Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing | Paper Citation Record

Observation 44e6275d-a92a-4664-95eb-e73353117efa · outbound

This paper cites Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:51.171002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce6c192-db32-472a-8e7b-d9a5806ab78d · outbound

This paper cites We highlight the key gaps our work addresses.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing We highlight the key gaps our work addresses

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:51.219113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb66f06c-ae68-41a3-872b-0a03eca8a98e · outbound

This paper cites ambiguous zone.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing ambiguous zone

Reference 3

Resolution: malformed identifier; no resolver link, observed 2026-08-01T14:01:51.295352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27a3bd94-5e80-4bc0-a393-fa9f131bf48f · outbound

This paper cites meeting.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing meeting

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:51.376144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc3c567e-f20d-4e37-b565-9f0cb8d58b5d · outbound

This paper cites an unresolved cited work.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:51.433016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac7308a-9a78-4487-88bf-191a96f177e0 · outbound

This paper cites the the the problem.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing the the the problem

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:51.511733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae154345-7f23-4227-8b58-efe4ac08294e · outbound

This paper cites t- trr- transformer.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing t- trr- transformer

Reference 7

Resolution: malformed identifier; no resolver link, observed 2026-08-01T14:01:51.657822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fce74bf2-9af5-4dd7-8de2-24faeb3c78e5 · outbound

This paper cites an unresolved cited work.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:51.777018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e262a43d-41f2-4bf1-a8ef-6b129ca5c0a0 · outbound

This paper cites The experiments were run manually and results were manually verified.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing The experiments were run manually and results were manually verified

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:51.935028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c44b3b6-8cd2-4570-b45b-acac832afc5c · outbound

This paper cites Recording for eyes, not echoing to ears: Contextu- alized spoken-to-written conversion of ASR transcripts,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Recording for eyes, not echoing to ears: Contextu- alized spoken-to-written conversion of ASR transcripts,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.050680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7f7790c-ca12-4e3a-af07-a07d41804810 · outbound

This paper cites Preliminaries to a theory of speech disfluencies,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Preliminaries to a theory of speech disfluencies,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.141399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be3e2077-8a2a-4a91-af23-bae715e87b3d · outbound

This paper cites Clinical applications of disfluency analysis in neurological populations,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Clinical applications of disfluency analysis in neurological populations,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.299644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f1f6af6-1037-4a25-ac52-168f14883b94 · outbound

This paper cites A multi-stage feature pipeline on timestamped speech transcriptions for demen- tia assessment,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing A multi-stage feature pipeline on timestamped speech transcriptions for demen- tia assessment,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.358985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4150781f-8742-46e4-89e5-de814b4cd6c7 · outbound

This paper cites Careful whisper – lever- aging advances in automatic speech recognition for robust and interpretable aphasia subtype classification,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Careful whisper – lever- aging advances in automatic speech recognition for robust and interpretable aphasia subtype classification,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.439082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d23b803-83fb-4df4-89b5-fdb9b7e079d0 · outbound

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

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Emilia: A large-scale, extensive, multilingual, and diverse dataset for speech generation,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.518467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 926282f9-850d-4fad-a74f-d54f67ef7a39 · outbound

This paper cites DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.575783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae30c9f7-5986-4dc3-b51c-d0bb76e893ad · outbound

This paper cites Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.630038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6960b66-d470-4ba4-9ba0-c4a9026b2694 · outbound

This paper cites NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.696984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd39223-b293-492c-bf5e-9893a6096f9f · outbound

This paper cites StutterZero and StutterFormer: End-to-end speech con- version for stuttering transcription and correction,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing StutterZero and StutterFormer: End-to-end speech con- version for stuttering transcription and correction,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.779760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 921e3258-ff9d-4529-8da6-78b9a25553c7 · outbound

This paper cites From user perceptions to technical improvement: Enabling people who stutter to better use speech recognition,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing From user perceptions to technical improvement: Enabling people who stutter to better use speech recognition,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.849066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2a38ba8-dc16-4a7b-bbbc-01e314b15720 · outbound

This paper cites J-j-j-just stutter: Benchmarking whisper’s performance disparities on different stuttering patterns,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing J-j-j-just stutter: Benchmarking whisper’s performance disparities on different stuttering patterns,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:52.926505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67fede44-eeae-4033-8bfb-4dc939f88090 · outbound

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

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Robust speech recognition via large-scale weak su- pervision,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.003409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf884f6c-f8eb-4da1-98b8-4bba6afb2b0c · outbound

This paper cites Careless whisper: Speech-to-text hallucination harms,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Careless whisper: Speech-to-text hallucination harms,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.049097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad398ccf-1d16-40cd-9069-2db5e7d42ec3 · outbound

This paper cites Inclusive ASR for disfluent speech: Cascaded large- scale self-supervised learning with targeted fine-tuning and data augmentation,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Inclusive ASR for disfluent speech: Cascaded large- scale self-supervised learning with targeted fine-tuning and data augmentation,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.124397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 396d3f12-1cd3-43f5-9d7a-b1745b7fa57c · outbound

This paper cites Speech disfluency detection with contextual representation and data distillation,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Speech disfluency detection with contextual representation and data distillation,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.187980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bfc3073-53d9-4ad1-a641-e0a0dbc7501b · outbound

This paper cites Acoustically Precise Hesitation Tagging Is Essential for End-to-End Verbatim Transcription Systems.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Acoustically Precise Hesitation Tagging Is Essential for End-to-End Verbatim Transcription Systems

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.222937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4d07868-2bc8-41ac-b448-70f87a14995c · outbound

This paper cites Granary: Speech Recognition and Translation Dataset in 25 European Languages.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Granary: Speech Recognition and Translation Dataset in 25 European Languages

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.304842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ffe8e9c-4f24-48ba-9d45-78e5f3020a6f · outbound

This paper cites CrisperWhisper: Accu- rate timestamps on verbatim speech transcriptions,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing CrisperWhisper: Accu- rate timestamps on verbatim speech transcriptions,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.387456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fad52e2e-977b-4ab5-b07a-9386ceca49b8 · outbound

This paper cites Adapting an ASR foundation model for spoken language assessment,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Adapting an ASR foundation model for spoken language assessment,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.462642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b1620cc-0539-40e8-913e-35726678a8db · outbound

This paper cites Prompting Whisper for Improved Verbatim Transcription and End-to-end Miscue Detection.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Prompting Whisper for Improved Verbatim Transcription and End-to-end Miscue Detection

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.548746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a212a2d1-7aa5-4484-9808-117076413617 · outbound

This paper cites WhisperX: Time- accurate speech transcription of long-form audio,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing WhisperX: Time- accurate speech transcription of long-form audio,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.630740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db074faa-8d8b-4a7a-942b-5149a0a3e9d5 · outbound

This paper cites Reverb: Open-Source ASR and Diarization from Rev.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Reverb: Open-Source ASR and Diarization from Rev

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.710975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6be4d2e6-1c87-4051-a164-4357157e984c · outbound

This paper cites On disfluency and non-lexical sound labeling for end- to-end automatic speech recognition,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing On disfluency and non-lexical sound labeling for end- to-end automatic speech recognition,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.793050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cd78a1c-0426-4e1d-9ae3-ca980f95745d · outbound

This paper cites End-to-end spontaneous speech recognition using disfluency labeling,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing End-to-end spontaneous speech recognition using disfluency labeling,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.851612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02e57d87-fc66-4c7d-a52a-adf121a55728 · outbound

This paper cites Streaming joint speech recogni- tion and disfluency detection,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Streaming joint speech recogni- tion and disfluency detection,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:53.926735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cebc41c4-795e-42bd-a829-f4312d128c74 · outbound

This paper cites Augmenting Automatic Speech Recognition Models with Disfluency Detection.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Augmenting Automatic Speech Recognition Models with Disfluency Detection

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:54.020152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88663f5a-fc2a-4e66-8cd4-ebed03d8ce5e · outbound

This paper cites Filler word detection and classification: A dataset and benchmark,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Filler word detection and classification: A dataset and benchmark,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:54.137976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 007cdbce-3b36-42b3-b40a-7141a527b373 · outbound

This paper cites Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:54.263319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7ae5549-b09e-49fa-83d8-2064ede7096a · outbound

This paper cites End-to-end speech recognition and disfluency removal,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing End-to-end speech recognition and disfluency removal,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:54.353887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fbe12a0-3457-4cbe-821a-0f6405f15a7f · outbound

This paper cites Canary-1B- v2 & Parakeet-TDT-0.6B-v3: Efficient and high-performance models for multilingual ASR and AST,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Canary-1B- v2 & Parakeet-TDT-0.6B-v3: Efficient and high-performance models for multilingual ASR and AST,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:54.576131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e654202-3686-415d-bc6c-4856115aa2a8 · outbound

This paper cites Unconstrained dysfluency modeling for dysfluent speech transcription and detec- tion,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Unconstrained dysfluency modeling for dysfluent speech transcription and detec- tion,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:54.686188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24311d0f-a00c-48c0-bbba-e8cce2d9b39f · outbound

This paper cites Quantification of stylistic differences in human- and asr-produced transcripts of african american english,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Quantification of stylistic differences in human- and asr-produced transcripts of african american english,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:54.790253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6642d0d6-476f-4ddc-b81f-52f660187089 · outbound

This paper cites Toward zero oracle word error rate on the switchboard benchmark,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Toward zero oracle word error rate on the switchboard benchmark,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:54.974938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebab213f-8be6-49d7-9955-580d69ddbec8 · outbound

This paper cites Style-agnostic evaluation of ASR using multiple reference transcripts.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Style-agnostic evaluation of ASR using multiple reference transcripts

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:55.111522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49d3016c-87cd-4091-8218-86592a23c612 · outbound

This paper cites The AMI meeting corpus,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing The AMI meeting corpus,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:55.206337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cf1cd32-fd3f-430d-96f7-3de945b277b7 · outbound

This paper cites Open ASR leaderboard,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Open ASR leaderboard,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:55.336894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2e60607-89e8-4f15-a4e4-3b7605de6c8c · outbound

This paper cites AA-WER v2.0: Speech to text accuracy benchmark,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing AA-WER v2.0: Speech to text accuracy benchmark,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:55.445326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aee1fab-c795-4e92-a106-cdc99df44155 · outbound

This paper cites Monitoring and self-repair in speech,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Monitoring and self-repair in speech,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:55.651268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a75b81d1-05e2-4790-a348-0f4136a10359 · outbound

This paper cites The DARPA TIMIT acoustic-phonetic continuous speech corpus (TIMIT),.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing The DARPA TIMIT acoustic-phonetic continuous speech corpus (TIMIT),

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:55.830312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a39c9fda-c3a5-4736-9d4a-b62ac47d3816 · outbound

This paper cites The ICSI meeting corpus,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing The ICSI meeting corpus,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.003122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd807295-d9ab-4d17-90b7-14f766ba5883 · outbound

This paper cites The corpus of regional african american language,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing The corpus of regional african american language,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.162764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa423c09-aca5-40e7-8e4d-035a198f84e4 · outbound

This paper cites Building the singapore english national speech corpus,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Building the singapore english national speech corpus,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.310260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e55d300e-189e-4898-86b5-282e78f3a89f · outbound

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

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Lib- rispeech: An asr corpus based on public domain audio books,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.469142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9218462-71e4-454e-bb93-3bf82b0deedf · outbound

This paper cites Common V oice: A massively-multilingual speech corpus,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Common V oice: A massively-multilingual speech corpus,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.594826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c1a671-2b59-4ba9-b2c2-e4ec8963fc76 · outbound

This paper cites V ocalSound: A dataset for improv- ing human vocal sounds recognition,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing V ocalSound: A dataset for improv- ing human vocal sounds recognition,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.632279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44bd2396-82ef-4195-9de2-5c6d077f563c · outbound

This paper cites Nonspeech7k dataset: Clas- sification and analysis of human non-speech sound,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Nonspeech7k dataset: Clas- sification and analysis of human non-speech sound,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.686733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff84f8bf-6e64-4caa-94ed-60a15629f9f3 · outbound

This paper cites Fluency- Bank timestamped: An updated data set for disfluency detection and automatic intended speech recognition,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Fluency- Bank timestamped: An updated data set for disfluency detection and automatic intended speech recognition,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.766108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60281d11-ee67-40c2-ad82-4eeefe85fb57 · outbound

This paper cites Thorsten - open german voice (neutral) dataset,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Thorsten - open german voice (neutral) dataset,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.850693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef7c58f-2436-4946-9668-dd3388f86fdc · outbound

This paper cites Hello GPT-4o,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Hello GPT-4o,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:56.929943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7735832-9935-4586-88f0-1363abb99473 · outbound

This paper cites Montreal forced aligner: Trainable text-speech align- ment using kaldi,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Montreal forced aligner: Trainable text-speech align- ment using kaldi,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:57.011372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74a45263-2388-4ee2-978c-93a04c164039 · outbound

This paper cites Tradition or in- novation: A comparison of modern asr methods for forced align- ment,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Tradition or in- novation: A comparison of modern asr methods for forced align- ment,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:57.101414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8beab804-c710-41ae-b649-f074dbd988ae · outbound

This paper cites Introducing Universal-3 Pro: A new class of speech language model optimized for voice AI,.

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Introducing Universal-3 Pro: A new class of speech language model optimized for voice AI,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T14:01:57.214750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers