Paper Citation Record · LEDGER

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding

As of 8 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 2 inbound Pith citation observations for arXiv:2506.23986.

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

pith.paper-citation-record.v1
2506.23986 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:33:09.398427Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:33:08.012661Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-16T19:24:56.100817Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy20
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation af939dcf-9018-4294-b23e-0922d2fb973a · outbound

This paper cites StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:08.012661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f532344d-420f-430f-9a28-781ea3946d97 · outbound

This paper cites Flow Matching In this section, we provide a brief description of flow match- ing (FM).

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Flow Matching In this section, we provide a brief description of flow match- ing (FM)

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.534012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e5ef9385-723f-47a9-87b4-db0d40f742fe · outbound

This paper cites The overall architecture of StreamFlow is shown in Figure.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding The overall architecture of StreamFlow is shown in Figure

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.490143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 99694557-0692-4298-ba9b-6659ebb2bbc6 · outbound

This paper cites which consists of several DiT-blocks.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding which consists of several DiT-blocks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.460528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5e8a6657-52f2-4eae-b56f-16b4a75495b5 · outbound

This paper cites Training Setup For training, we use the Chinese and English subsets of Emilia [18], which totals 100,000 hours of speech data.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Training Setup For training, we use the Chinese and English subsets of Emilia [18], which totals 100,000 hours of speech data

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.428421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 55a60e7f-f1e5-416b-b797-f39a038804e4 · outbound

This paper cites Audio Quantity Table 1: Evaluation results for different flow matching models.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Audio Quantity Table 1: Evaluation results for different flow matching models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.393722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 17e0011e-2bed-472c-9443-2869cbd4b09e · outbound

This paper cites We design a local block-wise re- ceptive field method to achieve efficient streaming inference, particularly for long-speech scenarios.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding We design a local block-wise re- ceptive field method to achieve efficient streaming inference, particularly for long-speech scenarios

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.362930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 50bcb9bd-d56c-467e-9319-905d2ec5e122 · outbound

This paper cites GPT-4o System Card.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding GPT-4o System Card

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.002151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1674e72-35f9-47b6-a736-f14fc0742e96 · outbound

This paper cites Moshi: a speech-text foundation model for real-time dialogue.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Moshi: a speech-text foundation model for real-time dialogue

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.015142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05530dd0-80ff-4f3b-9ea7-aeec50083394 · outbound

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

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Fastspeech 2: Fast and high-quality end-to-end text to speech,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.328291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 567325f2-2229-41f0-832c-5c3c3f202f69 · outbound

This paper cites Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.288030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 795d4394-ad5d-47c7-af45-642d61378699 · outbound

This paper cites The NPU-HWC system for the ISCSLP 2024 inspirational and convincing audio generation challenge,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding The NPU-HWC system for the ISCSLP 2024 inspirational and convincing audio generation challenge,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.250720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 40e12eec-8569-4de8-89b0-2d584479c018 · outbound

This paper cites Better speech synthesis through scaling.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Better speech synthesis through scaling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.226193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23ea6e2f-b893-487e-bfd2-775d1214ab6d · outbound

This paper cites BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.236045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c503e55-8ba0-4943-9f41-c006f5503240 · outbound

This paper cites WavChat: A Survey of Spoken Dialogue Models.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding WavChat: A Survey of Spoken Dialogue Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.245104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352604ed-2f48-4060-a009-4db1f282658e · outbound

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

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.255755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e1311b8-b12f-4de8-af07-d1dff9397c44 · outbound

This paper cites GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.263696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4200131-3fce-4a3c-aee7-b8012ca01300 · outbound

This paper cites Flow matching for generative modeling,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Flow matching for generative modeling,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.274457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee2f4ec3-0353-4aa8-b5b8-623c4c9ac85d · outbound

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

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.281849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7190a612-32bb-4c98-a4d4-6ff32481edaa · outbound

This paper cites Scalable diffusion models with transform- ers,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Scalable diffusion models with transform- ers,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.196430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation edcce1d0-eb99-46b8-9e83-f4987c403a17 · outbound

This paper cites Neu- ral ordinary differential equations,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Neu- ral ordinary differential equations,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.151298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5ed1b539-69f1-4d23-839e-8f140aa3d1cd · outbound

This paper cites Ot-flow: Fast and accurate continuous normalizing flows via optimal transport,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Ot-flow: Fast and accurate continuous normalizing flows via optimal transport,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.115560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2bd2af22-e1a4-4b0b-b2b3-df675fa33038 · outbound

This paper cites Classifier-Free Diffusion Guidance.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Classifier-Free Diffusion Guidance

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.318495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7604f425-ecd0-40de-82fa-dd381754f178 · outbound

This paper cites Bigv- gan: A universal neural vocoder with large-scale training,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Bigv- gan: A universal neural vocoder with large-scale training,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.077849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9984cf1e-8e2c-41fd-8878-4c2e019d5754 · outbound

This paper cites Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T21:33:09.346129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a20e3c84-a006-4149-9071-eb9fbcc9273c · outbound

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

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.048625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0936b2b4-ac48-4b7b-89e1-9025e6d9d18e · outbound

This paper cites ECAPA-TDNN embeddings for speaker diarization,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding ECAPA-TDNN embeddings for speaker diarization,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:10.007729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 97b7a742-805c-488e-8847-6de20985fd3c · outbound

This paper cites Scaling rectified flow transformers for high-resolution image synthesis,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Scaling rectified flow transformers for high-resolution image synthesis,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:09.976627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5ca1bf57-08c2-43dc-ad74-212df3c06e6a · outbound

This paper cites An al- gorithm for intelligibility prediction of time-frequency weighted noisy speech,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding An al- gorithm for intelligibility prediction of time-frequency weighted noisy speech,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:09.934273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 56b79991-5dd1-4044-9388-89c213bb555e · outbound

This paper cites Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:09.898745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 82cca3e9-db15-4ba7-bf5c-fad3b0a15546 · outbound

This paper cites Visqol: an objective speech quality model,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding Visqol: an objective speech quality model,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:09.867144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0419bf99-df11-46db-9b66-3856acb9c303 · outbound

This paper cites UTMOS: utokyo-sarulab system for voicemos challenge 2022,.

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding UTMOS: utokyo-sarulab system for voicemos challenge 2022,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:33:09.836305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation af939dcf-9018-4294-b23e-0922d2fb973a · inbound