Paper Citation Record · LEDGER

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners

As of 21 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 4 inbound Pith citation observations for arXiv:2412.04917.

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

pith.paper-citation-record.v1
2412.04917 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T21:12:24.123186Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:03:30.685319Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T20:45:08.132130Z

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 57e20474-ba2e-4d9a-90ac-ef77d669ecd1 · outbound

This paper cites EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:23.961929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b603eacb-3b43-4ded-94de-e74e081eb72b · outbound

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

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:23.979142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8127f057-5242-4aba-a1d2-86ff74d7fb31 · outbound

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

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Moshi: a speech-text foundation model for real-time dialogue

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:23.984579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3021b48b-e7f1-4a94-9036-9dd1c853f500 · outbound

This paper cites E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:23.988934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c56b5a3-535f-4f59-9386-a4c401157592 · outbound

This paper cites Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:23.993685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5267b4e2-7a21-48c7-9c16-7b84feba1748 · outbound

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

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:23.997188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 946cfcaf-f1c7-4e7f-af8e-a168e8f7037a · outbound

This paper cites VITA: Towards Open-Source Interactive Omni Multimodal LLM.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners VITA: Towards Open-Source Interactive Omni Multimodal LLM

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.001335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e74ffe0d-4a08-45b2-8b09-ca0d96878287 · outbound

This paper cites VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.005405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b50dc08f-184c-43ab-8d88-a206a844f672 · outbound

This paper cites GPT-4o System Card.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners GPT-4o System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.009654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a03dbb64-8ad8-47ff-8b52-f7946be435e7 · outbound

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

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners WavChat: A Survey of Spoken Dialogue Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.013748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7829fab8-35e1-49b8-b2aa-881cca0d32f5 · outbound

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

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.017408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 979a1fc0-da93-48da-afcc-623cc445ad85 · outbound

This paper cites Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.020995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1f51dc1-1cfa-4c52-870c-2446676844fe · outbound

This paper cites Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.032430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1aff6de-b716-4a8b-b614-80ac8f879a81 · outbound

This paper cites MoBoAligner: a Neural Alignment Model for Non-autoregressive TTS with Monotonic Boundary Search.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners MoBoAligner: a Neural Alignment Model for Non-autoregressive TTS with Monotonic Boundary Search

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.036707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7867242-133a-4905-b1b3-63cb5db9de4e · outbound

This paper cites Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.045362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74d342f8-f9e7-43bc-902d-c2e766602add · outbound

This paper cites DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.049483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3caa5dde-4d75-4246-a896-2f262d2f30f0 · outbound

This paper cites Autoregressive Speech Synthesis without Vector Quantization.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Autoregressive Speech Synthesis without Vector Quantization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.053891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d201cb1d-f8ce-4341-9bf9-a7d36e2a74ea · outbound

This paper cites Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.057607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69168993-6dbb-403d-8c7b-dc73dccc4d96 · outbound

This paper cites Mo\^usai: Text-to-Music Generation with Long-Context Latent Diffusion.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Mo\^usai: Text-to-Music Generation with Long-Context Latent Diffusion

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.061438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f07153a0-ea82-4e04-9ff0-c196a1530593 · outbound

This paper cites Bespoke Solvers for Generative Flow Models.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Bespoke Solvers for Generative Flow Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.065947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a15dfbd5-666e-4a52-a256-a949d4b516ca · outbound

This paper cites NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.072590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d06573db-0160-4c6a-98c2-0bab659855e6 · outbound

This paper cites Improving and generalizing flow-based generative models with minibatch optimal transport.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Improving and generalizing flow-based generative models with minibatch optimal transport

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.077413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e440572-9239-4a3b-b3b3-366bc5f11d2b · outbound

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

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.083513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72795f17-3505-4ec4-b58a-f73569adbbd4 · outbound

This paper cites Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.088388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44456515-7b16-4442-ad1d-e431217f467f · outbound

This paper cites Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.099012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ced33df-bf4e-4c94-92db-cee7a6a5191c · outbound

This paper cites Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.102735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d97c09-3a17-4b48-a6a0-28313112caba · outbound

This paper cites Qwen2 Technical Report.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Qwen2 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.106734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ad4dfac-b493-4042-948b-b91b33bbdc11 · outbound

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

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.111466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24fb27b1-dca9-4f65-8ef2-34f80ba7ec56 · outbound

This paper cites Boosting Diffusion Model for Spectrogram Up-sampling in Text-to-speech: An Empirical Study.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Boosting Diffusion Model for Spectrogram Up-sampling in Text-to-speech: An Empirical Study

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.117270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57606263-1fd7-4937-bb54-c3495b0086f1 · outbound

This paper cites OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.123186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21dc1169-1c22-44d0-b05a-abea892a15de · outbound

This paper cites PromptTTS 2: Describing and Generating Voices with Text Prompt.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners PromptTTS 2: Describing and Generating Voices with Text Prompt

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.028223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11b02b08-2e59-4e24-bd95-2b7283f4dcf8 · outbound

This paper cites VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:23.969675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bab0be1d-6279-4510-8f4c-9b040b3495a8 · outbound

This paper cites MarDini: Masked Autoregressive Diffusion for Video Generation at Scale.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.041379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ec7112d-9787-477e-8730-7f7185ce16b4 · outbound

This paper cites Understanding DDPM Latent Codes Through Optimal Transport.

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Understanding DDPM Latent Codes Through Optimal Transport

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:24.024563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cce992c9-8d14-4e91-b54e-8938282f5b6a · outbound

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

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners Recent Advances in Speech Language Models: A Survey

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T21:12:23.974565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4f425dfd-1a03-4aa3-8f97-c1519f08c345 · inbound

On The Landscape of Spoken Language Models: A Comprehensive Survey cites this paper.

On The Landscape of Spoken Language Models: A Comprehensive Survey Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-22T20:45:08.135585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a83a50da-cb83-4dd3-a6cc-78708deb9984 · inbound

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling cites this paper.

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:30.685319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57703305-fd3c-4bd1-8837-dd90a5334c5e · inbound

Next Tokens Denoising for Speech Synthesis cites this paper.

Next Tokens Denoising for Speech Synthesis Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T11:22:27.693175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebd68a4c-3872-4398-9419-19b1b8df4f0f · inbound

Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation cites this paper.

Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:46:42.075264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.