Paper Citation Record · LEDGER

Differentiable Reward Optimization for LLM based TTS system

As of 7 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 3 inbound Pith citation observations for arXiv:2507.05911.

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

pith.paper-citation-record.v1
2507.05911 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:21:04.007502Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:21:03.907098Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T03:27:34.881668Z

Reference resolution

34 of 34 outbound references displayed

verified exact1
verified fuzzy12
unresolved20
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation af6f0ba1-e714-474d-85b0-3c6f96591e36 · outbound

This paper cites an unresolved cited work.

Differentiable Reward Optimization for LLM based TTS system Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:21:04.287642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a8c3ba41-ce94-48ce-9281-c1dc4798c9f2 · outbound

This paper cites Differentiable Reward Optimization for LLM based TTS system.

Differentiable Reward Optimization for LLM based TTS system Differentiable Reward Optimization for LLM based TTS system

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.907098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d759b234-f61b-440c-a3a8-0414f5eaaf81 · outbound

This paper cites Figure 1 shows the difference between the DiffRO and the existing RL method like DPO.

Differentiable Reward Optimization for LLM based TTS system Figure 1 shows the difference between the DiffRO and the existing RL method like DPO

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.279359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3143c8d2-3fda-4e26-be7a-c317c3a78512 · outbound

This paper cites Experimental Setup.

Differentiable Reward Optimization for LLM based TTS system Experimental Setup

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T19:21:04.270240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e98d9252-e536-4fa8-936f-e4197d2273fe · outbound

This paper cites Compared to other reinforcement learning methods, DiffRO is capable of directly predicting reward scores from speech tokens rather than from synthesized audio.

Differentiable Reward Optimization for LLM based TTS system Compared to other reinforcement learning methods, DiffRO is capable of directly predicting reward scores from speech tokens rather than from synthesized audio

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.261574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fa37fdba-494b-4665-b948-5dbc05bc8b34 · outbound

This paper cites Denoising diffusion probabilistic models,.

Differentiable Reward Optimization for LLM based TTS system Denoising diffusion probabilistic models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.252926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation db4d6f1f-e8d5-424b-bbba-0311e1c1fef5 · outbound

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

Differentiable Reward Optimization for LLM based TTS system Neural codec language models are zero-shot text to speech synthesizers,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.243318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b87f9175-72f9-4052-ba6c-4c17668cba53 · outbound

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

Differentiable Reward Optimization for LLM based TTS system Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.927154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3419c96d-06ef-4023-9f1f-7aa98617f27a · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Differentiable Reward Optimization for LLM based TTS system Fine-Tuning Language Models from Human Preferences

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.930674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ca2a934-9b4e-4e91-b437-ec4e5b423d9a · outbound

This paper cites BATON: Aligning Text-to-Audio Model with Human Preference Feedback.

Differentiable Reward Optimization for LLM based TTS system BATON: Aligning Text-to-Audio Model with Human Preference Feedback

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:21:04.134137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ae14a623-b5bc-4baa-b660-2e36555c476f · outbound

This paper cites Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback.

Differentiable Reward Optimization for LLM based TTS system Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.937201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad003da6-0d82-4a6f-ae68-dc40dcb6d347 · outbound

This paper cites Robust zero- shot text-to-speech synthesis with reverse inference optimization,.

Differentiable Reward Optimization for LLM based TTS system Robust zero- shot text-to-speech synthesis with reverse inference optimization,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.234285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 24b90341-4162-4efd-b4e5-185aefe70570 · outbound

This paper cites Cosyvoice 2: Scalable streaming speech synthesis with large language models,.

Differentiable Reward Optimization for LLM based TTS system Cosyvoice 2: Scalable streaming speech synthesis with large language models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.216021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b63ce8a-c9bf-4023-b1e3-db6397667678 · outbound

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

Differentiable Reward Optimization for LLM based TTS system Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.946996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d68e9d5-2e5e-40cd-92bd-32082180c84d · outbound

This paper cites Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization.

Differentiable Reward Optimization for LLM based TTS system Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.949976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c62705d-c203-4ba0-a71a-92f75d48aa4b · outbound

This paper cites Proximal Policy Optimization Algorithms.

Differentiable Reward Optimization for LLM based TTS system Proximal Policy Optimization Algorithms

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.952970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c36fff5-d410-4ec5-8f65-8e207496bd0e · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Differentiable Reward Optimization for LLM based TTS system Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.955658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39a0bd8d-5ab3-46b2-920b-5f6e1f5668db · outbound

This paper cites Asq: An ultra-low bit rate asr-oriented speech quantization method,.

Differentiable Reward Optimization for LLM based TTS system Asq: An ultra-low bit rate asr-oriented speech quantization method,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.225241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 82b8e870-57a9-4240-8ada-7202285ac39e · outbound

This paper cites AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark.

Differentiable Reward Optimization for LLM based TTS system AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.983187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dafd7893-1b29-45a3-af82-fb00420edb9a · outbound

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

Differentiable Reward Optimization for LLM based TTS system CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.964399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b9ce675-5e3d-4150-8ae2-dc62834e45d7 · outbound

This paper cites Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio,.

Differentiable Reward Optimization for LLM based TTS system Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.207339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9cf9a8d5-836e-4f85-a99a-afb1b4a17279 · outbound

This paper cites Panns: Large-scale pretrained audio neural networks for audio pattern recognition,.

Differentiable Reward Optimization for LLM based TTS system Panns: Large-scale pretrained audio neural networks for audio pattern recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.198504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 433206e1-8cd7-4efd-9f85-458541ea8b18 · outbound

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

Differentiable Reward Optimization for LLM based TTS system Common voice: A massively-multilingual speech corpus,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.972402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07aae18e-a3e3-4cc6-811e-2c7ab260765d · outbound

This paper cites The voicemos challenge 2022,.

Differentiable Reward Optimization for LLM based TTS system The voicemos challenge 2022,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.184689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7ab4b5bd-b48f-4fee-9fda-fd0ec86dea26 · outbound

This paper cites Iemocap: Interactive emotional dyadic motion capture database,.

Differentiable Reward Optimization for LLM based TTS system Iemocap: Interactive emotional dyadic motion capture database,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.979488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f89e426-80c3-4f7b-889d-7f0670e5d05c · outbound

This paper cites Robust Speech Recognition via Large-Scale Weak Supervision.

Differentiable Reward Optimization for LLM based TTS system Robust Speech Recognition via Large-Scale Weak Supervision

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:04.004618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a397a2aa-8407-4328-8ff1-11f688955eb5 · outbound

This paper cites FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs.

Differentiable Reward Optimization for LLM based TTS system FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.987118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 036ae5c2-1986-4023-a598-1804bcc8cea9 · outbound

This paper cites Dnsmos p.835: A non- intrusive perceptual objective speech quality metric to evaluate noise suppressors,.

Differentiable Reward Optimization for LLM based TTS system Dnsmos p.835: A non- intrusive perceptual objective speech quality metric to evaluate noise suppressors,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.172299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a913a405-6aa8-4709-99b5-ba60796d5be2 · outbound

This paper cites EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark.

Differentiable Reward Optimization for LLM based TTS system EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.992535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19dc18b0-34b9-4b54-9d08-4ceb984b145e · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

Differentiable Reward Optimization for LLM based TTS system Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.995596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9690060e-f981-4df2-969d-edbf34cee12c · outbound

This paper cites MinMo: A Multimodal Large Language Model for Seamless Voice Interaction.

Differentiable Reward Optimization for LLM based TTS system MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.998457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cddfe44-4ecd-431a-a4b1-c23c24355f13 · outbound

This paper cites Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to- end speech recognition,.

Differentiable Reward Optimization for LLM based TTS system Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to- end speech recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:21:04.163819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1db4b377-e5fd-4c35-b9b2-d12bf1683ce2 · outbound

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

Differentiable Reward Optimization for LLM based TTS system F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:04.007502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f700fc2-640f-4295-a63f-959c6af2aac1 · outbound

This paper cites Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization.

Differentiable Reward Optimization for LLM based TTS system Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T19:21:03.943678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a8c3ba41-ce94-48ce-9281-c1dc4798c9f2 · inbound