Paper Citation Record · LEDGER

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs

As of 21 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 2 inbound Pith citation observations for arXiv:2506.10299.

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

pith.paper-citation-record.v1
2506.10299 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:36:00.786445Z

measured 48 of 48 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:35:57.016869Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T07:11:53.109624Z

Reference resolution

46 of 46 outbound references displayed

verified exact0
verified fuzzy41
unresolved4
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0c67365c-715a-4f4d-a9cb-6e9e61eb62f5 · outbound

This paper cites Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T04:35:57.016869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 201aee1b-781f-40e8-ac1a-d16ca8846b8d · outbound

This paper cites Speech-to-speech translation (S2ST) End-to-end speech-to-speech translation (S2ST) systems have been actively studied, which is jointly optimized as a speech-to- speech task [2–9].

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Speech-to-speech translation (S2ST) End-to-end speech-to-speech translation (S2ST) systems have been actively studied, which is jointly optimized as a speech-to- speech task [2–9]

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.223466Z

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.

Observation 4277612b-a8d2-4dfc-92b8-82741556f477 · outbound

This paper cites Speech-to-speech translation system As shown in Figure 2, we adopt a speech-to-speech translation (S2ST) system fine-tuned from an LLM, as in AudioPaLM [7].

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Speech-to-speech translation system As shown in Figure 2, we adopt a speech-to-speech translation (S2ST) system fine-tuned from an LLM, as in AudioPaLM [7]

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.203017Z

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.

Observation e6072cdc-72ec-4206-af51-5341a59ebcb4 · outbound

This paper cites an unresolved cited work.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:36:03.183586Z

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.

Observation 29a1df17-1875-4cf4-b0f5-c04bf5000bd2 · outbound

This paper cites The CVSS corpus is a widely used corpus for multilingual S2ST, built by speech synthe- sis from the CoV oST2 [36] speech-to-text translation corpus.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs The CVSS corpus is a widely used corpus for multilingual S2ST, built by speech synthe- sis from the CoV oST2 [36] speech-to-text translation corpus

Reference 5

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T04:36:03.168690Z

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.

Observation 5b6d84b8-286b-42c8-8a83-10bcb2e5469e · outbound

This paper cites We use interleaved speech–text units as the input and output of LLM, instead of the speech units, during fine-tuning LLM.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs We use interleaved speech–text units as the input and output of LLM, instead of the speech units, during fine-tuning LLM

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.145119Z

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.

Observation 73674bb9-7054-462b-8acb-996cc960ecfb · outbound

This paper cites The ATR multilingual speech-to-speech translation system,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs The ATR multilingual speech-to-speech translation system,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.126804Z

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.

Observation 6f79be64-ec0e-480b-8638-c10156d67053 · outbound

This paper cites Direct speech-to-speech translation with a sequence- to-sequence model,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Direct speech-to-speech translation with a sequence- to-sequence model,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.106380Z

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.

Observation db1f0174-f87b-443f-b0ef-a8640d38851a · outbound

This paper cites Trans- latotron 2: High-quality direct speech-to-speech translation with voice preservation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Trans- latotron 2: High-quality direct speech-to-speech translation with voice preservation,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.070103Z

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.

Observation ad958d3a-8311-4ff3-bb1a-66ca0925185c · outbound

This paper cites Direct speech- to-speech translation with discrete units,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Direct speech- to-speech translation with discrete units,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.049986Z

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.

Observation 50be0966-0b4c-4b07-8434-4417e400eb88 · outbound

This paper cites UnitY: Two- pass direct speech-to-speech translation with discrete units,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs UnitY: Two- pass direct speech-to-speech translation with discrete units,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.032451Z

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.

Observation 8f2a3717-4052-46c7-855c-62ccf491932c · outbound

This paper cites SeamlessM4T: Massively mul- tilingual&multimodal machine translation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs SeamlessM4T: Massively mul- tilingual&multimodal machine translation,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:03.014533Z

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.

Observation 42335768-8cee-481f-a316-74ac65f2a976 · outbound

This paper cites AudioPaLM: A large language model that can speak and listen,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs AudioPaLM: A large language model that can speak and listen,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.910716Z

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.

Observation 0d9a00c6-1051-476a-bb3a-d9488c89ec48 · outbound

This paper cites PolyV oice: Language models for speech to speech translation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs PolyV oice: Language models for speech to speech translation,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.669830Z

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.

Observation dc4a533c-2a14-457a-a9cf-3f9722ce4c60 · outbound

This paper cites MSLM-S2ST: A multitask speech language model for textless speech-to-speech translation with speaker style preserva- tion,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs MSLM-S2ST: A multitask speech language model for textless speech-to-speech translation with speaker style preserva- tion,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.616522Z

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.

Observation 213bbfb2-9406-4881-ae48-23092541654c · outbound

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

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.598378Z

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.

Observation 8cf1f694-4944-4e25-a4e9-d4ddc3a0b0df · outbound

This paper cites w2v-BERT: Combining contrastive learning and masked language modeling for self-supervised speech pre- training,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs w2v-BERT: Combining contrastive learning and masked language modeling for self-supervised speech pre- training,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.580959Z

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.

Observation bd4740d8-e80e-48d8-87c8-a2829e247d6c · outbound

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

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs SoundStream: An end-to-end neural audio codec,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.558873Z

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.

Observation f33f6157-a8ab-448b-bdf8-c0aa3a4ed88a · outbound

This paper cites High fidelity neural audio compression,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs High fidelity neural audio compression,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:35:58.376350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3079b3e6-108e-46bf-a7cf-1d20af200453 · outbound

This paper cites Language models are few-shot learners,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Language models are few-shot learners,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.521050Z

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.

Observation 9882ea6b-851b-4660-b8c2-53fafa7a4a02 · outbound

This paper cites Prompting large language models with speech recognition abilities,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Prompting large language models with speech recognition abilities,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.498520Z

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.

Observation 75ca9f52-f304-4fc7-b7e6-e728ac618b7c · outbound

This paper cites SLM: Bridge the thin gap between speech and text foun- dation models,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs SLM: Bridge the thin gap between speech and text foun- dation models,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.479961Z

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.

Observation 41737303-affc-4460-86a2-7eb37e006e1e · outbound

This paper cites On decoder-only architecture for speech-to-text and large language model integration,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs On decoder-only architecture for speech-to-text and large language model integration,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.462356Z

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.

Observation 63102fb5-df9e-46ad-b8f1-cfe2e5323c48 · outbound

This paper cites V oxtLM: Unified decoder-only models for consolidating speech recognition, synthesis and speech, text continuation tasks,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs V oxtLM: Unified decoder-only models for consolidating speech recognition, synthesis and speech, text continuation tasks,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.444074Z

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.

Observation a6619f27-2a8f-4112-b20b-547c52b1d9e1 · outbound

This paper cites Qwen-Audio: Advancing universal audio understanding via unified large-scale audio-language models,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Qwen-Audio: Advancing universal audio understanding via unified large-scale audio-language models,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.427769Z

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.

Observation efd7679b-354e-4eed-b0f1-8d48a8138c50 · outbound

This paper cites SpeechGPT: Empowering large language models with intrinsic cross-modal conversational abilities,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs SpeechGPT: Empowering large language models with intrinsic cross-modal conversational abilities,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.409782Z

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.

Observation 7e7c0c7e-ac86-4bc7-afe0-eda957170126 · outbound

This paper cites SALMONN: Towards generic hearing abilities for large language models,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs SALMONN: Towards generic hearing abilities for large language models,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.390320Z

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.

Observation 2d787354-2c2d-4963-a1d9-cd376e6fdb64 · outbound

This paper cites PaLM 2 technical report,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs PaLM 2 technical report,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.373985Z

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.

Observation 219889a7-ed25-4341-b034-a064555d5787 · outbound

This paper cites Bridging the modality gap for speech-to-text translation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Bridging the modality gap for speech-to-text translation,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.354529Z

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.

Observation 39ab0872-e6e9-44f0-8922-88a87624cad7 · outbound

This paper cites Push- ing the limits of zero-shot end-to-end speech translation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Push- ing the limits of zero-shot end-to-end speech translation,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.334713Z

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.

Observation 522090b3-3d5d-42f8-a843-51af0e8f6b53 · outbound

This paper cites SpiRit-LM: In- terleaved spoken and written language model,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs SpiRit-LM: In- terleaved spoken and written language model,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.318937Z

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.

Observation 00aafe0a-508e-4e80-a1e1-9eb84e955021 · outbound

This paper cites The llama 3 herd of models,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs The llama 3 herd of models,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.300516Z

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.

Observation f2d33f73-62c6-4ba6-85e0-f8aa3f2866de · outbound

This paper cites CVSS corpus and massively multilingual speech-to-speech translation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs CVSS corpus and massively multilingual speech-to-speech translation,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.284842Z

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.

Observation 0ecd7193-bc8e-4457-a050-0ce6ad047006 · outbound

This paper cites Speech resynthesis from discrete disentangled self-supervised representations,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Speech resynthesis from discrete disentangled self-supervised representations,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.268446Z

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.

Observation 08d467e9-3a37-48fc-a5fe-0a1611504a52 · outbound

This paper cites HiFi-GAN: Generative adversar- ial networks for efficient and high fidelity speech synthesis,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs HiFi-GAN: Generative adversar- ial networks for efficient and high fidelity speech synthesis,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T04:35:59.801777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d92952c-a5af-4fbd-841a-cc4c449d59cf · outbound

This paper cites On generative spoken language modeling from raw audio,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs On generative spoken language modeling from raw audio,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.238915Z

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.

Observation e970c5ac-a21b-4d8a-9a40-19c348d83ccc · outbound

This paper cites AudioLM: A language modeling approach to audio generation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs AudioLM: A language modeling approach to audio generation,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.222869Z

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.

Observation b251883f-ff82-4bbe-bb97-bb4c961be324 · outbound

This paper cites Neural codec language models are zero-shot text to speech synthesizers,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Neural codec language models are zero-shot text to speech synthesizers,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.207684Z

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.

Observation d2cfee65-97ea-4016-9dc8-b5575ccb51d0 · outbound

This paper cites Speak for- eign languages with your own voice: Cross-lingual neural codec language modeling,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Speak for- eign languages with your own voice: Cross-lingual neural codec language modeling,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.190651Z

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.

Observation 8e895d53-15e0-4fe5-b322-049f26681bcf · outbound

This paper cites Scaling speech-text pre-training with synthetic interleaved data,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Scaling speech-text pre-training with synthetic interleaved data,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.170997Z

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.

Observation 1ab6d6e6-20eb-4abe-a7b2-8c5e65cb6062 · outbound

This paper cites CTC-segmentation of large corpora for german end-to-end speech recognition,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs CTC-segmentation of large corpora for german end-to-end speech recognition,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.151621Z

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.

Observation 4f54195b-4f99-48a7-b2ba-12aed8b44562 · outbound

This paper cites CoV oST 2 and massively multilingual speech translation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs CoV oST 2 and massively multilingual speech translation,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:02.127549Z

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.

Observation 1310da3b-42f6-487b-8c1d-6c1901b54136 · outbound

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

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs ESPnet: End-to-end speech processing toolkit,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:01.944452Z

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.

Observation 6624793d-9b5a-4b8f-ae3e-36b306871312 · outbound

This paper cites Robust speech recognition via large-scale weak su- pervision,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Robust speech recognition via large-scale weak su- pervision,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:01.711048Z

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.

Observation f1a8bf44-a61b-4888-8541-80c4cde1c945 · outbound

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

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs UTMOS: Utokyo-sarulab system for voicemos challenge 2022,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:01.329064Z

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.

Observation d6b071d8-822d-40b2-9a08-1456c7190136 · outbound

This paper cites Investigating decoder-only large language models for speech-to-text translation,.

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs Investigating decoder-only large language models for speech-to-text translation,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:36:01.089859Z

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.

Pith citing papers

Observation 0c67365c-715a-4f4d-a9cb-6e9e61eb62f5 · inbound