What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection | Paper Citation Record

Observation 500e5d23-640d-4d47-bdaa-1039c798acc7 · outbound

This paper cites Warning: Humans cannot reliably detect speech deepfakes,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Warning: Humans cannot reliably detect speech deepfakes,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97245bb3-fcfb-496f-a82d-7fda31a29bce · outbound

This paper cites Audio deepfake detection using deep learning,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Audio deepfake detection using deep learning,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 164ed5dd-068d-4779-ac97-0091eb21954f · outbound

This paper cites A comprehensive survey of deepfake generation and detection techniques in audio-visual media,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection A comprehensive survey of deepfake generation and detection techniques in audio-visual media,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e6c06dd-aa76-408a-aad9-d99c1b4d9be8 · outbound

This paper cites Audio Deepfake Detection: A Survey.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Audio Deepfake Detection: A Survey

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a29b8516-b507-4410-a095-856dabe45eec · outbound

This paper cites Vulnerabilities of audio-based biometric authentication systems against deepfake speech synthesis,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Vulnerabilities of audio-based biometric authentication systems against deepfake speech synthesis,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 320195a0-9e01-4a7a-a1df-c24ab9c33ad5 · outbound

This paper cites Audio deepfake detection: What has been achieved and what lies ahead,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Audio deepfake detection: What has been achieved and what lies ahead,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1faa814-c3c4-4601-9a0b-25d7e0f3e3ba · outbound

This paper cites ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6b77ab7-9f35-4c9e-be70-c30297a4c804 · outbound

This paper cites End-to-end anti-spoofing with RawNet2,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection End-to-end anti-spoofing with RawNet2,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb4fa149-b063-43b0-9c38-f73ad086d184 · outbound

This paper cites AASIST: Audio anti-spoofing using integrated spectro-temporal graph attention networks,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection AASIST: Audio anti-spoofing using integrated spectro-temporal graph attention networks,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56234ba1-da39-4deb-b9db-4d83c8d8d758 · outbound

This paper cites Bias in data-driven artificial intelligence systems: An introductory survey,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Bias in data-driven artificial intelligence systems: An introductory survey,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bf8d3ad-2984-42d0-b5d9-4a0a7c765235 · outbound

This paper cites Fair voice biometrics: Impact of demographic imbalance on group fairness in speaker recogni- tion,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Fair voice biometrics: Impact of demographic imbalance on group fairness in speaker recogni- tion,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4707b01c-377a-4af6-902e-307d88362123 · outbound

This paper cites Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd25dc13-567a-4457-bcee-b405b065c7db · outbound

This paper cites Gender fairness in audio deepfake detection: Performance and disparity analysis,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Gender fairness in audio deepfake detection: Performance and disparity analysis,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1cfe465-de47-4d8a-bd38-7f67e9e34bb1 · outbound

This paper cites Fairness without demographics in repeated loss minimization,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Fairness without demographics in repeated loss minimization,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 578d2c61-9225-4ca5-a778-f9a40eaf7c31 · outbound

This paper cites AFSS: Artifact-focused self-synthesis for mitigat- ing bias in audio deepfake detection,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection AFSS: Artifact-focused self-synthesis for mitigat- ing bias in audio deepfake detection,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf4dde60-f1e4-405a-937a-6190c490623b · outbound

This paper cites GBDF: Gender balanced deepfake dataset towards fair deepfake detection,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection GBDF: Gender balanced deepfake dataset towards fair deepfake detection,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94a2b0a1-497b-40f0-a103-847da1791cb2 · outbound

This paper cites A survey on bias and fairness in machine learning,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection A survey on bias and fairness in machine learning,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6351f4d-1f6e-400a-80c1-c8dd36ac651f · outbound

This paper cites Improving fairness in deepfake detection,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Improving fairness in deepfake detection,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7d62e4f-33a5-4da1-8e09-15686bbf16bb · outbound

This paper cites Preserving fairness generalization in deepfake detection,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Preserving fairness generalization in deepfake detection,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724b10d1-e7bc-47c5-9d28-87e4b8fbe71a · outbound

This paper cites FairSSD: Understanding bias in synthetic speech detectors,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection FairSSD: Understanding bias in synthetic speech detectors,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5766938f-019b-4e4d-9ecd-e9c26572eb06 · outbound

This paper cites Equality of opportunity in supervised learning,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Equality of opportunity in supervised learning,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 276050b4-d39d-4689-b183-545b64c19b7f · outbound

This paper cites Fair prediction with disparate impact: A study of bias in recidivism prediction instruments,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Fair prediction with disparate impact: A study of bias in recidivism prediction instruments,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d3b187-b1ea-49a9-a58c-52f940637ba3 · outbound

This paper cites Phonetic analysis of real and synthetic speech using HuBERT embeddings: Perspectives for deepfake detection,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Phonetic analysis of real and synthetic speech using HuBERT embeddings: Perspectives for deepfake detection,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b378a403-35e3-4e6d-a029-27639ac92806 · outbound

This paper cites Towards trustworthy audio deepfake detection: A systematic framework for diagnosing and mitigating gender bias,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Towards trustworthy audio deepfake detection: A systematic framework for diagnosing and mitigating gender bias,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff8a8e8-2de7-4ea2-ade8-eb26f255bb33 · outbound

This paper cites PhonemeDF: A synthetic speech dataset for audio deepfake detection and naturalness evaluation,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection PhonemeDF: A synthetic speech dataset for audio deepfake detection and naturalness evaluation,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc3ecfd-e067-408b-b294-3ea28890d035 · outbound

This paper cites Investigating the impact of speech enhancement on audio deepfake detection in noisy environments,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Investigating the impact of speech enhancement on audio deepfake detection in noisy environments,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74a5b503-d539-4f04-b7f4-3a33ee616212 · outbound

This paper cites An Examination of Fairness of AI Models for Deepfake Detection.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection An Examination of Fairness of AI Models for Deepfake Detection

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beabd784-f88f-4c4c-8c33-7f7cc0270172 · outbound

This paper cites Analyzing fairness in deepfake detection with massively annotated databases,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Analyzing fairness in deepfake detection with massively annotated databases,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f2053d5-6ad8-4279-a36e-28e8d1552c64 · outbound

This paper cites Bias in automated speaker recognition,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Bias in automated speaker recognition,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6140bbc3-9585-4538-907e-f5f13063a11b · outbound

This paper cites SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2bad8a-eb84-4786-8c1a-c74818bd1705 · outbound

This paper cites Deep residual learning for image recognition,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Deep residual learning for image recognition,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0817f0d-60a7-4c63-921c-bdec0ec869f8 · outbound

This paper cites Easy, interpretable, effective: openSMILE for voice deepfake detection,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Easy, interpretable, effective: openSMILE for voice deepfake detection,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e960aa1b-57e6-4574-b420-9d422aa6bc89 · outbound

This paper cites Natural- Speech: End-to-end text-to-speech synthesis with human-level quality,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Natural- Speech: End-to-end text-to-speech synthesis with human-level quality,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48ea459f-51b7-415c-bc40-c443c5b5d9a3 · outbound

This paper cites ASVspoof: The automatic speaker verification spoofing and countermeasures challenge,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection ASVspoof: The automatic speaker verification spoofing and countermeasures challenge,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c4aae33-4a1e-4e5d-b086-0ce13e99eb2d · outbound

This paper cites ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b326bcb6-6afd-4fc3-9f66-dd2d4b32cddb · outbound

This paper cites ASVspoof 2021: Towards spoofed and deepfake speech detection in the wild,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection ASVspoof 2021: Towards spoofed and deepfake speech detection in the wild,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc88e0cf-2c58-41f6-b86e-3a3bbb96811c · outbound

This paper cites To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de5d25ab-52c5-481f-b1d7-4f14d9d4b3ae · outbound

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

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection WavLM: Large-scale self-supervised pre-training for full stack speech processing,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8f19344-3532-45f3-88f4-273318edaf5d · outbound

This paper cites Controlling the false discovery rate: A practical and powerful approach to multiple testing,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Controlling the false discovery rate: A practical and powerful approach to multiple testing,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2195dba8-a93a-4b69-96a4-0a548fbbf9f1 · outbound

This paper cites An intervention-based framework for shortcut diagnosis in spoofing countermeasures,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection An intervention-based framework for shortcut diagnosis in spoofing countermeasures,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f615f2-cf63-463a-9849-b2ab225c3d68 · outbound

This paper cites Can SSL frontend generalize to all-type audio spoofing?.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Can SSL frontend generalize to all-type audio spoofing?

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 881e8326-4971-44d5-979d-29113fb17af2 · outbound

This paper cites Decoupled Weight Decay Regularization.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Decoupled Weight Decay Regularization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2944c02e-eb90-4b35-a0d5-5847726a4542 · outbound

This paper cites Creating non-parametric bootstrap samples using Poisson frequencies,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Creating non-parametric bootstrap samples using Poisson frequencies,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e993a5-53bf-4e76-ad57-e985329a3291 · outbound

This paper cites The control of the false discovery rate in multiple testing under dependency,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection The control of the false discovery rate in multiple testing under dependency,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dda6e18-031f-4239-93d7-45f8af273cd7 · outbound

This paper cites Efron and R.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Efron and R

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b66ccb00-8c55-4a6c-baa6-19e27d59d9bb · outbound

This paper cites Creating new language and voice components for the updated MaryTTS text-to-speech synthesis platform,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Creating new language and voice components for the updated MaryTTS text-to-speech synthesis platform,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffcced3b-cf2d-42d9-804e-a409a60e4ecc · outbound

This paper cites ZMM-TTS: Zero-shot multilingual and multispeaker speech synthesis conditioned on self-supervised discrete speech representations,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection ZMM-TTS: Zero-shot multilingual and multispeaker speech synthesis conditioned on self-supervised discrete speech representations,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5e333e2-9209-4819-bef3-bae11bb12651 · outbound

This paper cites YourTTS: Towards zero-shot multi-speaker TTS and zero- shot voice conversion for everyone,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection YourTTS: Towards zero-shot multi-speaker TTS and zero- shot voice conversion for everyone,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 598472a0-17c8-4bad-a142-30cdc42e8ed0 · outbound

This paper cites XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4933bd34-6528-43e1-a495-e1681c938d82 · outbound

This paper cites Glow-TTS: A generative flow for text-to-speech via monotonic alignment search,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Glow-TTS: A generative flow for text-to-speech via monotonic alignment search,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 696d2734-4ef1-4a46-a55f-5ab2955a5524 · outbound

This paper cites Grad- TTS: A diffusion probabilistic model for text-to-speech,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Grad- TTS: A diffusion probabilistic model for text-to-speech,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e71e3b9a-8de6-4cc1-99c5-688362adba5b · outbound

This paper cites BigVGAN: A Universal Neural Vocoder with Large-Scale Training.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection BigVGAN: A Universal Neural Vocoder with Large-Scale Training

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55722d7e-133a-438d-bf3f-19224d02d79b · outbound

This paper cites Exact prosody cloning in zero-shot multispeaker text-to-speech,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Exact prosody cloning in zero-shot multispeaker text-to-speech,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 963ad5dd-2e68-4467-988b-c4663b0bee64 · outbound

This paper cites FastPitch: Parallel text-to-speech with pitch prediction,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection FastPitch: Parallel text-to-speech with pitch prediction,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f432cba7-ddda-4927-af22-bfa7231ad499 · outbound

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

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e148a87-2b1f-4159-9772-7bd22a6b8bfc · outbound

This paper cites Low-resource multilingual and zero- shot multispeaker TTS,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Low-resource multilingual and zero- shot multispeaker TTS,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7b1ade3-0c46-4c20-95d6-f9752b32c64f · outbound

This paper cites Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24b6a1b7-2b96-4467-8af8-1cb998e91ee8 · outbound

This paper cites HiFi-GAN: Generative adversarial net- works for efficient and high-fidelity speech synthesis,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection HiFi-GAN: Generative adversarial net- works for efficient and high-fidelity speech synthesis,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19b9363f-7e2a-4602-a373-90ee30f2e6b6 · outbound

This paper cites Natural TTS synthesis by conditioning WaveNet on mel spectrogram predictions,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Natural TTS synthesis by conditioning WaveNet on mel spectrogram predictions,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e9c61e-998a-493d-bb7b-fdbbd34c7b87 · outbound

This paper cites StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e8ec5d-c38e-4b13-b24a-ac0ef6eeef64 · outbound

This paper cites V oice conversion using speech-to-speech neuro-style transfer,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection V oice conversion using speech-to-speech neuro-style transfer,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfbd7a63-2dcf-4fa8-b925-a74ee6e780ba · outbound

This paper cites Self-supervised speech representation learning: A review,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Self-supervised speech representation learning: A review,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0840c4c5-62a1-49aa-a2ab-8ffc2bf37e1e · outbound

This paper cites Toward noise-aware audio deepfake detection: Survey, SNR-benchmarks, and practical recipes,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Toward noise-aware audio deepfake detection: Survey, SNR-benchmarks, and practical recipes,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e966358-5b5f-45ed-a45e-260d84dbbd7b · outbound

This paper cites C3-DINO: Joint contrastive and non-contrastive self-supervised learning for speaker verification,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection C3-DINO: Joint contrastive and non-contrastive self-supervised learning for speaker verification,

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21193bf5-0242-451d-96ca-2c4060cd8187 · outbound

This paper cites Context and transcripts improve detection of deepfake audios of public figures,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Context and transcripts improve detection of deepfake audios of public figures,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b839c8db-ed75-4964-b6f2-4077e1d1027a · outbound

This paper cites Fine-tuning self-supervised learning models for end-to-end pronunciation scoring,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Fine-tuning self-supervised learning models for end-to-end pronunciation scoring,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 708f5ecf-8359-4ded-8112-23cff57438e9 · outbound

This paper cites Using optimal f-measure and random resampling in gene ontology enrichment calculations,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Using optimal f-measure and random resampling in gene ontology enrichment calculations,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87154a5c-95b1-441c-b09a-3e9de05ca0fd · outbound

This paper cites Modified FDR controlling proce- dure for multi-stage analyses,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Modified FDR controlling proce- dure for multi-stage analyses,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fce8bcef-eebe-4620-b540-60c50826209f · outbound

This paper cites Cyclostationarity analysis as a complement to self-supervised representations for speech deepfake detection,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Cyclostationarity analysis as a complement to self-supervised representations for speech deepfake detection,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e06aba63-311a-46e9-b06a-7f19b18c29ef · outbound

This paper cites Training-free cross- lingual dysarthria severity assessment via phonological subspace analysis in self-supervised speech representations,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Training-free cross- lingual dysarthria severity assessment via phonological subspace analysis in self-supervised speech representations,

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2932c63c-ecc5-40eb-954d-5f204883f7f7 · outbound

This paper cites Bootstrap confidence regions for the intensity of a Poisson point process,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Bootstrap confidence regions for the intensity of a Poisson point process,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3bdd6d1-2856-47d9-b328-afa624d7dbea · outbound

This paper cites PyTorch: An imperative style, high- performance deep learning library,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection PyTorch: An imperative style, high- performance deep learning library,

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159b92fa-3cb8-4b55-88b3-4855081c08d7 · outbound

This paper cites Fairness through awareness,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Fairness through awareness,

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee125d76-89b7-4f11-9198-d16c2a1ad946 · outbound

This paper cites Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62356cb7-8ed5-4db1-9604-80a7dbda200d · outbound

This paper cites A review on fairness in machine learning,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection A review on fairness in machine learning,

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 542fcb57-3546-41d1-b60b-f0062bc4486c · outbound

This paper cites Fairness definitions explained,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Fairness definitions explained,

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 079a216e-b869-4b07-92f4-d76824fd3444 · outbound

This paper cites Measuring algorithmic fairness,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Measuring algorithmic fairness,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3994676e-5610-420e-81e4-c81491ea2866 · outbound

This paper cites Bias preservation in machine learning: The legality of fairness metrics under EU non-discrimination law,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Bias preservation in machine learning: The legality of fairness metrics under EU non-discrimination law,

Reference 78

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f7cc17-e27f-42ad-bbe6-f0045dd5947f · outbound

This paper cites Inclusive Speaker Verification with Adaptive thresholding.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection Inclusive Speaker Verification with Adaptive thresholding

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36a2e6a9-a767-4e1a-87eb-db955ca2430a · outbound

This paper cites On fairness and calibration,.

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection On fairness and calibration,

Reference 80

Resolution: unresolved; no resolver link, observed 2026-07-14T14:47:58.592181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers