Paper Citation Record · LEDGER

SpectroStream: A Versatile Neural Codec for General Audio

As of 8 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 4 inbound Pith citation observations for arXiv:2508.05207.

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

pith.paper-citation-record.v1
2508.05207 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:33:19.743287Z

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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:33:19.656344Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T14:59:54.992758Z

Reference resolution

30 of 30 outbound references displayed

verified exact1
verified fuzzy20
unresolved7
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7c464923-91f2-4025-b754-ec05b9daf525 · outbound

This paper cites The de- velopment of SoundStream [1] was a key development that unlocked the potential of autogressive audio generation with standard language-modeling objectives [2].

SpectroStream: A Versatile Neural Codec for General Audio The de- velopment of SoundStream [1] was a key development that unlocked the potential of autogressive audio generation with standard language-modeling objectives [2]

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:22.596166Z

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 e200ab57-0403-4138-9ffa-c999d9a924c8 · outbound

This paper cites SpectroStream: A Versatile Neural Codec for General Audio.

SpectroStream: A Versatile Neural Codec for General Audio SpectroStream: A Versatile Neural Codec for General Audio

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T23:33:19.656344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f62aa91-0962-45fe-b91f-23e15d13c7da · outbound

This paper cites Unlike [17], we do not use the wave-based discrimina- tor [18].

SpectroStream: A Versatile Neural Codec for General Audio Unlike [17], we do not use the wave-based discrimina- tor [18]

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:22.427339Z

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 e15ce3c1-5de2-44b4-8759-2a767f3afccd · outbound

This paper cites Both the generator and the discriminators are updated exactly once in each step.

SpectroStream: A Versatile Neural Codec for General Audio Both the generator and the discriminators are updated exactly once in each step

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:22.253700Z

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 23c07c69-1ecf-4932-8924-20f963bafe2a · outbound

This paper cites A key innovation of our model lies in its 2D con- volutional architecture, which operates directly on the time- frequency representation.

SpectroStream: A Versatile Neural Codec for General Audio A key innovation of our model lies in its 2D con- volutional architecture, which operates directly on the time- frequency representation

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:22.093003Z

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 e80fe371-4b62-44bb-b593-b5b970936ad7 · outbound

This paper cites Soundstream: An end-to-end neural audio codec,.

SpectroStream: A Versatile Neural Codec for General Audio Soundstream: An end-to-end neural audio codec,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:21.955459Z

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 1f36ce13-882b-425f-ae5c-70fcd1ea6d74 · outbound

This paper cites Audiolm: A language modeling ap- proach to audio generation,.

SpectroStream: A Versatile Neural Codec for General Audio Audiolm: A language modeling ap- proach to audio generation,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:21.705949Z

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 0974b518-d5fd-417c-bc8d-33ecc50a4a36 · outbound

This paper cites High fidelity neural audio compression,.

SpectroStream: A Versatile Neural Codec for General Audio High fidelity neural audio compression,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T23:33:19.675147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f369632-7091-42a2-8800-300f7e21cf91 · outbound

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

SpectroStream: A Versatile Neural Codec for General Audio High-fidelity audio compression with improved RVQGAN,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:21.497743Z

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 12464c7a-ba1f-41c0-b0ea-e66387278c50 · outbound

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

SpectroStream: A Versatile Neural Codec for General Audio Moshi: a speech-text foundation model for real-time dialogue,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:21.243096Z

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 bb9933dd-52c1-4bef-9e9a-c83a5b1990c1 · outbound

This paper cites Fo- calcodec: Low-bitrate speech coding via focal modulation net- works,.

SpectroStream: A Versatile Neural Codec for General Audio Fo- calcodec: Low-bitrate speech coding via focal modulation net- works,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:21.049575Z

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 48c297d5-4eef-4e5c-8b06-0843d46f1920 · outbound

This paper cites FlowDec: A flow- based full-band general audio codec with high percep- tual quality,.

SpectroStream: A Versatile Neural Codec for General Audio FlowDec: A flow- based full-band general audio codec with high percep- tual quality,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:20.816294Z

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 19f95d28-7696-4534-91b2-42480e7f4f32 · outbound

This paper cites Streaming keyword spotting on mobile devices.

SpectroStream: A Versatile Neural Codec for General Audio Streaming keyword spotting on mobile devices

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-05T23:33:19.815592Z

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 5cae8b5f-7a0e-4f59-ad40-b5d30cf1e953 · outbound

This paper cites SEANet: A multi-modal speech enhancement network,.

SpectroStream: A Versatile Neural Codec for General Audio SEANet: A multi-modal speech enhancement network,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:20.600843Z

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 7da8ff5b-219d-4922-ae0e-deb83331618f · outbound

This paper cites SoundStorm: Efficient Parallel Audio Generation.

SpectroStream: A Versatile Neural Codec for General Audio SoundStorm: Efficient Parallel Audio Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T23:33:19.696010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b7ff75-c35a-4ac1-9019-bee20efc893b · outbound

This paper cites MusicRL: Aligning Music Generation to Human Preferences.

SpectroStream: A Versatile Neural Codec for General Audio MusicRL: Aligning Music Generation to Human Preferences

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T23:33:19.698892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7180966e-065d-4023-8728-156dd5dac211 · outbound

This paper cites MusicLM: Generating Music From Text.

SpectroStream: A Versatile Neural Codec for General Audio MusicLM: Generating Music From Text

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T23:33:19.701844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e92dc22c-4c24-4db6-bd5e-bdb9ecdf617c · outbound

This paper cites Weight normalization: A sim- ple reparameterization to accelerate training of deep neural net- works,.

SpectroStream: A Versatile Neural Codec for General Audio Weight normalization: A sim- ple reparameterization to accelerate training of deep neural net- works,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:20.347269Z

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 34e3d981-dd61-4ef7-869e-521e64fb2f1a · outbound

This paper cites Layer Normalization.

SpectroStream: A Versatile Neural Codec for General Audio Layer Normalization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T23:33:19.707384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a4eb047-f888-49fc-a1f5-8bf3e860aac3 · outbound

This paper cites Fast and accurate deep network learning by exponential linear units (ELUs),.

SpectroStream: A Versatile Neural Codec for General Audio Fast and accurate deep network learning by exponential linear units (ELUs),

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:20.126988Z

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 bd8da1e8-f09e-4cd0-a970-ec72d6bd0448 · outbound

This paper cites Rectifier nonlinear- ities improve neural network acoustic models,.

SpectroStream: A Versatile Neural Codec for General Audio Rectifier nonlinear- ities improve neural network acoustic models,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:19.992087Z

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 d8601910-cbbe-48a3-9f91-084b05f3dc41 · outbound

This paper cites ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric.

SpectroStream: A Versatile Neural Codec for General Audio ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T23:33:19.737744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 054d0725-59d0-462d-a96a-4a0e4b9694e8 · outbound

This paper cites Mel- GAN: Generative adversarial networks for conditional wave- form synthesis,.

SpectroStream: A Versatile Neural Codec for General Audio Mel- GAN: Generative adversarial networks for conditional wave- form synthesis,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:19.941283Z

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 a266bad2-600b-4564-907e-04a530907fca · outbound

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

SpectroStream: A Versatile Neural Codec for General Audio Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:19.922920Z

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 45ef31af-4c71-4aa4-ae12-89c02a060bf7 · outbound

This paper cites Generative adversarial nets,.

SpectroStream: A Versatile Neural Codec for General Audio Generative adversarial nets,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:19.907832Z

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 52fdf571-3564-4a2d-9612-49b1abf593a1 · outbound

This paper cites A spectral energy distance for parallel speech synthesis,.

SpectroStream: A Versatile Neural Codec for General Audio A spectral energy distance for parallel speech synthesis,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:19.889665Z

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 055f1448-0dc3-4760-9cd1-9895f10f4850 · outbound

This paper cites Adam: A method for stochastic opti- mization.

SpectroStream: A Versatile Neural Codec for General Audio Adam: A method for stochastic opti- mization

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:19.874354Z

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 b5b16f5f-dc56-4c85-8af2-c79286ac22f4 · outbound

This paper cites Visqol: The virtual speech quality objective listener,.

SpectroStream: A Versatile Neural Codec for General Audio Visqol: The virtual speech quality objective listener,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:33:19.855888Z

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 5d134de1-f0eb-4cca-b647-d575347d1f5f · outbound

This paper cites The MUSDB18 corpus for music separation,.

SpectroStream: A Versatile Neural Codec for General Audio The MUSDB18 corpus for music separation,

Reference 31

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T23:33:19.838150Z

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 c1c6205c-badc-4ad4-a03e-050f796a4e24 · outbound

This paper cites Wavesplit: End-to-End Speech Separation by Speaker Clustering.

SpectroStream: A Versatile Neural Codec for General Audio Wavesplit: End-to-End Speech Separation by Speaker Clustering

Reference 2020

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T23:33:19.776450Z

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 e200ab57-0403-4138-9ffa-c999d9a924c8 · inbound