Paper Citation Record · LEDGER

Speechless: Speech Instruction Training Without Speech for Low Resource Languages

As of 19 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 2 inbound Pith citation observations for arXiv:2505.17417.

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

pith.paper-citation-record.v1
2505.17417 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:51:19.432830Z

measured 47 of 47 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:51:15.305445Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T11:58:44.561636Z

Reference resolution

45 of 45 outbound references displayed

verified exact1
verified fuzzy22
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 11d56fbd-b22c-4a54-b72e-5a8c8ecf1c8e · outbound

This paper cites Speechless: Speech Instruction Training Without Speech for Low Resource Languages.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Speechless: Speech Instruction Training Without Speech for Low Resource Languages

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:15.305445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 900b0269-1f87-4455-87c5-55626e2fffb6 · outbound

This paper cites First, we train a residual vector quantizer (RVQ) to en- code speech into discrete semantic tokens that align with Whis- per’s encoder representations.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages First, we train a residual vector quantizer (RVQ) to en- code speech into discrete semantic tokens that align with Whis- per’s encoder representations

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:23.699872Z

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 51b3eb90-d3d4-4fbb-ae2d-e431f0cab151 · outbound

This paper cites Datasets For Stage 1, we utilized two automatic speech recognition (ASR) datasets: viV oice (Vietnamese) and LibriTTS-R[22] (English).

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Datasets For Stage 1, we utilized two automatic speech recognition (ASR) datasets: viV oice (Vietnamese) and LibriTTS-R[22] (English)

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:23.550068Z

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 1702fe69-67d2-46e0-8a75-5b85d782328b · outbound

This paper cites ASR and Speechless Comparisons To evaluate the performance of the Speechless model alone, we make use of ASR test sets.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages ASR and Speechless Comparisons To evaluate the performance of the Speechless model alone, we make use of ASR test sets

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:23.379474Z

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 dacab840-508a-49a8-a599-669601336807 · outbound

This paper cites By lever- aging a quantized Whisper encoder, Speechless generates se- mantic speech tokens, effectively addressing challenges in low- resource languages.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages By lever- aging a quantized Whisper encoder, Speechless generates se- mantic speech tokens, effectively addressing challenges in low- resource languages

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:22.925666Z

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 2c1e8d43-313a-4cff-8756-24ca52554909 · outbound

This paper cites This is also clear when see that with added noise (VBD noisy), the Whisper encoder starts to generate tokens that show poorer WER in comparison.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages This is also clear when see that with added noise (VBD noisy), the Whisper encoder starts to generate tokens that show poorer WER in comparison

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:23.064274Z

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 eaf8e15b-238e-44e0-a5c9-eadd4d06e17a · outbound

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

Speechless: Speech Instruction Training Without Speech for Low Resource Languages SALMONN: Towards generic hearing abilities for large language models,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:16.343843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2345f4fd-92d2-4833-8314-f1a8d9e0a7c2 · outbound

This paper cites Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:51:19.788559Z

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 24297cbb-faa3-4c2a-a25a-9cf84fe8d9b4 · outbound

This paper cites WavChat: A Survey of Spoken Dialogue Models.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages WavChat: A Survey of Spoken Dialogue Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:15.917688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b62c3c8-bdc0-46e4-bea0-2e93f641eeb5 · outbound

This paper cites Recent Advances in Speech Language Models: A Survey.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Recent Advances in Speech Language Models: A Survey

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:15.984529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d13692c-21c8-42a9-bc12-cfe3f818b5c3 · outbound

This paper cites LLaMA-Omni: Seamless Speech Interaction with Large Language Models.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:16.069890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a563852e-78bc-42c8-8b2d-111ec6d27c1c · outbound

This paper cites Instruction data generation and unsupervised adap- tation for speech language models,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Instruction data generation and unsupervised adap- tation for speech language models,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:22.786323Z

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 4f491142-bab0-4c43-95c5-2aa0aaed3b49 · outbound

This paper cites Tango 2: Aligning diffusion-based text-to-audio generations through direct preference optimization,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Tango 2: Aligning diffusion-based text-to-audio generations through direct preference optimization,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:22.581169Z

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 caa0ee6b-f3a4-45e4-98b1-de8f6327de53 · outbound

This paper cites Distilling an End-to-End Voice Assistant Without Instruction Training Data.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Distilling an End-to-End Voice Assistant Without Instruction Training Data

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:17.014767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 607d190d-46da-4014-af69-c27e2ebce769 · outbound

This paper cites COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:16.436586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c1edec-a87e-4e7f-a463-d1e943a859ce · outbound

This paper cites LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:16.525195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c331902-1aca-4b33-9d3c-e062d51eaabd · outbound

This paper cites An efficient and high fidelity vietnamese streaming end-to-end speech synthesis,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages An efficient and high fidelity vietnamese streaming end-to-end speech synthesis,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:22.428889Z

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 53ecc50b-f8f7-484c-ba70-7a61eb396779 · outbound

This paper cites Low-resource multilingual and zero-shot multispeaker TTS,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Low-resource multilingual and zero-shot multispeaker TTS,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:22.262103Z

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 f546cba8-f8c1-4c1a-b2b0-7d4610d039f5 · outbound

This paper cites Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:16.797400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c790d769-9dcd-4498-b404-bb479547d23d · outbound

This paper cites Unsupervised cross-modal alignment of speech and text embedding spaces,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Unsupervised cross-modal alignment of speech and text embedding spaces,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:22.078323Z

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 a31e3807-8636-42a3-b356-ff6020e822fb · outbound

This paper cites Alpaca: A strong, replicable instruction-following model,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Alpaca: A strong, replicable instruction-following model,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:21.053822Z

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 7c2dd311-c4b4-4b2c-8cdf-0d8e87ddef20 · outbound

This paper cites An analysis of semantically-aligned speech-text embeddings,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages An analysis of semantically-aligned speech-text embeddings,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:21.907697Z

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 c1591c75-ab13-4a3b-b6fc-2972fd1bf797 · outbound

This paper cites Astra: Aligning speech and text representa- tions for asr without sampling,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Astra: Aligning speech and text representa- tions for asr without sampling,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:21.694139Z

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 abf51dc9-7f4b-4e10-8e0f-db41f1142271 · outbound

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

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Robust speech recognition via large-scale weak supervision,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:17.321338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9347ce0c-ce5b-4d54-aaac-79a2f5c4f7cb · outbound

This paper cites Speecht5: Unified-modal encoder-decoder pre-training for spoken language processing,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Speecht5: Unified-modal encoder-decoder pre-training for spoken language processing,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:21.495300Z

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 d1757e7c-322e-43a2-914b-f4543644f43c · outbound

This paper cites Sailor 2 dataset,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Sailor 2 dataset,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:21.318498Z

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 d3fad88d-c6b6-4f61-954b-221df6fbe0e2 · outbound

This paper cites Vtsnlp instruct general dataset,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Vtsnlp instruct general dataset,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:21.209910Z

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 a89f7a66-63ba-40b4-9f0a-949c3ae289c1 · outbound

This paper cites VoiceBench: Benchmarking LLM-Based Voice Assistants.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages VoiceBench: Benchmarking LLM-Based Voice Assistants

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:18.448509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cfdabc0-e0dc-4eb3-8c5c-aa231bd844b1 · outbound

This paper cites LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:17.873469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acede9d8-bcef-4531-b951-8ca6819b8fb1 · outbound

This paper cites vivoice: Enabling vietnamese multi-speaker speech synthesis,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages vivoice: Enabling vietnamese multi-speaker speech synthesis,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:20.884120Z

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 389b06a8-4a30-4540-af90-b95b5f135e3a · outbound

This paper cites an unresolved cited work.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:51:23.175121Z

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 0cc6ac39-bfac-41f9-91ac-54f907faddbf · outbound

This paper cites Libritts-p: A corpus with speaking style and speaker identity prompts for text-to-speech and style captioning,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Libritts-p: A corpus with speaking style and speaker identity prompts for text-to-speech and style captioning,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:20.728142Z

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 50bd9f11-e106-401b-9dec-ce817a39b5dd · outbound

This paper cites MLS: A Large-Scale Multilingual Dataset for Speech Research.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages MLS: A Large-Scale Multilingual Dataset for Speech Research

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:18.155649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e5160ce-8d1b-4afb-82b0-c0bd78df15ff · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:18.265223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b6be35c-d36b-4d4c-a7a6-61f9e11e547c · outbound

This paper cites Ray: A Distributed Framework for Emerging AI Applications.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Ray: A Distributed Framework for Emerging AI Applications

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:18.378750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee710545-1be9-43f2-8cd7-d8b722303ef4 · outbound

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

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Lib- rispeech: an asr corpus based on public domain audio books,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:18.542975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf34e67-8708-42fb-bb91-58d90c51c0d2 · outbound

This paper cites Speech enhancement for a noise-robust text-to-speech synthe- sis system using deep recurrent neural networks,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Speech enhancement for a noise-robust text-to-speech synthe- sis system using deep recurrent neural networks,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:20.561260Z

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 18225890-ce84-465f-95d6-18d6f01ce73a · outbound

This paper cites The diverse environments multi-channel acoustic noise database (demand): A database of multichannel environmental noise recordings,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages The diverse environments multi-channel acoustic noise database (demand): A database of multichannel environmental noise recordings,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:18.760225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be6b2239-8b98-4800-b2aa-c7d0d53ef519 · outbound

This paper cites Com- mon voice: A massively-multilingual speech corpus,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Com- mon voice: A massively-multilingual speech corpus,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:20.395648Z

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 520c3d00-e442-4328-a5f0-0dd46f1321b7 · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:18.912898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccb497d4-3c47-4829-a70a-ba964cd1bfd5 · outbound

This paper cites SD-QA: Spoken dialectal question answering for the real world,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages SD-QA: Spoken dialectal question answering for the real world,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:20.223654Z

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 41d8c8c1-34f7-4e8a-ba81-3a2af63b33d9 · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:19.139471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ccdc6d9-0ca4-42ca-8e96-0d8ac76004b9 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:19.219916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb07a2e8-90bc-4f87-a40a-8a4236a11a76 · outbound

This paper cites Moshi: a speech-text foundation model for real-time dialogue.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages Moshi: a speech-text foundation model for real-time dialogue

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:19.350579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21615463-daac-4d2e-8f38-928b36f96ce0 · outbound

This paper cites BLSP: Bootstrapping language-speech pre-training via behavior alignment of continuation writing,.

Speechless: Speech Instruction Training Without Speech for Low Resource Languages BLSP: Bootstrapping language-speech pre-training via behavior alignment of continuation writing,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:51:20.026378Z

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 11d56fbd-b22c-4a54-b72e-5a8c8ecf1c8e · inbound