Paper Citation Record · LEDGER

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis

As of 18 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 3 inbound Pith citation observations for arXiv:2508.19098.

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

pith.paper-citation-record.v1
2508.19098 v1

Coverage vector

measured 69 of 69 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:01:52.889397Z

measured 72 of 72 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T21:18:22.911332Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T19:47:19.713205Z

Reference resolution

69 of 69 outbound references displayed

verified exact0
verified fuzzy33
unresolved34
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 958bcb74-b0d2-4b6d-b750-76a12a654377 · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.500071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce96466a-3f3c-498a-b4c6-699d1b217b7a · outbound

This paper cites SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing, May 2022.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing, May 2022

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.886110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ee274c21-6231-4378-b2c4-d7d16bd2c174 · outbound

This paper cites Rethinking lossy compression: The rate-distortion-perception tradeoff.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Rethinking lossy compression: The rate-distortion-perception tradeoff

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.863775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9568581b-d05c-427d-bcda-b47528a0d1a1 · outbound

This paper cites Audiolm: a language modeling approach to audio generation.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Audiolm: a language modeling approach to audio generation

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.843458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 90aa4c5a-2bd8-46eb-8908-16a6a917b2c7 · outbound

This paper cites Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models, April 2025.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models, April 2025

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.823149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 19a81d71-38a8-4e58-8a48-58b6b09987ee · outbound

This paper cites Wavlm: Large-scale self-supervised pre- training for full stack speech processing.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Wavlm: Large-scale self-supervised pre- training for full stack speech processing

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.802618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 53ce4747-da48-485a-b0f5-1a133c8439b7 · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.534536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 745110e8-993f-4339-8a4b-51e03547cfbb · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.541441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57fdbef0-4a32-4f96-8ff3-dfb48569668b · outbound

This paper cites High Fidelity Neural Audio Compression, October 2022.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis High Fidelity Neural Audio Compression, October 2022

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.782035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 14557648-9203-4b77-94aa-6dde161d30c6 · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.553461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5adda8a6-57e9-4477-82d1-a3a07bf6a619 · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.558566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b85f4d6d-3bfa-4a61-a653-8b689b6c30b2 · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.564223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67b6aa19-bfba-4ecf-9d2b-7792931a7eb6 · outbound

This paper cites Taming Transformers for High-Resolution Image Synthesis.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Taming Transformers for High-Resolution Image Synthesis

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.766551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ae6eafc0-1ccf-4c0c-b577-b0739db50a6e · outbound

This paper cites Scaling Rectified Flow Transformers for High-Resolution Image Synthesis.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.575279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb7fc861-e8fa-4c79-a6fd-53f57b73239f · outbound

This paper cites Fast Timing-Conditioned Latent Audio Diffusion.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Fast Timing-Conditioned Latent Audio Diffusion

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.581625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44e1c1ad-4a1d-4d7f-8636-d23a5b4e962c · outbound

This paper cites E3 TTS: Easy End-to-End Diffusion-Based Text To Speech.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis E3 TTS: Easy End-to-End Diffusion-Based Text To Speech

Reference 16

Resolution: malformed identifier; no resolver link, observed 2026-08-05T16:01:52.587056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0c4c34e-f724-4f59-97a1-ce13369336bd · outbound

This paper cites Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.749600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 04207df1-0bfa-4b6d-9458-20207a08e057 · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.598217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb6b0037-dbd3-4354-9c35-d3fcd46dd6fd · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.604143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e65ad875-0b89-4e36-a11c-da80d888d4e1 · outbound

This paper cites Classifier-Free Diffusion Guidance.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Classifier-Free Diffusion Guidance

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.611342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aef40a6e-b847-4b40-8e4c-da3022bfe9f7 · outbound

This paper cites Straightening out the straight- through estimator: Overcoming optimization challenges in vector quantized networks.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Straightening out the straight- through estimator: Overcoming optimization challenges in vector quantized networks

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.730366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7833edb7-8922-4c02-aa15-c5cf3f7ac512 · outbound

This paper cites Ditar: Diffusion transformer au- toregressive modeling for speech generation, 2025.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Ditar: Diffusion transformer au- toregressive modeling for speech generation, 2025

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.711234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2e5b129c-c9c6-4923-bcd8-3039bb2510ee · outbound

This paper cites Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis, April 2024.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis, April 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.692761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 31454201-0a0c-44ca-837f-36efe3eea5f1 · outbound

This paper cites NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models, April 2024.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models, April 2024

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.672734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 84602fb7-7bf0-4493-9b41-12650abc3872 · outbound

This paper cites Libriheavy: a 50,000 hours asr corpus with punctuation casing and context,.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Libriheavy: a 50,000 hours asr corpus with punctuation casing and context,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.654066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fa7fcdce-99c5-42f5-a527-58038e72b5a1 · outbound

This paper cites Analyzing and Improving the Training Dynamics of Diffusion Models.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Analyzing and Improving the Training Dynamics of Diffusion Models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.633340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bc03816e-8704-4a65-a3bf-6d7772f6b3be · outbound

This paper cites CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.654964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e0749a-329f-4bde-968a-37b2e22944bd · outbound

This paper cites High-Fidelity Audio Compression with Improved RVQGAN.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis High-Fidelity Audio Compression with Improved RVQGAN

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.610995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5cfa107d-b223-498f-870b-eec2eb05cec5 · outbound

This paper cites BASE TTS: Lessons from building a billion- parameter Text-to-Speech model on 100K hours of data, February 2024.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis BASE TTS: Lessons from building a billion- parameter Text-to-Speech model on 100K hours of data, February 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.586357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d5de89ad-5244-4d9f-98e4-a6e6c7f4439d · outbound

This paper cites V oicebox: Text-guided multilin- gual universal speech generation at scale.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis V oicebox: Text-guided multilin- gual universal speech generation at scale

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.567050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eebed74a-9958-470e-95d0-23b257fd04be · outbound

This paper cites REPA-E: Unlocking V AE for End-to-End Tuning with Latent Diffusion Transformers, April 2025.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis REPA-E: Unlocking V AE for End-to-End Tuning with Latent Diffusion Transformers, April 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.549525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 91a25cc2-7bd8-42d5-8329-6c8aba46c0a8 · outbound

This paper cites Neural Speech Synthesis with Transformer Network.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Neural Speech Synthesis with Transformer Network

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.684377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e8c5c59-9594-4e39-b972-1cd22596e5c6 · outbound

This paper cites Autoregressive Image Generation without Vector Quantization.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Autoregressive Image Generation without Vector Quantization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.689870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54dc638d-e939-4cb4-8af7-14894dfa04f4 · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.695773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fbfafa0-f539-453a-95f2-15b3161ffe4c · outbound

This paper cites Autoregressive Diffusion Transformer for Text-to-Speech Synthesis.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Autoregressive Diffusion Transformer for Text-to-Speech Synthesis

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.701539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 439fbd8b-bb4f-46e5-95be-fc4997f507ad · outbound

This paper cites LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of End-to-End ASR Models.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of End-to-End ASR Models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.516431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 95e71bba-b9f8-4aa8-9666-b8f109020006 · outbound

This paper cites Autoregressive Speech Synthesis without Vector Quantization.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Autoregressive Speech Synthesis without Vector Quantization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.712652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40e3b997-26db-4c2a-bd81-b5ea98b4355a · outbound

This paper cites Finite Scalar Quantization: VQ-V AE Made Simple, October 2023.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Finite Scalar Quantization: VQ-V AE Made Simple, October 2023

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.492317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ca2f0a00-cd01-453c-ab18-6e562a1fbf90 · outbound

This paper cites HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.722764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c9ac590-e942-4621-8e3c-34b488390f90 · outbound

This paper cites Librispeech: An ASR corpus based on public domain audio books.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Librispeech: An ASR corpus based on public domain audio books

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.470831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 25b5268c-6ecf-4fe3-9b77-07cb518ff5bd · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Robust speech recognition via large-scale weak supervision

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.736142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e2ca104-69e1-476a-8e25-097231b26321 · outbound

This paper cites Revisiting over-smoothness in text to speech.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Revisiting over-smoothness in text to speech

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.435875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7d78640a-6f08-41fe-8d3a-5d48bcd6aad6 · outbound

This paper cites UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.748760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7183e728-81f3-4342-807a-9d614121e605 · outbound

This paper cites AutoClip: Adaptive Gradient Clipping for Source Separation Networks, July 2020.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis AutoClip: Adaptive Gradient Clipping for Source Separation Networks, July 2020

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.418343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f5943c9b-07cd-4172-98a2-2b6298578e77 · outbound

This paper cites GLU Variants Improve Transformer.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis GLU Variants Improve Transformer

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.761504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c67adb7-6ae8-4540-9c83-0d94bb0ab2bd · outbound

This paper cites NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers, May 2023.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers, May 2023

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.396325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aeb04ce9-c2aa-4a98-9784-484353023d73 · outbound

This paper cites Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.774022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7350a1b-82de-4554-bdc7-c4b14864f0d5 · outbound

This paper cites Ella-v: Stable neural codec language modeling with alignment-guided sequence reordering.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Ella-v: Stable neural codec language modeling with alignment-guided sequence reordering

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.359518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8d0864e8-9d61-4847-b4ae-8007d02a4b4a · outbound

This paper cites Steinmetz, Jordi Pons, Santiago Pascual, and Joan Serrà.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Steinmetz, Jordi Pons, Santiago Pascual, and Joan Serrà

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.339544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 88ac9b82-424e-4284-90e6-7e3474890267 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.792348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e22d374-289f-4f3a-9e3a-fd63b7c1ac92 · outbound

This paper cites NaturalSpeech: End-to-End Text-to-Speech Synthesis With Human-Level Quality.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis NaturalSpeech: End-to-End Text-to-Speech Synthesis With Human-Level Quality

Reference 51

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T16:01:53.540373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1d9c93ff-5827-44e5-a4de-57432d2981a0 · outbound

This paper cites Continuous Speech Synthesis using per-token Latent Diffusion, October 2024.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Continuous Speech Synthesis using per-token Latent Diffusion, October 2024

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.309528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6e0e7da8-4df0-4875-9f8c-592ba1c12b98 · outbound

This paper cites Neural Discrete Representation Learning.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Neural Discrete Representation Learning

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.284600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e7a870c0-8ae9-4cb2-b7d2-6361397113fe · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.813060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5b0d8c7-9cc3-4359-8b41-ce886d522b74 · outbound

This paper cites FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.818331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f5c358-f70e-48f2-9779-a8badee88a3c · outbound

This paper cites Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.823558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d998edd-d252-4ed5-a46d-6df9e126adaa · outbound

This paper cites MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer, October 2024.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer, October 2024

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.263650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 536b2ec0-62b9-481b-b8ee-ab4ccc1042b9 · outbound

This paper cites Towards audio language modeling -- an overview.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Towards audio language modeling -- an overview

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.834220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 981dec4e-3a18-4f0b-a20a-d12e616454d4 · outbound

This paper cites RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.839342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa13fcd6-7014-4990-9911-08281a879493 · outbound

This paper cites On Layer Normalization in the Transformer Architecture.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis On Layer Normalization in the Transformer Architecture

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.844345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ee09ec-e051-4671-805d-6f91e1e6141b · outbound

This paper cites Reconstruction vs.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Reconstruction vs

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.245081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cc1ff55e-0c36-4212-9fcd-d9cfb7916350 · outbound

This paper cites Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.854277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffefd789-2cff-4087-abec-ee7e034b4dd6 · outbound

This paper cites Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think, February 2025.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think, February 2025

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.219454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0fb202ed-c747-45d3-918b-8fe81290ee9f · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Soundstream: An end-to-end neural audio codec

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.864521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ac53ff-9952-42b0-9262-3634970b2ed3 · outbound

This paper cites Weiss, Ye Jia, Zhifeng Chen, and Yonghui Wu.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Weiss, Ye Jia, Zhifeng Chen, and Yonghui Wu

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.188022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 449586ca-366b-4904-8afd-99a0efc17c80 · outbound

This paper cites Root Mean Square Layer Normalization.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Root Mean Square Layer Normalization

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.877438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9c9843c-e0b0-4d37-9727-f0540ccd7d32 · outbound

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

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.883671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c846336-a41f-4239-85a9-dc8976d02ace · outbound

This paper cites ,𝑁𝑆𝐵,𝐶!,𝑁 + UpsamplingBlock Channel toSpace ChannelDuplicating𝐵,𝐶.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis ,𝑁𝑆𝐵,𝐶!,𝑁 + UpsamplingBlock Channel toSpace ChannelDuplicating𝐵,𝐶

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:01:54.168792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c35e1bbd-d098-48b1-b4de-3d045c067d50 · outbound

This paper cites Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.645000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f877a92c-605b-4346-bb9a-935b28c1d987 · inbound

On the Distillation Loss Functions of Speech VAE for Unified Reconstruction, Understanding, and Generation cites this paper.

On the Distillation Loss Functions of Speech VAE for Unified Reconstruction, Understanding, and Generation CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:25:59.528620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c6001f44-543d-4894-8ba1-62ff1c34b900 · inbound

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis cites this paper.

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-19T19:02:43.569018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6947956a-a27e-4039-9221-c3793b937b2b · inbound

VoxCPM2 Technical Report cites this paper.

VoxCPM2 Technical Report CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-02T19:47:19.714861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.