Paper Citation Record · LEDGER

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding

As of 8 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 3 inbound Pith citation observations for arXiv:2505.15380.

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

pith.paper-citation-record.v1
2505.15380 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:23:17.839718Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:23:15.143902Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T03:07:35.840013Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy9
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 24a1e843-44d3-47ad-8717-7485443a8ae8 · outbound

This paper cites Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.143902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 872514fb-4d98-49e1-b55c-dc839c255d33 · outbound

This paper cites an unresolved cited work.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:23:20.322728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c9abe58f-1ca2-4bb9-9030-9ceffc84b2af · outbound

This paper cites Implementation Details We use CosyV oice 2 [5] as the target model, which is a highly efficient TTS model consisting of 24 layers of Transformer adapted from Qwen2.5 (0.5B) [28].

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Implementation Details We use CosyV oice 2 [5] as the target model, which is a highly efficient TTS model consisting of 24 layers of Transformer adapted from Qwen2.5 (0.5B) [28]

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:20.207630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 10d1f27b-e487-43a9-a148-445c0eb55121 · outbound

This paper cites train-clean-100.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding train-clean-100

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:20.077043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation db1db276-7d3c-46cd-a6a8-faf31224f583 · outbound

This paper cites an unresolved cited work.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:23:19.959504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 33f18f76-31ce-491f-83c9-11ec38c10b5a · outbound

This paper cites We propose a lightweight draft model constructed by fine- tuning a few parameters from the target model.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding We propose a lightweight draft model constructed by fine- tuning a few parameters from the target model

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:19.855401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3c42f3aa-6462-4a62-bcbd-6ad8ddce9fe4 · outbound

This paper cites an unresolved cited work.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.551203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b69b132-0295-4655-a468-effbb30fa8e2 · outbound

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

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.575777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64fe4a74-6347-4730-9265-6015099d6104 · outbound

This paper cites Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.604779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca8bfa3e-ec9a-44ad-b667-1584f0572553 · outbound

This paper cites Seed-TTS: A Family of High-Quality Versatile Speech Generation Models.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.641196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4e28ec6-9b36-419d-98bc-e27196d76e11 · outbound

This paper cites CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.731823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cb08c7b-a74c-4ae4-a7ba-6089eeb595af · outbound

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

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.777675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8383ff8-ddd2-4fd7-8b0c-546f08809e16 · outbound

This paper cites Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.813372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ba236b4-77cf-483f-80a7-d4709efe4c0d · outbound

This paper cites FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:15.859744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f465032-5e78-48ef-a896-195465f89196 · outbound

This paper cites Speak, read and prompt: High-fidelity text-to-speech with min- imal supervision,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Speak, read and prompt: High-fidelity text-to-speech with min- imal supervision,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:19.709640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3cff66e8-7686-4e37-902f-7bfdff761efa · outbound

This paper cites BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.017706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3468eeba-dae0-47ae-b1a0-87c518360087 · outbound

This paper cites VoiceCraft: Zero-shot speech editing and text-to-speech in the wild,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding VoiceCraft: Zero-shot speech editing and text-to-speech in the wild,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:19.586294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6c5afbac-e9d2-4862-8f5f-cab96a22e33d · outbound

This paper cites UniAudio: An Audio Foundation Model Toward Universal Audio Generation.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding UniAudio: An Audio Foundation Model Toward Universal Audio Generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.151902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96e4fd3-69c0-4ab7-a063-bf77ecc4dab8 · outbound

This paper cites Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.203599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f75ea3-9fc1-4e6a-8739-017b35a216f1 · outbound

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

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Soundstream: An end-to-end neural audio codec,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.281099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ddf565-d73b-4efd-97b4-1068b845d91e · outbound

This paper cites High fidelity neural audio compression,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding High fidelity neural audio compression,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.349834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d701b6bc-99c1-4a21-a74d-12fe62439679 · outbound

This paper cites Attention is all you need,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Attention is all you need,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.414472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 487eff77-b90a-407b-9ddb-4ad995b087d2 · outbound

This paper cites Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.481026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 470d2aea-2acf-4d9f-8e6e-a118df1b37ba · outbound

This paper cites Vits2: Improving quality and efficiency of single-stage text-to-speech with adversarial learning and architecture design,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Vits2: Improving quality and efficiency of single-stage text-to-speech with adversarial learning and architecture design,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.568587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e9d3fe9-a6cf-4a45-9a8f-3ca81cfaf868 · outbound

This paper cites F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.617519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d0cc4b9-8fbd-42a0-85b2-d587cbc04dad · outbound

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

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.693219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197fe7f3-9c56-4e98-896f-ecffdbbe174e · outbound

This paper cites E2 tts: Embarrassingly easy fully non-autoregressive zero-shot tts,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding E2 tts: Embarrassingly easy fully non-autoregressive zero-shot tts,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.781575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5181814-bea1-419c-a700-9e0471be7a48 · outbound

This paper cites V oicebox: Text-guided multilingual universal speech generation at scale,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding V oicebox: Text-guided multilingual universal speech generation at scale,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:16.886672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e62cdb9c-53a5-4ab2-a29a-da9d01cecb95 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:17.015468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f8448db-da43-45bd-8af1-f70057db5367 · outbound

This paper cites Fast inference from transformers via speculative decoding,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Fast inference from transformers via speculative decoding,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:17.116127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d462931-f02b-46b1-8917-3aa7eab461fd · outbound

This paper cites Accelerating codec-based speech synthesis with multi- token prediction and speculative decoding,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Accelerating codec-based speech synthesis with multi- token prediction and speculative decoding,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:19.182314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5d031e44-2e1a-4046-9a31-3445e80e2638 · outbound

This paper cites Fast and high- quality auto-regressive speech synthesis via speculative decod- ing,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Fast and high- quality auto-regressive speech synthesis via speculative decod- ing,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:18.969777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d0629482-ebf6-4d76-95d3-6b775180c0b9 · outbound

This paper cites Parameter-efficient transfer learning for nlp,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Parameter-efficient transfer learning for nlp,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:17.482133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99a912a4-5304-4ad4-999c-7f8e935d24d8 · outbound

This paper cites Efficient adapter transfer of self-supervised speech models for automatic speech recogni- tion,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Efficient adapter transfer of self-supervised speech models for automatic speech recogni- tion,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:18.640010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a8cae2a1-88b7-4f1b-b646-e638af413132 · outbound

This paper cites Qwen2.5 Technical Report.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Qwen2.5 Technical Report

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:17.675437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9406f94a-5627-4515-a080-dbe4ed64e775 · outbound

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

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:17.733722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 341f9f31-33d0-4522-9639-33909a0b7b13 · outbound

This paper cites Unicats: A unified context-aware text- to-speech framework with contextual vq-diffusion and vocoding,.

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Unicats: A unified context-aware text- to-speech framework with contextual vq-diffusion and vocoding,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:18.378283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 24a1e843-44d3-47ad-8717-7485443a8ae8 · inbound