Paper Citation Record · LEDGER

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features

As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2411.11232.

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

pith.paper-citation-record.v1
2411.11232 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T18:50:08.405900Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T18:50:08.261278Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-12T18:50:08.499324Z

Reference resolution

41 of 41 outbound references displayed

verified exact3
verified fuzzy28
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a10d66e1-013c-4a02-a300-2a91e0e2666b · outbound

This paper cites Common ob- jective evaluation metrics, such as mel-cepstral distance (MCD).

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Common ob- jective evaluation metrics, such as mel-cepstral distance (MCD)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.906628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 310222d8-cc72-43e2-8675-17cf92c5aab0 · outbound

This paper cites As a result, some ob- jective measures or models related to human perception have been proposed [3, 4, 5, 6].

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features As a result, some ob- jective measures or models related to human perception have been proposed [3, 4, 5, 6]

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.893734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e87ed4fb-8977-4686-88e2-04c264b79dd2 · outbound

This paper cites Dataset In this paper, the experiments followed the same settings as the V oiceMOS Challenge 2022 [15].

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Dataset In this paper, the experiments followed the same settings as the V oiceMOS Challenge 2022 [15]

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.857226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 780f391c-0607-4a61-aa33-3478aefec9fb · outbound

This paper cites mean-listener.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features mean-listener

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.881238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ee4f1d43-f25c-4638-bcb1-238c065bba6e · outbound

This paper cites When the rater ID is not the mean-listener, the label representing the sample is the score given by the individual rater (an integer i from 1 to 5).

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features When the rater ID is not the mean-listener, the label representing the sample is the score given by the individual rater (an integer i from 1 to 5)

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.869423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1f5c6476-c622-4219-8e09-7e6423a05b1d · outbound

This paper cites NISQA: A deep CNN-self-attention model for multidimensional speech quality prediction with crowdsourced datasets,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features NISQA: A deep CNN-self-attention model for multidimensional speech quality prediction with crowdsourced datasets,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.762518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 67bc5e51-1fd6-407d-bb72-5fb44d2d6e40 · outbound

This paper cites Comparision with baseline methods We first compare the proposed SAMOS with the baselines.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Comparision with baseline methods We first compare the proposed SAMOS with the baselines

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.846329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 41c32c20-0186-47f1-a6b0-8cb3bec56c93 · outbound

This paper cites We can see that removing the semantic module resulted in the degradation of all the metrics on both datasets, indicating the importance of semantic repre- sentations from SSL model.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features We can see that removing the semantic module resulted in the degradation of all the metrics on both datasets, indicating the importance of semantic repre- sentations from SSL model

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.834338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cdec2479-b405-4bf8-85b1-1d9413048786 · outbound

This paper cites To improve prediction accuracy, SAMOS employs parallel regression and classification heads, and finally outputs the final MOS score through an aggregation layer.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features To improve prediction accuracy, SAMOS employs parallel regression and classification heads, and finally outputs the final MOS score through an aggregation layer

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.821712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a4a7314c-03f6-4e6b-9fbc-0c1eacc56cf3 · outbound

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

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Mel-cepstral distance measure for objective speech quality assessment,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.808890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9029bd3b-988a-4b5d-a2ce-96aa0b219744 · outbound

This paper cites SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-12T18:50:08.503803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 30193a09-e986-462f-9cfc-2ca600386acb · outbound

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

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features SDR– half-baked or well done?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.292704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e07f6f7b-3792-4d31-b07a-1e0954f8979d · outbound

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

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Per- ceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.296480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e44b9181-7668-4052-8766-de5ac55a6734 · outbound

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

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features A short- time objective intelligibility measure for time-frequency weighted noisy speech,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.300376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f594f578-5842-4e96-9dde-2ef897188c1c · outbound

This paper cites ViSQOL: An objective speech quality model,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features ViSQOL: An objective speech quality model,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.774239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e699b29c-92a3-4aad-8d43-3aa357453f6f · outbound

This paper cites AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.312306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b82dcd7-8716-4fbe-8279-c3b28f26b027 · outbound

This paper cites Quality-Net: An end-to-end non-intrusive speech quality assessment model based on blstm,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Quality-Net: An end-to-end non-intrusive speech quality assessment model based on blstm,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.751072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3e78365f-4946-4647-898c-9c39a313e118 · outbound

This paper cites MOSNet: Deep learning-based objec- tive assessment for voice conversion,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features MOSNet: Deep learning-based objec- tive assessment for voice conversion,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.320018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d77dae0-f23a-4757-844d-9fa4cf8e0cbe · outbound

This paper cites MBNet: MOS prediction for synthesized speech with mean-bias network,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features MBNet: MOS prediction for synthesized speech with mean-bias network,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.323526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 794cebee-6b36-4bbb-b50d-89a86f18a8e7 · outbound

This paper cites LDNet: Unified listener dependent modeling in mos prediction for syn- thetic speech,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features LDNet: Unified listener dependent modeling in mos prediction for syn- thetic speech,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.724766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 52e2e90f-d821-48e3-befb-f3f91db3124b · outbound

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

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Generaliza- tion ability of mos prediction networks,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.712368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fb553b37-1660-4ac6-83a8-6a2253627619 · outbound

This paper cites Deep learning-based non-intrusive multi- objective speech assessment model with cross-domain features,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Deep learning-based non-intrusive multi- objective speech assessment model with cross-domain features,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.700005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 60af0c23-252a-4d64-97a0-0496ea529157 · outbound

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

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.337864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54fe6ef4-8be8-4958-8218-b5dc94710d9f · outbound

This paper cites The V oiceMOS Challenge 2022,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features The V oiceMOS Challenge 2022,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.679439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c22bcfd-ac74-4282-8180-efc23733ff3e · outbound

This paper cites A transfer and multi-task learning based approach for MOS predic- tion,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features A transfer and multi-task learning based approach for MOS predic- tion,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.667934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 25448d39-b0e7-4b40-8abc-220ca5382bb6 · outbound

This paper cites DDOS: A MOS predic- tion framework utilizing domain adaptive pre-training and distri- bution of opinion scores,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features DDOS: A MOS predic- tion framework utilizing domain adaptive pre-training and distri- bution of opinion scores,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.656349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b4ec5239-740e-4ec7-912c-06563030db64 · outbound

This paper cites UTMOS: UTokyo-SaruLab system for V oice- MOS Challenge 2022,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features UTMOS: UTokyo-SaruLab system for V oice- MOS Challenge 2022,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.643694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c7776e9b-87ab-4c7b-9e29-10bdc810d981 · outbound

This paper cites Fusion of self-supervised learned models for MOS pre- diction,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Fusion of self-supervised learned models for MOS pre- diction,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.631520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dded1169-beef-48c3-a257-46a1ba2d1be0 · outbound

This paper cites Ensem- ble of deep neural network models for MOS prediction,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Ensem- ble of deep neural network models for MOS prediction,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.618523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 447a59fb-38f9-4672-a89c-98c72831c85d · outbound

This paper cites RAMP: Retrieval- augmented MOS prediction via confidence-based dynamic weighting,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features RAMP: Retrieval- augmented MOS prediction via confidence-based dynamic weighting,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.606030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 91352e5e-3eba-47d5-ab95-306699f19a0c · outbound

This paper cites Investigating content-aware neural text-to-speech MOS prediction using prosodic and linguistic fea- tures,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Investigating content-aware neural text-to-speech MOS prediction using prosodic and linguistic fea- tures,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.593262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1fee44e5-7b9f-45fb-8672-4163a1ba579f · outbound

This paper cites Wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.580675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fffca9b7-87f0-4c05-9ff7-43ce8e77bfb5 · outbound

This paper cites BiVocoder: A Bidirectional Neural Vocoder Integrating Feature Extraction and Waveform Generation.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features BiVocoder: A Bidirectional Neural Vocoder Integrating Feature Extraction and Waveform Generation

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-12T18:50:08.475207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1027c81d-02da-479f-ac32-dcac8a1dbf17 · outbound

This paper cites SQAT-LD: Speech quality assessment transformer utilizing listener depen- dent modeling for zero-shot out-of-domain MOS prediction,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features SQAT-LD: Speech quality assessment transformer utilizing listener depen- dent modeling for zero-shot out-of-domain MOS prediction,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.569287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 151e9e29-7922-43e7-982b-329479541b82 · outbound

This paper cites How do Voices from Past Speech Synthesis Challenges Compare Today?.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features How do Voices from Past Speech Synthesis Challenges Compare Today?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.381069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02825d8f-0937-4a6c-8255-0eaafae92b5f · outbound

This paper cites The Blizzard Challenge 2019,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features The Blizzard Challenge 2019,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.385075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d4e407a-af34-485f-aa7f-04e59493193e · outbound

This paper cites Conformer: Convolution- augmented transformer for speech recognition,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Conformer: Convolution- augmented transformer for speech recognition,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T18:50:08.389039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd6d85c-a83c-4c24-98d7-879b107e970d · outbound

This paper cites ConvNeXt V2: Co-designing and scaling convnets with masked autoencoders,.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features ConvNeXt V2: Co-designing and scaling convnets with masked autoencoders,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.543400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 632c41a8-ad18-440c-8953-02c144402482 · outbound

This paper cites Improving Self-Supervised Learning-based MOS Prediction Networks.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features Improving Self-Supervised Learning-based MOS Prediction Networks

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-12T18:50:08.445952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 567d4e74-2d84-44c6-a656-ca38ed976c65 · outbound

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

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features ESP- Net: End-to-end speech processing toolkit,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.531013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b41c0c1c-fce8-4f73-bbbc-cc8666f5f234 · outbound

This paper cites CSTR VCTK cor- pus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92),.

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features CSTR VCTK cor- pus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92),

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:50:08.518311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 9029bd3b-988a-4b5d-a2ce-96aa0b219744 · inbound