Paper Citation Record · LEDGER

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency

As of 9 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 1 inbound Pith citation observation for arXiv:2505.22515.

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

pith.paper-citation-record.v1
2505.22515 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:10:18.545560Z

measured 31 of 31 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:10:13.833228Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T13:10:18.923633Z

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy21
unresolved7
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3214d133-e3d0-4e42-8505-cae52e5aaf1f · outbound

This paper cites Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T13:10:19.104296Z

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 c4af061c-cb27-4952-a3b7-8ea52ba3e3a4 · outbound

This paper cites We then practically decom- pose it into two key capabilities: robust reconstruction quality and consistency on downstream signal processing tasks.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency We then practically decom- pose it into two key capabilities: robust reconstruction quality and consistency on downstream signal processing tasks

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:26.038387Z

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 bd4d2e1f-f7a4-447d-974d-64864ac2da96 · outbound

This paper cites Using this benchmark, several mainstream codecs are evaluated.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Using this benchmark, several mainstream codecs are evaluated

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:25.726165Z

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 6e1861d2-2f70-423b-a3b9-53b9e5fd5afb · outbound

This paper cites While a few codecs have comparatively better reconstruction quality, such as DAC [5], they still lack down- stream task consistency.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency While a few codecs have comparatively better reconstruction quality, such as DAC [5], they still lack down- stream task consistency

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:25.422742Z

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 4aa1e32d-57dc-40a1-95a5-bb1baca815b4 · outbound

This paper cites an unresolved cited work.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:10:25.146899Z

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 28b0e6cd-22cb-4bbf-8c43-46c99221fd8c · outbound

This paper cites w/o codec recon.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency w/o codec recon

Reference 6

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:10:24.848045Z

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 0ec85e33-c5aa-4c9e-8629-e851447a191d · outbound

This paper cites Our experiments show that none of the tested codecs perform well in both aspects.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Our experiments show that none of the tested codecs perform well in both aspects

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:24.597140Z

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 8936a41c-1560-4729-a944-0b88ad0ed044 · outbound

This paper cites 92370206), the Shanghai Municipal Science and Technol- ogy Major Project (2021SHZDZX0102) and the Key Re- search and Development Program of Jiangsu Province, China (No.BE2022059).

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency 92370206), the Shanghai Municipal Science and Technol- ogy Major Project (2021SHZDZX0102) and the Key Re- search and Development Program of Jiangsu Province, China (No.BE2022059)

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:24.354513Z

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 4c48144c-07ad-4700-99f7-4e07e8374713 · outbound

This paper cites Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:23.998348Z

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 5adb3320-db19-47ba-9466-af420e4bcf97 · outbound

This paper cites VioLA: Conditional Lan- guage Models for Speech Recognition, Synthesis, and Transla- tion,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency VioLA: Conditional Lan- guage Models for Speech Recognition, Synthesis, and Transla- tion,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:23.506954Z

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 2af725de-8077-4e40-95a5-8c5836f1d9b2 · outbound

This paper cites GenSE: Generative speech enhancement via language models using hier- archical modeling,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency GenSE: Generative speech enhancement via language models using hier- archical modeling,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:23.188475Z

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 0d1cc385-e16a-49d5-a4e5-f193666cfc8f · outbound

This paper cites High Fidelity Neu- ral Audio Compression,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency High Fidelity Neu- ral Audio Compression,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:22.889336Z

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 5c5cc042-50c5-4b0f-b7ce-9ea8425ecd46 · outbound

This paper cites High-Fidelity Audio Compression with Improved RVQGAN,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency High-Fidelity Audio Compression with Improved RVQGAN,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:22.659194Z

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 f570a2db-810d-4fca-8c42-1110c2784911 · outbound

This paper cites SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:22.492429Z

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 ecd4377b-9c82-459b-bd6c-53d2c2809887 · outbound

This paper cites SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:22.203927Z

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 4d8e903d-7815-4b5d-88b7-e66dcf891891 · outbound

This paper cites Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:16.250961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caefb2d7-14b4-4978-ae73-df1d869aafec · outbound

This paper cites Recent advances in discrete speech tokens: A review,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Recent advances in discrete speech tokens: A review,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:16.373501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 950b4b5e-2fde-45a2-a7ee-fd29e7c2b0c7 · outbound

This paper cites HuBERT: Self- Supervised Speech Representation Learning by Masked Predic- tion of Hidden Units,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency HuBERT: Self- Supervised Speech Representation Learning by Masked Predic- tion of Hidden Units,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:21.869382Z

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 7f60830f-debe-4ed1-b360-a5ed97ca6c50 · outbound

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

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:16.744389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3220e114-b8ea-4d27-bc95-11c8041ad9ef · outbound

This paper cites Codec-SUPERB: An In-Depth Analysis of Sound Codec Models.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Codec-SUPERB: An In-Depth Analysis of Sound Codec Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:16.855230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 318945e0-f53b-43ab-9bf4-1a5c01d0b38a · outbound

This paper cites DASB - Discrete Audio and Speech Benchmark.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency DASB - Discrete Audio and Speech Benchmark

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:17.038345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ead3b84-04e7-4acc-b451-8fbf2e2ec5e8 · outbound

This paper cites ICASSP 2023 deep noise suppression challenge,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency ICASSP 2023 deep noise suppression challenge,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:21.591563Z

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 6417ce1e-ee8c-47ae-9a5d-4a20b0e24dbe · outbound

This paper cites TorchAudio-Squim: Reference-less speech quality and intelligibility measures in torchaudio,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency TorchAudio-Squim: Reference-less speech quality and intelligibility measures in torchaudio,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:21.248913Z

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 5e2faa5e-e469-4c19-8f2e-cb2b29eedaad · outbound

This paper cites The PASCAL CHiME speech separation and recognition challenge,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency The PASCAL CHiME speech separation and recognition challenge,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:20.917315Z

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 d028e555-6523-4179-9060-1c7d7df16c04 · outbound

This paper cites The INTERSPEECH 2020 deep noise suppression challenge: Datasets, subjective testing framework, and challenge results,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency The INTERSPEECH 2020 deep noise suppression challenge: Datasets, subjective testing framework, and challenge results,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:20.605173Z

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 67e13fb2-097b-4086-9aca-94cff3979ba9 · outbound

This paper cites The 4th CHiME speech separation and recognition challenge,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency The 4th CHiME speech separation and recognition challenge,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:20.318390Z

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 4d04acfa-e957-4270-8e55-96c45377047c · outbound

This paper cites Robust Speech Recognition via Large-Scale Weak Supervision,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Robust Speech Recognition via Large-Scale Weak Supervision,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:20.001058Z

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 d4de15e6-1453-4126-99da-8fe1fe38ec91 · outbound

This paper cites Attention is all you need in speech separation,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency Attention is all you need in speech separation,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:19.729246Z

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 4c2853f3-0088-4617-8002-3e3aef871dee · outbound

This paper cites WHAM!: Extending speech separation to noisy environments,.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency WHAM!: Extending speech separation to noisy environments,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:19.409079Z

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 c15c2178-688d-4af4-8e2d-1d99a5850cd5 · outbound

This paper cites VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music.

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:18.545560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 3214d133-e3d0-4e42-8505-cae52e5aaf1f · inbound