Paper Citation Record · LEDGER

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM

As of 13 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2411.13159.

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

pith.paper-citation-record.v1
2411.13159 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T16:49:52.048329Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

38 of 38 outbound references displayed

verified exact2
verified fuzzy26
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0e6fab46-8dbb-4c43-a896-2b8f8f623927 · outbound

This paper cites Attention-based models for speech recognition,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Attention-based models for speech recognition,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.598461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b00eac6e-65b4-4d5a-ae86-1f5e9c96da1b · outbound

This paper cites Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.585587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f6f47d35-077a-454e-b07c-b0a9e2b3e0f7 · outbound

This paper cites Sequence transduction with recurrent neural networks,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Sequence transduction with recurrent neural networks,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.572921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fc370d7e-fa83-44c5-ab50-be9990152af1 · outbound

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

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:51.903271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21da7e93-d7b2-4662-96c3-58113ff3e93f · outbound

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

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:51.907801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfdf576d-1c58-4cac-944f-fd9fb19810b4 · outbound

This paper cites Human per- ception of audio deepfakes,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Human per- ception of audio deepfakes,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.559569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 06bcdbe3-bf3f-4a60-87f5-2cc13fed8b59 · outbound

This paper cites As Good As A Coin Toss: Human detection of AI-generated images, videos, audio, and audiovisual stimuli.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM As Good As A Coin Toss: Human detection of AI-generated images, videos, audio, and audiovisual stimuli

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:51.916766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bd13e30-b48b-4b67-98e2-81ac773c8dff · outbound

This paper cites Task arithmetic can mitigate synthetic-to-real gap in automatic speech recognition,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Task arithmetic can mitigate synthetic-to-real gap in automatic speech recognition,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.545205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d201a81d-046d-4a36-90f6-61b94d136eff · outbound

This paper cites Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.532429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 682d7fe9-d62b-42b1-ab1b-d155925d83c3 · outbound

This paper cites Using synthetic audio to improve the recognition of out-of-vocabulary words in end-to-end asr systems,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Using synthetic audio to improve the recognition of out-of-vocabulary words in end-to-end asr systems,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.519505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5a073a15-7086-4f8f-a40a-8c7c7ef1b06f · outbound

This paper cites Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-12T16:49:52.205063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2c645ce8-be4c-4f3b-87ad-373694d2c021 · outbound

This paper cites SYNT++: utilizing imperfect synthetic data to improve speech recognition,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM SYNT++: utilizing imperfect synthetic data to improve speech recognition,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.505925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation afdea102-9083-4122-aa83-0c68034576b2 · outbound

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

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM V oicecraft: Zero-shot speech editing and text-to-speech in the wild,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.493281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation da877376-ab53-4e33-b329-0132b5ff4076 · outbound

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

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:51.947601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb95c1ce-fc56-420c-be68-f932a69f80c5 · outbound

This paper cites Text is all you need: Personalizing ASR models using controllable speech synthesis,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Text is all you need: Personalizing ASR models using controllable speech synthesis,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.479677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 46f256f2-7526-4c5c-bd1a-87dc94ba4b5c · outbound

This paper cites Using personalized speech synthesis and neural language generator for rapid speaker adaptation,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Using personalized speech synthesis and neural language generator for rapid speaker adaptation,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.465878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ac775e04-ab81-417a-b470-955d87b7cd9e · outbound

This paper cites Rapid RNN-T adaptation using personalized speech synthesis and neural language generator,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Rapid RNN-T adaptation using personalized speech synthesis and neural language generator,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.452237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f0e52a0c-586b-4529-97f5-d78145dd7ac7 · outbound

This paper cites Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:51.964550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d4ded72-29d8-4f52-824e-b533b07b0c4e · outbound

This paper cites Synthesizing dysarthric speech using multi-speaker tts for dysarthric speech recognition,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Synthesizing dysarthric speech using multi-speaker tts for dysarthric speech recognition,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.439133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2efbe179-bce2-48fc-8a09-bf68c18b3620 · outbound

This paper cites GPT-4 Technical Report.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM GPT-4 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:51.973366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ae5b9e3-8bea-46f3-91d8-a699c22c9b60 · outbound

This paper cites Glm-130b: An open bilingual pre-trained model,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Glm-130b: An open bilingual pre-trained model,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.426246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3e78e59e-362e-4c20-b85e-7397e19b203d · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM LLaMA: Open and Efficient Foundation Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:51.981507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dd375f2-57a6-4b4b-ade3-3b7f75de6257 · outbound

This paper cites Can Generative Large Language Models Perform ASR Error Correction?.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Can Generative Large Language Models Perform ASR Error Correction?

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:51.985501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76db2d5b-ad26-4709-9692-cbbd5fd86135 · outbound

This paper cites Rewritelm: An instruction- tuned large language model for text rewriting,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Rewritelm: An instruction- tuned large language model for text rewriting,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.413071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b8b9cdac-352b-4501-8bbc-460f16831a6a · outbound

This paper cites 69–80, Springer Nature Switzerland, 2023.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM 69–80, Springer Nature Switzerland, 2023

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.400242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e0cb417d-c619-47b9-917b-995e9fae522c · outbound

This paper cites Leveraging llm for augmenting textual data in code-switching asr: Arabic as an example,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Leveraging llm for augmenting textual data in code-switching asr: Arabic as an example,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.386859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c7f0150b-edc8-4fc2-a7fc-a052aa11709b · outbound

This paper cites Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-12T16:49:52.117561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4649d660-aef9-4711-aa25-2f3aa81a475d · outbound

This paper cites Corpus synthesis for zero-shot ASR domain adaptation using large language models,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Corpus synthesis for zero-shot ASR domain adaptation using large language models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.373589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 656e6a83-fa4b-4ab6-9e48-0b8f59fb3cbc · outbound

This paper cites Librispeech: an asr corpus based on public domain audio books,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Librispeech: an asr corpus based on public domain audio books,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.360137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ed13c12b-97b8-4280-a7ad-390c02959f4d · outbound

This paper cites Attention is all you need,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Attention is all you need,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.346265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1e2e7bfd-efb1-46a9-92fe-00c16f4c5c79 · outbound

This paper cites Conformer: Convolution-augmented transformer for speech recognition,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Conformer: Convolution-augmented transformer for speech recognition,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.331915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 72d6e128-fe9f-4661-9957-86c7f615ce2c · outbound

This paper cites ESPnet: End-to-end speech processing toolkit,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM ESPnet: End-to-end speech processing toolkit,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.316927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ee1d0c56-a028-4941-bd31-e05e9cd300fb · outbound

This paper cites Specaugment: A simple data augmentation method for automatic speech recognition,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Specaugment: A simple data augmentation method for automatic speech recognition,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.303126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3faa20a1-64e9-489e-88dc-56294bd127a3 · outbound

This paper cites Hybrid CTC/attention architecture for end-to-end speech recognition,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Hybrid CTC/attention architecture for end-to-end speech recognition,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.288996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3a9c15a0-d59a-4fd0-8499-40903b06ab84 · outbound

This paper cites Mosnet: Deep learning based objective assessment for voice conversion,.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Mosnet: Deep learning based objective assessment for voice conversion,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.275023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6dd41499-236c-4ce4-8ddb-28c99ea24716 · outbound

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

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM WavLM: Large-scale self-supervised pre- training for full stack speech processing,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:49:52.260429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 18475b0f-bbe1-4fa3-9e59-9ac00c2f9990 · outbound

This paper cites Quantifying Bias in Automatic Speech Recognition.

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Quantifying Bias in Automatic Speech Recognition

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:52.044066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e36dc1-c0a5-4332-a579-641e05bc45fd · outbound

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

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM Robust Speech Recognition via Large-Scale Weak Supervision

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:52.048329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.