8d2bfb4899 · outbound

This paper cites Target dir.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Target dir

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:33.981480Z

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 000c481e-3285-4b69-b20b-f6f44bd78ae0 · outbound

This paper cites Eligible.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Eligible

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:33.967338Z

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 7a20f43f-20d1-4052-b10a-4cfed696f46f · outbound

This paper cites H1 evaluates whether target and off-target changes are perceptible relative to a matched baseline, while H2 compares the candidates selected by V oDER-Cal and Target-only selection.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation H1 evaluates whether target and off-target changes are perceptible relative to a matched baseline, while H2 compares the candidates selected by V oDER-Cal and Target-only selection

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:33.953904Z

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 41c289c5-1e8c-430e-b6d0-ac3219c99aa0 · outbound

This paper cites an unresolved cited work.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Unresolved cited work

Reference 7

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T00:43:33.939870Z

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 f1e88653-5ac0-4c5c-a5e3-6d7d5580e918 · outbound

This paper cites Prompt adherence and attribute preservation are comple- mentary Prompt adherence and attribute preservation capture different aspects of controllability.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Prompt adherence and attribute preservation are comple- mentary Prompt adherence and attribute preservation capture different aspects of controllability

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:33.793626Z

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 ab4a9aa8-a37a-4006-be16-2b4b6b2b442d · outbound

This paper cites When attribute-specific editing is desired, evaluation must also test whether characteristics outside the requested target remain stable.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation When attribute-specific editing is desired, evaluation must also test whether characteristics outside the requested target remain stable

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:33.617402Z

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 7c42b87d-6d7f-47f2-8c1d-c474cba9842a · outbound

This paper cites PromptTTS: Controllable text-to-speech with text descriptions,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation PromptTTS: Controllable text-to-speech with text descriptions,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:33.407854Z

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 2b43486c-39a6-4f3f-823a-f9b0bc69cde3 · outbound

This paper cites InstructTTS: Modelling expressive tts in discrete latent space with natural language style prompt,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation InstructTTS: Modelling expressive tts in discrete latent space with natural language style prompt,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:33.134775Z

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 f128f87b-acbf-468a-8894-064982a0c5d7 · outbound

This paper cites PromptTTS 2: Describing and generating voices with text prompt,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation PromptTTS 2: Describing and generating voices with text prompt,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:32.848451Z

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 39ee1fe6-e0ae-4ed9-b9e4-74bdd267ec76 · outbound

This paper cites PromptStyle: Controllable Style Transfer for Text-to-Speech with Natural Language Descriptions.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation PromptStyle: Controllable Style Transfer for Text-to-Speech with Natural Language Descriptions

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T00:43:25.535345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7567a70d-f866-4bd4-92b8-1fe4e765f6fb · outbound

This paper cites PromptTTS++: Controlling speaker identity in prompt-based text-to-speech using natural language descriptions,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation PromptTTS++: Controlling speaker identity in prompt-based text-to-speech using natural language descriptions,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:32.608542Z

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 a8c758e2-63a4-43ba-9829-9ab1ff2a3fd4 · outbound

This paper cites ControlSpeech: Towards simultane- ous and independent zero-shot speaker cloning and zero-shot language style control,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation ControlSpeech: Towards simultane- ous and independent zero-shot speaker cloning and zero-shot language style control,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:32.189142Z

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 956cd6c5-0acb-4932-b44c-d615a586d851 · outbound

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

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T00:43:25.749513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3284906c-4f32-48b2-b704-264a0680c73e · outbound

This paper cites VoxCPM2 Technical Report.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation VoxCPM2 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T00:43:25.858970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc6f3b1-03c7-47a1-8041-5a5499cbda76 · outbound

This paper cites Fish Audio S2 technical report,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Fish Audio S2 technical report,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T00:43:25.899839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5df56a05-5f12-435d-b0bd-29cf0d59075b · outbound

This paper cites OV-InstructTTS: To- wards open-vocabulary instruct text-to-speech,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation OV-InstructTTS: To- wards open-vocabulary instruct text-to-speech,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T00:43:25.981554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a0cba3a-5d83-4ab8-b3f3-948da64a8d1d · outbound

This paper cites FlexiV oice: Enabling flexible style control in zero-shot tts with natural language instructions,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation FlexiV oice: Enabling flexible style control in zero-shot tts with natural language instructions,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T00:43:26.042228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e39b400-d8f9-48ee-812f-f0de8a735222 · outbound

This paper cites InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T00:43:26.122470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d17f93-6144-49a4-8d7e-ae14f41e4480 · outbound

This paper cites SPAM: Style prompt adherence metric for prompt-based tts,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation SPAM: Style prompt adherence metric for prompt-based tts,

Reference 22

Resolution: verified exact; raw_fallback, observed 2026-08-05T00:43:28.270669Z

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 460139f4-f9ee-4b29-9205-a549ac959f73 · outbound

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

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Towards end-to-end prosody transfer for expressive speech synthesis with tacotron,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:31.832623Z

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 6547024f-7e78-4574-b7cf-3c8e7571bfdc · outbound

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

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:31.522677Z

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 26bb9f86-b1d1-4c8f-8c00-932ca589e3bb · outbound

This paper cites FastSpeech 2: Fast and high-quality end-to- end text to speech,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation FastSpeech 2: Fast and high-quality end-to- end text to speech,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:31.244938Z

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 08d228ec-9df4-43f1-a5a1-a493431dfbe5 · outbound

This paper cites FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-05T00:43:28.089113Z

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 c24f49b8-bcbc-4b2e-876c-343b6eb3134c · outbound

This paper cites DisCo-Speech: Controllable zero-shot speech generation with a disentangled speech codec,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation DisCo-Speech: Controllable zero-shot speech generation with a disentangled speech codec,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T00:43:26.523554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fb23b82-7194-4f52-8e32-4d7e31332b25 · outbound

This paper cites Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-05T00:43:27.825771Z

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 c1353b3f-80c8-4ef5-b548-9c29d8c04e83 · outbound

This paper cites Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-05T00:43:27.679553Z

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 9f7420a2-d0ea-42b0-aace-54fc24364f4c · outbound

This paper cites librosa: Audio and music signal analysis in python,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation librosa: Audio and music signal analysis in python,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:30.908644Z

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 f969820c-6a57-4b90-84b0-1c31520ec666 · outbound

This paper cites pYIN: A fundamental fre- quency estimator using probabilistic threshold distributions,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation pYIN: A fundamental fre- quency estimator using probabilistic threshold distributions,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:30.637156Z

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 8ade6e93-30cd-4431-8f56-649437d81dd1 · outbound

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

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Robust speech recognition via large-scale weak supervision,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:30.386649Z

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 9b296ea7-0a8f-4de5-9a0a-4a0ce7ef5de8 · outbound

This paper cites ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:30.275377Z

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 e6317aef-e4d4-4892-b8e6-4361d4a938b4 · outbound

This paper cites X-vectors: Robust dnn em- beddings for speaker recognition,.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation X-vectors: Robust dnn em- beddings for speaker recognition,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:30.099429Z

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 679055f3-4a95-4f43-a588-f68c48c3a2ee · outbound

This paper cites Systems and model identifiers Table 3 lists the three systems, model identifiers, and control inter- faces used for generation.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Systems and model identifiers Table 3 lists the three systems, model identifiers, and control inter- faces used for generation

Reference 35

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T00:43:29.911410Z

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 88064882-defe-47f4-becf-8dcfc1d4f365 · outbound

This paper cites Acoustic and prosodic measurements The analysis uses F0, speaking rate, duration, RMS energy, spectral centroid, 85% spectral roll-off, spectral flatness, and zero-crossing rate.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Acoustic and prosodic measurements The analysis uses F0, speaking rate, duration, RMS energy, spectral centroid, 85% spectral roll-off, spectral flatness, and zero-crossing rate

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:29.748678Z

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 914c2ea9-e9d4-4359-8b18-3217e9097ebc · outbound

This paper cites Responsive.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Responsive

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:29.537975Z

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 c28ffc11-fddb-45f8-b29e-95778b1ec6e0 · outbound

This paper cites Policies and operating point The candidate budget counts descriptor-conditioned generations; the matched neutral baseline y0 is shared across all policies and is not included in B.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation Policies and operating point The candidate budget counts descriptor-conditioned generations; the matched neutral baseline y0 is shared across all policies and is not included in B

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:29.330524Z

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 22edf21a-4aba-4921-bd41-eb509ebf9f80 · outbound

This paper cites no difference.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation no difference

Reference 39

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T00:43:29.160492Z

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 b80b9f84-81a7-487f-b09f-6c15861a9567 · outbound

This paper cites V oDER-Cal shows that preservation-aware ranking can select candidates with lower measured off-target devia- tion from a fixed pool.

Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation V oDER-Cal shows that preservation-aware ranking can select candidates with lower measured off-target devia- tion from a fixed pool

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:43:28.945666Z

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 f2c67c2c-2d77-4bdf-84b3-e3939f851936 · inbound