Paper Citation Record · LEDGER

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models

As of 22 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 1 inbound Pith citation observation for arXiv:2605.27383.

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

pith.paper-citation-record.v1
2605.27383 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-12T23:22:40.218077Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T22:33:49.043236Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T22:33:49.485867Z

Reference resolution

34 of 34 outbound references displayed

verified exact0
verified fuzzy0
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4fa26187-00ca-4407-805d-c4a6d3e980c3 · outbound

This paper cites SeamlessM4T: Massively Multilingual & Multimodal Machine Translation.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffa327fc-97cd-48bc-8014-dbf8c4b1138f · outbound

This paper cites Tts- transducer: End-to-end speech synthesis with neural transducer.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Tts- transducer: End-to-end speech synthesis with neural transducer

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b7560a5-a2a8-40c9-8c07-0ba9161e44f6 · outbound

This paper cites Scaling low- resource mt via synthetic data generation with llms.arXiv preprint arXiv:2505.14423,.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Scaling low- resource mt via synthetic data generation with llms.arXiv preprint arXiv:2505.14423,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b04e41-d6ae-4753-939f-41e7e5a0bb9e · outbound

This paper cites and Yu, K.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models and Yu, K

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2cb8323-c747-4ea7-a6ca-b0c5cb7e6824 · outbound

This paper cites CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 587866f2-c686-4c2b-8194-ca847afeaf2a · outbound

This paper cites an unresolved cited work.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 674ddf21-7e01-4212-9653-48ef2ac92fd5 · outbound

This paper cites Surveying the technology support of languages.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Surveying the technology support of languages

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f63ffd4-b4db-46af-bcd5-efd1c1592850 · outbound

This paper cites UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d780fb8-2c7b-480a-96fb-68f09212fef2 · outbound

This paper cites Low-resource expressive text-to- speech using data augmentation.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Low-resource expressive text-to- speech using data augmentation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5007c5d8-f4a9-4ca6-8f73-c5946bbcc6c2 · outbound

This paper cites J., Cao, Y ., Chiu, C.-C., Ari, N., Laurenzo, S., and Wu, Y.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models J., Cao, Y ., Chiu, C.-C., Ari, N., Laurenzo, S., and Wu, Y

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e47ccf1a-a9b7-4784-a477-cc112ae8cae5 · outbound

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

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e46c3244-87d6-4e67-8202-da10ad8b1a64 · outbound

This paper cites Self-training for end- to-end speech recognition.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Self-training for end- to-end speech recognition

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42b528ab-bb88-4f92-a365-72f13a760b47 · outbound

This paper cites Parameter-efficient fine-tuning for low-resource text-to-speech via cross- lingual continual learning.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Parameter-efficient fine-tuning for low-resource text-to-speech via cross- lingual continual learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8e9aa74-563f-4cb0-be4e-7b8df58f7d9e · outbound

This paper cites Disco-speech: Controllable zero-shot speech generation with a disentangled speech codec.arXiv preprint arXiv:2512.13251,.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Disco-speech: Controllable zero-shot speech generation with a disentangled speech codec.arXiv preprint arXiv:2512.13251,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bf0c2af-694d-47ee-a2ec-df039d64ed13 · outbound

This paper cites Lao-english code-switched speech synthesis via neural codec language modeling.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Lao-english code-switched speech synthesis via neural codec language modeling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5e865ca-1348-4678-84c3-c0977397f6ec · outbound

This paper cites Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32712e11-475e-4bcc-a39a-aa8a6b5bd5aa · outbound

This paper cites Overcoming Data Scarcity in Generative Language Modelling for Low-Resource Languages: A Systematic Review.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Overcoming Data Scarcity in Generative Language Modelling for Low-Resource Languages: A Systematic Review

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f677a92d-7855-4884-8152-9077a63cb311 · outbound

This paper cites an unresolved cited work.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 840f16de-833b-4a62-802f-0b80aaaab01b · outbound

This paper cites Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8f369c3-483a-4ad8-b7d3-916453a1a098 · outbound

This paper cites Is synthetic data truly effective for training speech language models? InProc.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Is synthetic data truly effective for training speech language models? InProc

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a70ccd9-9a71-43f5-a190-b1e16e566dd0 · outbound

This paper cites VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9bd1dc6-d26d-46d9-868b-cfdd8533689f · outbound

This paper cites PyThaiNLP: Thai Natural Language Processing in Python.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models PyThaiNLP: Thai Natural Language Processing in Python

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b612da92-67c7-438d-ab6d-48b0f42d664a · outbound

This paper cites Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a50f25fd-bf8f-4ef4-94dc-22d87ae9cb24 · outbound

This paper cites M., Rath, S.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models M., Rath, S

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 079264d7-a20e-480f-a1bc-fc98b826910f · outbound

This paper cites Encoding of lexical tone in self-supervised models of spoken language.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Encoding of lexical tone in self-supervised models of spoken language

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8effd83b-ce1b-48ea-893c-66bd54962587 · outbound

This paper cites V ., Montalan, J.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models V ., Montalan, J

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21d7e943-815b-4136-bfc0-c3f4d4ba9034 · outbound

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

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a8cd09b-e550-44bf-ae45-8a3cc484b2f0 · outbound

This paper cites Theoretical Proof that Auto-regressive Language Models Collapse when Real-world Data is a Finite Set.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Theoretical Proof that Auto-regressive Language Models Collapse when Real-world Data is a Finite Set

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ba1b052-2b71-40eb-9662-1d20a65d3f9c · outbound

This paper cites Speechalign: Aligning speech generation to human preferences.Advances in Neural Information Processing Systems, 37:50343–50360, 2024a.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Speechalign: Aligning speech generation to human preferences.Advances in Neural Information Processing Systems, 37:50343–50360, 2024a

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b40e008-94be-42c8-892c-44693658acbd · outbound

This paper cites and Maleki, F.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models and Maleki, F

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36e13d81-5ccf-4e06-ba95-38fb2313201e · outbound

This paper cites H., Yip, J.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models H., Yip, J

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83ee14a3-95d2-4d98-9e1f-a50521d9375b · outbound

This paper cites an unresolved cited work.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95021f20-9325-447d-ae76-7452ed61dee5 · outbound

This paper cites Table 11.General training hyperparameters across different stages.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Table 11.General training hyperparameters across different stages

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb7327e1-81f1-4f21-842e-4ec58a831baf · outbound

This paper cites Similarly, for Lao, we address its scriptio continua nature by employing the laonlp4 library for linguistic normalization and word segmentation.

Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models Similarly, for Lao, we address its scriptio continua nature by employing the laonlp4 library for linguistic normalization and word segmentation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-12T23:22:40.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation aa1ea841-3d5a-4b35-9797-dc2bbfb5b45f · inbound

CLASVS: Continuous-Latent Autoregression for Melody-Preserving Lyric Editing in Singing Voice Synthesis cites this paper.

CLASVS: Continuous-Latent Autoregression for Melody-Preserving Lyric Editing in Singing Voice Synthesis Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models

Reference 64

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T22:33:49.597361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.