Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-25T02:52:22.610397Z
Paper Citation Record · LEDGER
StepAudio 2.5 Technical Report
As of 10 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 4 inbound Pith citation observations for arXiv:2605.23463.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-08T18:13:04.179577Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-03T17:18:44.075741Z
Reference resolution
39 of 39 outbound references displayed
- verified exact20
- verified fuzzy18
- unresolved1
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 086e75aa-a6ef-417f-b944-038c36ad785f · outbound
This paper cites Connectionist temporal classification.
StepAudio 2.5 Technical Report Connectionist temporal classification
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.361557Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 14ae607c-95e5-44d1-bdf8-4b5aacb3f70c · outbound
This paper cites Sequence Transduction with Recurrent Neural Networks.
StepAudio 2.5 Technical Report Sequence Transduction with Recurrent Neural Networks
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.521251Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 6eab5b32-aab8-4e2a-a3fe-7d9fdbfc6b2a · outbound
This paper cites Listen, Attend and Spell.
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.509973Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 5eeac4c3-be4e-46d5-b52c-f412f6d551a2 · outbound
This paper cites Robust speech recognition via large-scale weak supervision.
StepAudio 2.5 Technical Report Robust speech recognition via large-scale weak supervision
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.353701Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation df029add-8e4b-4238-ab59-6d9334d01e84 · outbound
This paper cites VIBEVOICE-ASR technical report.
StepAudio 2.5 Technical Report VIBEVOICE-ASR technical report
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.526933Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 5e20d531-5ce5-478e-afeb-3a15edf3fa37 · outbound
This paper cites Fun-ASR technical report.
StepAudio 2.5 Technical Report Fun-ASR technical report
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.532217Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 91001d88-a7f2-4930-8541-dc76486a95f5 · outbound
This paper cites Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition.
StepAudio 2.5 Technical Report Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.515698Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9fd13268-45a3-43f5-a739-bfc06b0f025e · outbound
This paper cites Qwen3-ASR Technical Report.
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.483222Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation ae35f11f-b45b-4570-a385-d37c6d821ce6 · outbound
This paper cites Step-Audio 2 Technical Report.
StepAudio 2.5 Technical Report Step-Audio 2 Technical Report
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.487852Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 713f12d6-bd4a-407b-8965-ba391750f8e0 · outbound
This paper cites Qwen3-Omni Technical Report.
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.441821Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 0953c54f-6449-4679-b7a8-a5382add346c · outbound
This paper cites Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation.
StepAudio 2.5 Technical Report Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.477459Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation fc8064bb-97ff-403c-9dfd-eedabf2c2453 · outbound
This paper cites Salmonn: Towards generic hearing abilities for large language models.
StepAudio 2.5 Technical Report Salmonn: Towards generic hearing abilities for large language models
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.371149Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 57515c3d-9c92-4e8e-9189-36d3eb900b8a · outbound
This paper cites Audiolm: a language modeling approach to audio generation.IEEE/ACM transactions on audio, speech, and language processing, 31:2523–2533.
StepAudio 2.5 Technical Report Audiolm: a language modeling approach to audio generation.IEEE/ACM transactions on audio, speech, and language processing, 31:2523–2533
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.374738Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 350987e5-fa75-45d3-8571-0bcdb7a12996 · outbound
This paper cites Recent advances in speech language models: A survey.
StepAudio 2.5 Technical Report Recent advances in speech language models: A survey
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.379842Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation c59d0276-31d1-4f4f-b648-9517b90875b5 · outbound
This paper cites Paralinguistics-aware speech-empowered large language models for natural conversation.Advances in Neural Information Processing Systems, 37:131072–131103.
StepAudio 2.5 Technical Report Paralinguistics-aware speech-empowered large language models for natural conversation.Advances in Neural Information Processing Systems, 37:131072–131103
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.383483Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 0caf796e-e190-4ba0-b488-fdd8162c462c · outbound
This paper cites Freeze-omni: A smart and low latency speech-to-speech dialogue model with frozen LLM.
StepAudio 2.5 Technical Report Freeze-omni: A smart and low latency speech-to-speech dialogue model with frozen LLM
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.389815Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 2c452943-18a0-4a86-b196-e4b4c9f47119 · outbound
This paper cites Depflow: Disentangled speech generation to mitigate semantic bias in depression detection.
StepAudio 2.5 Technical Report Depflow: Disentangled speech generation to mitigate semantic bias in depression detection
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.431713Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9b34497f-a2a0-43e7-a002-f32ab6dbe7ee · outbound
This paper cites A new approach to extract fetal electrocardiogram using affine combination of adaptive filters.
StepAudio 2.5 Technical Report A new approach to extract fetal electrocardiogram using affine combination of adaptive filters
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.367549Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation e2be10c6-91b2-40e5-abf2-c6973cc89d8b · outbound
This paper cites Multi-bench: A multi-turn interactive benchmark for assessing emotional intelligence ability of spoken dialogue models.
StepAudio 2.5 Technical Report Multi-bench: A multi-turn interactive benchmark for assessing emotional intelligence ability of spoken dialogue models
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.436892Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation be94f0cd-1a89-49c5-9cc2-8a8b361e35e7 · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
StepAudio 2.5 Technical Report Gemini: A Family of Highly Capable Multimodal Models
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.463143Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation a0b65575-9b51-44bd-9706-5a1487dd1153 · outbound
This paper cites Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models.
StepAudio 2.5 Technical Report Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.472393Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 3f84023c-a4ee-4d5f-bc42-95785eff768a · outbound
This paper cites Chronological thinking in full-duplex spoken dialogue language models.
StepAudio 2.5 Technical Report Chronological thinking in full-duplex spoken dialogue language models
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.505381Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 63082297-3c5c-4db9-aca2-327d8a2db705 · outbound
This paper cites Duplexsla: A full-duplex spoken language model with synchronized speech, language, and action.
StepAudio 2.5 Technical Report Duplexsla: A full-duplex spoken language model with synchronized speech, language, and action
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.386641Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 20c44ea9-682f-4e47-ab7b-0581c94a5b9b · outbound
This paper cites Mamba in speech: Towards an alternative to self-attention.IEEE Transactions on Audio, Speech and Language Processing.
StepAudio 2.5 Technical Report Mamba in speech: Towards an alternative to self-attention.IEEE Transactions on Audio, Speech and Language Processing
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.392860Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation df5d89ca-d3a6-4fe0-b631-566a1f8999a9 · outbound
This paper cites Code-switching speech recognition under the lens: Model-and data-centric perspectives.IEEE Transactions on Audio, Speech and Language Processing.
StepAudio 2.5 Technical Report Code-switching speech recognition under the lens: Model-and data-centric perspectives.IEEE Transactions on Audio, Speech and Language Processing
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.396848Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 413f7c81-0419-41ee-9e47-258ff55a93e6 · outbound
This paper cites Step-audio-r1 technical report.
StepAudio 2.5 Technical Report Step-audio-r1 technical report
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.500260Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 61a5a62a-d7e4-43fe-b7da-eb8aaabcd02b · outbound
This paper cites Step-Audio-R1.5 Technical Report.
StepAudio 2.5 Technical Report Step-Audio-R1.5 Technical Report
Reference 28
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.494617Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 6bef68ea-45ae-41f8-adba-1faf1a74e168 · outbound
This paper cites Park, William Chan, Yu Zhang, et al.
StepAudio 2.5 Technical Report Park, William Chan, Yu Zhang, et al
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.402758Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 1a6e80ea-7904-4bf1-ba00-a51938a47ef3 · outbound
This paper cites an unresolved cited work.
StepAudio 2.5 Technical Report Unresolved cited work
Reference 30
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T02:56:35.406529Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 697f37fc-63c2-408f-8eb4-c9cef2fdab7e · outbound
This paper cites AIShell-1: An open-source mandarin speech corpus and a speech recognition baseline.
StepAudio 2.5 Technical Report AIShell-1: An open-source mandarin speech corpus and a speech recognition baseline
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.409728Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 01cf541e-269d-45f9-9451-c73612401bd9 · outbound
This paper cites AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale.
StepAudio 2.5 Technical Report AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.451910Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 8d2d211f-feb6-4434-83a8-468b733a68fc · outbound
This paper cites WenetSpeech: A 10000+ hours multi-domain mandarin corpus for speech recognition.
StepAudio 2.5 Technical Report WenetSpeech: A 10000+ hours multi-domain mandarin corpus for speech recognition
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.422611Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 49a49c25-9c27-466e-ae3e-3b83d2481bb9 · outbound
This paper cites FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech.
StepAudio 2.5 Technical Report FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.447086Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 01041449-4711-47c4-8cb1-e0f0585030bc · outbound
This paper cites LibriSpeech: An ASR corpus based on public domain audio books.
StepAudio 2.5 Technical Report LibriSpeech: An ASR corpus based on public domain audio books
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.425885Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 8f1435fe-f4a1-4c63-b748-925370e9a75e · outbound
This paper cites Common voice: A massively-multilingual speech corpus.
StepAudio 2.5 Technical Report Common voice: A massively-multilingual speech corpus
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.419215Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 6c171711-18e3-4de3-9885-1f7b8eac9738 · outbound
This paper cites V oxpopuli-cleaned-aa: Cleaned ground truth transcripts for voxpopuli english test set.
StepAudio 2.5 Technical Report V oxpopuli-cleaned-aa: Cleaned ground truth transcripts for voxpopuli english test set
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.415860Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9d1bfb95-8e08-47a5-b14c-f7e005da005c · outbound
This paper cites Earnings22-cleaned-aa: Cleaned ground truth transcripts for earnings22 english test set.
StepAudio 2.5 Technical Report Earnings22-cleaned-aa: Cleaned ground truth transcripts for earnings22 english test set
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T02:56:35.412796Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 4534e43b-4358-4eec-be62-10f5a597de92 · outbound
This paper cites Step-audio-editx technical report.
StepAudio 2.5 Technical Report Step-audio-editx technical report
Reference 39
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T02:55:16.458036Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation ae24bc43-fe61-4d31-a7a5-2443a782c1a9 · outbound
This paper cites Proximal Policy Optimization Algorithms.
StepAudio 2.5 Technical Report Proximal Policy Optimization Algorithms
Reference 40
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T02:55:16.467568Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Pith citing papers
Observation 789faeb4-f885-46e4-a64f-704563c7b88e · inbound
Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech cites this paper.
Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech StepAudio 2.5 Technical Report
Reference 23
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T17:18:44.077038Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation a05dba3a-3f4d-45fe-ad13-fa4c033e29f2 · inbound
ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition cites this paper.
ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition StepAudio 2.5 Technical Report
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T10:13:56.110991Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e4b4e415-38b6-40d6-9aca-411f1eb58d31 · inbound
Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders cites this paper.
Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders StepAudio 2.5 Technical Report
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T21:28:33.190018Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 090e4f5b-a5f6-48b6-8b13-4f2c233b7f3c · inbound
Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders cites this paper.
Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders StepAudio 2.5 Technical Report
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-08T18:13:04.179577Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.