Paper Citation Record · LEDGER

Uni-VERSA: Versatile Speech Assessment with a Unified Network

As of 22 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 2 inbound Pith citation observations for arXiv:2505.20741.

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

pith.paper-citation-record.v1
2505.20741 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:52:59.789462Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:52:56.895340Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T00:59:56.523759Z

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy36
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f8dd4428-aa9e-4618-8cb7-6785b1586b9a · outbound

This paper cites an unresolved cited work.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:53:09.946455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bf691886-94f3-496c-89ed-e78c946ed9be · outbound

This paper cites Uni-VERSA: Versatile Speech Assessment with a Unified Network.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Uni-VERSA: Versatile Speech Assessment with a Unified Network

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:56.895340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6abbb4e3-f726-49b5-a770-f1f7f47bb5aa · outbound

This paper cites URGENT24 Benchmark The Universality, Robustness, and Generalizability for EnhancemeNT (URGENT) 2024 challenge, hosted at NeurIPS2024, is a speech enhancement competition.

Uni-VERSA: Versatile Speech Assessment with a Unified Network URGENT24 Benchmark The Universality, Robustness, and Generalizability for EnhancemeNT (URGENT) 2024 challenge, hosted at NeurIPS2024, is a speech enhancement competition

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:09.659138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f1a65e41-53a0-4d99-9e52-7ede96f9b145 · outbound

This paper cites Our experiments on the UR- GENT24 benchmark and out-of-domain scenarios demonstrate its effectiveness for various applications.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Our experiments on the UR- GENT24 benchmark and out-of-domain scenarios demonstrate its effectiveness for various applications

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:09.162364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ada9a9c9-0072-4446-9a22-6377df22d411 · outbound

This paper cites We would like to thank Daniel Leong and Megan Choo for their valuable com- ments.

Uni-VERSA: Versatile Speech Assessment with a Unified Network We would like to thank Daniel Leong and Megan Choo for their valuable com- ments

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:08.869018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 21969747-e873-4f97-918d-096ab84370f0 · outbound

This paper cites On some biases encoun- tered in modern audio quality listening tests-a review,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network On some biases encoun- tered in modern audio quality listening tests-a review,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:57.840880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b2ab319-debc-412f-8190-fd13ef8eb79d · outbound

This paper cites The V oiceMOS challenge 2022,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network The V oiceMOS challenge 2022,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:08.641173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7e8012e9-25e3-4f80-8e9e-684accdb50e7 · outbound

This paper cites Conferencingspeech 2022 challenge: Non-intrusive objective speech quality assessment (NISQA) challenge for on- line conferencing applications,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Conferencingspeech 2022 challenge: Non-intrusive objective speech quality assessment (NISQA) challenge for on- line conferencing applications,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:08.321786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aa3d947e-ae1f-42e2-9f9a-1f0c6cc9f55e · outbound

This paper cites ESPnet-Codec: Com- prehensive training and evaluation of neural codecs for audio, mu- sic, and speech,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network ESPnet-Codec: Com- prehensive training and evaluation of neural codecs for audio, mu- sic, and speech,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:08.014315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c1f3e16b-3c80-4eaa-bd49-3c802e424ebf · outbound

This paper cites Objective measures of per- ceptual audio quality reviewed: An evaluation of their application domain dependence,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Objective measures of per- ceptual audio quality reviewed: An evaluation of their application domain dependence,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:07.785796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b5f50998-a105-47ed-b92f-61e02b878e54 · outbound

This paper cites A review on subjective and objective evaluation of syn- thetic speech,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network A review on subjective and objective evaluation of syn- thetic speech,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:07.544448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f49f62a3-e4a0-4487-bf51-8488fdedc0b6 · outbound

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

Uni-VERSA: Versatile Speech Assessment with a Unified Network Per- ceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:05.944786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 987a4219-68c2-4a1d-90ea-2160f45af944 · outbound

This paper cites Speech quality assessment,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Speech quality assessment,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:07.221136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5d17fbfa-14cd-458b-9aaa-c9b9acc1a941 · outbound

This paper cites Removing the bias in speech quality scores collected in noisy crowdsourcing environ- ments,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Removing the bias in speech quality scores collected in noisy crowdsourcing environ- ments,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:06.917644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b9ce6fe3-f802-4f98-9ae2-175878f43fa9 · outbound

This paper cites Towards speech quality assessment using a crowdsourcing approach: evaluation of standardized methods,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Towards speech quality assessment using a crowdsourcing approach: evaluation of standardized methods,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:06.577712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c308ebce-2ce4-41fd-8649-b2a7f9af6166 · outbound

This paper cites Ablation Studies.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Ablation Studies

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:09.459395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1606d301-34a1-41de-abd4-c4c4afdc96db · outbound

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

Uni-VERSA: Versatile Speech Assessment with a Unified Network VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:58.072917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecd92510-c37a-4e40-8df5-188c35967a31 · outbound

This paper cites Mel-cepstral distance measure for objective speech quality assessment,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Mel-cepstral distance measure for objective speech quality assessment,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:06.226696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 631ca2bb-45a5-4151-bb35-362547b8bf0d · outbound

This paper cites A short- time objective intelligibility measure for time-frequency weighted noisy speech,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network A short- time objective intelligibility measure for time-frequency weighted noisy speech,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:05.515858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8ef8c94e-d2ec-4753-ab26-d9e686c09ae0 · outbound

This paper cites DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise sup- pressors,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise sup- pressors,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:05.117695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e20111d8-74a9-4eeb-8c18-657144d9b0c3 · outbound

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

Uni-VERSA: Versatile Speech Assessment with a Unified Network UTMOS: Utokyo-sarulab system for voicemos challenge 2022,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:04.767907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7ad3e21d-7c9a-4e86-85f8-375e813f4c84 · outbound

This paper cites K ¨oster, Multidimensional analysis of conversational telephone speech.

Uni-VERSA: Versatile Speech Assessment with a Unified Network K ¨oster, Multidimensional analysis of conversational telephone speech

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:04.461154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0b65fe95-3af6-4165-ae3e-296ae6c3b35d · outbound

This paper cites Multi-dimensional speech quality assessment in crowdsourcing,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Multi-dimensional speech quality assessment in crowdsourcing,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:04.122369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 536d3fd8-787e-44d8-8de6-cad1c74e07c1 · outbound

This paper cites ESPnet: End-to-end speech processing toolkit,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network ESPnet: End-to-end speech processing toolkit,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:03.859821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3d75e311-6b0a-465c-9446-e6d629cfb2c0 · outbound

This paper cites Amphion: An Open-Source Audio, Music and Speech Generation Toolkit.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Amphion: An Open-Source Audio, Music and Speech Generation Toolkit

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:58.666332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88ac773b-e255-4b02-b58d-df5d5983edac · outbound

This paper cites AudioLDM: Text-to-audio generation with latent diffusion models,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network AudioLDM: Text-to-audio generation with latent diffusion models,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:03.649098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6167c837-1983-4e73-9ed8-cb0c5d94b405 · outbound

This paper cites Adapting frechet audio distance for generative music evaluation,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Adapting frechet audio distance for generative music evaluation,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:03.405808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 78e44141-ea53-4c6b-8f78-f276aa88ce7f · outbound

This paper cites UR- GENT challenge: Universality, robustness, and generalizability for speech enhancement,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network UR- GENT challenge: Universality, robustness, and generalizability for speech enhancement,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:03.179374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c5d4c295-6e50-4f9d-b47f-d0ea37af5c78 · outbound

This paper cites Torchaudio-Squim: Reference-less speech qual- ity and intelligibility measures in TorchAudio,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Torchaudio-Squim: Reference-less speech qual- ity and intelligibility measures in TorchAudio,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:02.938181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 543e0c36-ea48-42ac-a0a5-d33f792380ba · outbound

This paper cites SDR– half-baked or well done?.

Uni-VERSA: Versatile Speech Assessment with a Unified Network SDR– half-baked or well done?

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:02.735092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 36f45eac-5ff9-449a-bd4c-3ca421a1fd5c · outbound

This paper cites TASnet: time-domain audio separation network for real-time, single-channel speech separation,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network TASnet: time-domain audio separation network for real-time, single-channel speech separation,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:02.515803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3ef2c115-65d2-438d-9b4b-f96a248cf214 · outbound

This paper cites MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models.

Uni-VERSA: Versatile Speech Assessment with a Unified Network MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:59.087606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faacd7ef-7123-4145-8a12-5bae8bd1a658 · outbound

This paper cites SpeechBERTScore: Reference-aware automatic evaluation of speech generation leveraging nlp evaluation metrics,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network SpeechBERTScore: Reference-aware automatic evaluation of speech generation leveraging nlp evaluation metrics,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:02.270676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c9cf121e-60fa-46ef-960d-b01b4d44e248 · outbound

This paper cites Speaker recognition based on deep learning: An overview,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Speaker recognition based on deep learning: An overview,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:02.037602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 98c4a34b-d62a-446f-8c06-98bcaa120a8e · outbound

This paper cites NOMAD: Unsupervised learning of perceptual embeddings for speech enhancement and non-matching reference audio quality assessment,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network NOMAD: Unsupervised learning of perceptual embeddings for speech enhancement and non-matching reference audio quality assessment,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:01.760285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3a7660b6-9234-48c4-9373-5bdfd0a2e12d · outbound

This paper cites SCOREQ: Speech quality assessment with contrastive re- gression,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network SCOREQ: Speech quality assessment with contrastive re- gression,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:01.436898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ea572a16-8480-4881-9daa-d627a4dbd0e5 · outbound

This paper cites The V oiceMOS challenge 2023: zero-shot subjective speech quality prediction for multiple domains,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network The V oiceMOS challenge 2023: zero-shot subjective speech quality prediction for multiple domains,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:01.211934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 16d867d8-4609-49d6-b414-8895604f6d1f · outbound

This paper cites The V oiceMOS challenge 2024: Beyond speech quality prediction,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network The V oiceMOS challenge 2024: Beyond speech quality prediction,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:00.957314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9ae52342-1033-45f4-867b-6496d96c2888 · outbound

This paper cites Generaliza- tion ability of MOS prediction networks,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Generaliza- tion ability of MOS prediction networks,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:00.717723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 50fd1dbf-6ad1-4a02-aac5-060070bdbd31 · outbound

This paper cites WavLM: Large-scale self- supervised pre-training for full stack speech processing,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network WavLM: Large-scale self- supervised pre-training for full stack speech processing,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:59.597873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc62618-e045-4633-8ea7-bd288afb4e77 · outbound

This paper cites SUPERB: Speech processing universal performance benchmark,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network SUPERB: Speech processing universal performance benchmark,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:00.414178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aa7a8d49-ccc1-4094-97bb-954c7527f6ae · outbound

This paper cites HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:53:00.141517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 249ca42c-5c60-4629-b243-c0457bdd4ce9 · outbound

This paper cites Multi- resolution HuBERT: Multi-resolution speech self-supervised learning with masked unit prediction,.

Uni-VERSA: Versatile Speech Assessment with a Unified Network Multi- resolution HuBERT: Multi-resolution speech self-supervised learning with masked unit prediction,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:59.964482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

Observation bf691886-94f3-496c-89ed-e78c946ed9be · inbound