Paper Citation Record · LEDGER

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec

As of 13 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 2 inbound Pith citation observations for arXiv:2505.24314.

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

pith.paper-citation-record.v1
2505.24314 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:29:42.730075Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:29:38.143308Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T12:58:08.378519Z

Reference resolution

36 of 36 outbound references displayed

verified exact1
verified fuzzy7
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2fa164f2-80ec-4a8d-b819-b94dfee2e5c0 · outbound

This paper cites A pivotal challenge is the transformation of continuous speech signals into interpretable representations suitable for inference and training within large language models.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec A pivotal challenge is the transformation of continuous speech signals into interpretable representations suitable for inference and training within large language models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:29:45.426994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 76b3dc45-1f91-4739-b897-3356dcbba6c3 · outbound

This paper cites DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:38.143308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0c0a5dc-6434-47c6-b322-762abc0e66cd · outbound

This paper cites Dataset and Metrics We use LibriSpeech [27] to train the speech codec we proposed.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Dataset and Metrics We use LibriSpeech [27] to train the speech codec we proposed

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:29:45.216566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 50daa269-e8bb-427e-85fa-e338e3a0802c · outbound

This paper cites an unresolved cited work.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:29:45.003225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 135c561d-84a1-4b24-ad73-6fd213a3eb8b · outbound

This paper cites an unresolved cited work.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:38.724956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c93301bc-58d4-4e4a-895d-74c5133d163b · outbound

This paper cites GPT-4 Technical Report.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec GPT-4 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:38.877708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df8710a3-de5f-4dc5-a521-9e6086b4050e · outbound

This paper cites GPT-4o System Card.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec GPT-4o System Card

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:38.995350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66668e64-fd4e-4e02-80ef-9a0e7aedb0c6 · outbound

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

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:39.170430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d20e720-c46f-429d-940e-18ebc9537d45 · outbound

This paper cites Audiolm: a language modeling approach to audio gener- ation,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Audiolm: a language modeling approach to audio gener- ation,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:29:44.799493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dd6f89eb-99a1-4a4f-b2c3-2541d03efd3c · outbound

This paper cites AudioGen: Textually Guided Audio Generation.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec AudioGen: Textually Guided Audio Generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:39.487610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a05e72-d8c6-460b-8948-185223fca620 · outbound

This paper cites Slim- speech: Lightweight and efficient text-to-speech with slim recti- fied flow,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Slim- speech: Lightweight and efficient text-to-speech with slim recti- fied flow,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:29:44.553668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8aed8f60-4168-402d-833e-330fb7cca6b2 · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:39.703511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7f091b9-a0e6-4a24-993f-f5a1d4d7890b · outbound

This paper cites wav2vec: Unsupervised Pre-training for Speech Recognition.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec wav2vec: Unsupervised Pre-training for Speech Recognition

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:39.796888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fbe07b5-6546-48b6-b90f-3772504bdf95 · outbound

This paper cites Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:39.892248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78a5e2e8-1abb-47ea-85e7-721a5bb96f9d · outbound

This paper cites Neural discrete represen- tation learning,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Neural discrete represen- tation learning,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:29:44.307824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2523b863-a545-4f77-a382-86958b415664 · outbound

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

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Soundstream: An end-to-end neural audio codec,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:40.070603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6b6e291-50a2-419b-bda5-1d403f010a1e · outbound

This paper cites A review of vector quantization tech- niques,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec A review of vector quantization tech- niques,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:40.192413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f05c427-1b02-471e-9010-8995781d9162 · outbound

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

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec High-fidelity audio compression with improved rvqgan,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:40.359010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7be356b-fd57-472e-a7d5-42ef4f47fad2 · outbound

This paper cites High Fidelity Neural Audio Compression.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec High Fidelity Neural Audio Compression

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:40.426238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25530ef0-39a0-44ea-99d3-c96a65232ecd · outbound

This paper cites HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:40.551229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be0e75f5-0f79-433d-a3df-d9d60d153304 · outbound

This paper cites WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:40.695004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18ce0122-83d8-410c-a52c-5e72d928fc6a · outbound

This paper cites BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:40.791796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd699265-cf72-4969-8c57-dfa127b10c6c · outbound

This paper cites Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:40.894154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd0c454-47d4-4e4c-a0f1-a5ed8524626a · outbound

This paper cites Addressing Index Collapse of Large-Codebook Speech Tokenizer with Dual-Decoding Product-Quantized Variational Auto-Encoder.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Addressing Index Collapse of Large-Codebook Speech Tokenizer with Dual-Decoding Product-Quantized Variational Auto-Encoder

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:29:43.140544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 446a5104-842b-467a-b0a4-d240d0b57b5b · outbound

This paper cites NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:41.168284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4799653-6b8b-4791-8dde-31578b37c5f6 · outbound

This paper cites Neural networks fail to learn periodic functions and how to fix it,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Neural networks fail to learn periodic functions and how to fix it,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:41.272611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88b08a74-0353-4fc9-bb31-d1c8306b6e77 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec LLaMA: Open and Efficient Foundation Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:41.423921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea8bc6fa-13d4-4dc6-b9ed-2dc502f00316 · outbound

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

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Hifi-gan: Generative adversarial net- works for efficient and high fidelity speech synthesis,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:41.569951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72a21425-ef2f-45e1-b045-18c894474aed · outbound

This paper cites Vector-quantized Image Modeling with Improved VQGAN.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Vector-quantized Image Modeling with Improved VQGAN

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:41.764813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7dfcef2-cb64-443f-964a-127c625c7164 · outbound

This paper cites Product quantization for nearest neighbor search,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Product quantization for nearest neighbor search,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:41.908267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d360477-8cb8-4fd3-8c03-57363716f9aa · outbound

This paper cites Apcodec+: A spectrum-coding-based high-fidelity and high-compression-rate neural audio codec with staged training paradigm,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Apcodec+: A spectrum-coding-based high-fidelity and high-compression-rate neural audio codec with staged training paradigm,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:29:44.001741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 78882b71-3869-46ee-be91-9f552fe4d393 · outbound

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

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Lib- rispeech: an asr corpus based on public domain audio books,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:42.189677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7213156-5f1e-49bc-937f-5e62869b6ad6 · outbound

This paper cites Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:42.327056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e454bdb2-bee3-4c12-b1ac-760223fe8ed8 · outbound

This paper cites UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:42.472159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59040c31-6b56-4635-ba6f-3724689adf01 · outbound

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

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:42.622160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83dbc189-7a8e-4ccf-b0a1-1a46cc871e63 · outbound

This paper cites Fewer-token neural speech codec with time-invariant codes,.

DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Fewer-token neural speech codec with time-invariant codes,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:29:43.717631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

Observation 76b3dc45-1f91-4739-b897-3356dcbba6c3 · inbound