Paper Citation Record · LEDGER

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset

As of 19 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2505.10885.

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

pith.paper-citation-record.v1
2505.10885 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:05:30.006687Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:05:29.840446Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T21:05:30.216088Z

Reference resolution

35 of 35 outbound references displayed

verified exact3
verified fuzzy13
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 69b8143c-7172-4f6b-92f6-5da069959a22 · outbound

This paper cites Auto- matic speaker verification (ASV) tools, widely used for bio- metric identification, are increasingly vulnerable to spoofing at- tacks, particularly deepfake audios.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Auto- matic speaker verification (ASV) tools, widely used for bio- metric identification, are increasingly vulnerable to spoofing at- tacks, particularly deepfake audios

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.510553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 06be47ec-fc50-4cc2-b352-3f58fdfd18e6 · outbound

This paper cites BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T21:05:30.221572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9d0c11b7-5c85-4e86-bbad-8e091623fdf7 · outbound

This paper cites an unresolved cited work.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:05:30.497138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 55a3a4af-aee4-42a3-9249-6dc191b42a7b · outbound

This paper cites Later we explain how we used the trained model to create the Bangla Deepfake audio dataset.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Later we explain how we used the trained model to create the Bangla Deepfake audio dataset

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.482766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d912126e-c122-440a-9c1e-2040580c0d75 · outbound

This paper cites Figure 2: t-SNE visualization of MFCC features for real and deepfake audio samples.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Figure 2: t-SNE visualization of MFCC features for real and deepfake audio samples

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.467155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fa2cfd5f-ba6f-4181-b24c-30a5e4c00848 · outbound

This paper cites an unresolved cited work.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:05:30.453830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6d67fa83-f926-435c-86d2-b7406f1239c8 · outbound

This paper cites The average Robust-MOS scores for these questions were 3.40, and 4.01, respectively.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset The average Robust-MOS scores for these questions were 3.40, and 4.01, respectively

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.439842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fa6b1548-6a78-4384-8c5a-09d8ef28eec3 · outbound

This paper cites an unresolved cited work.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:05:30.426847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cf0e9587-9fc0-4639-9295-b2df22cb9c85 · outbound

This paper cites Deepfakes: What are they and why would i make one?.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Deepfakes: What are they and why would i make one?

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.413587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c18de0bd-7b54-4e9e-9d4d-fc921da6e67e · outbound

This paper cites Dataset pruning for resource-constrained spoofed audio detection,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Dataset pruning for resource-constrained spoofed audio detection,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.398194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b9a54dcd-9401-4221-aa68-ef7de98174b9 · outbound

This paper cites Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-15T21:05:30.202974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6b93324c-a809-4013-a7d9-6383c6f8e5cb · outbound

This paper cites An introduction to variational autoencoders,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset An introduction to variational autoencoders,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.383110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 20a9c11d-27f6-41ef-b3ee-57cebb53c98f · outbound

This paper cites Fastspeech: Fast, robust and controllable text to speech,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Fastspeech: Fast, robust and controllable text to speech,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.900172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd062871-c34d-4945-8d80-45fec1d4be74 · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.904729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc36593-3922-4757-963e-7eef389e9aeb · outbound

This paper cites Zmm-tts: Zero-shot multi- lingual and multispeaker speech synthesis conditioned on self- supervised discrete speech representations,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Zmm-tts: Zero-shot multi- lingual and multispeaker speech synthesis conditioned on self- supervised discrete speech representations,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.353681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6e62bde8-ef28-48e6-9b18-934b9b67b312 · outbound

This paper cites Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-15T21:05:30.183894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3bab4df1-a9eb-4c6d-9a19-b3cd268f8bdf · outbound

This paper cites Asvspoof 2021: accelerating progress in spoofed and deep- fake speech detection,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Asvspoof 2021: accelerating progress in spoofed and deep- fake speech detection,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.920446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f05207e-7580-424a-b9b1-67e4adceedf7 · outbound

This paper cites ADD 2023: the Second Audio Deepfake Detection Challenge.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset ADD 2023: the Second Audio Deepfake Detection Challenge

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.925126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d71c1d-5b2a-4740-8af4-83451e2d4d3a · outbound

This paper cites Comparative Analysis of Transfer Learning in Deep Learning Text-to-Speech Models on a Few-Shot, Low-Resource, Customized Dataset.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Comparative Analysis of Transfer Learning in Deep Learning Text-to-Speech Models on a Few-Shot, Low-Resource, Customized Dataset

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-15T21:05:30.147672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f6bbe83a-5d51-4762-a87c-23a7186b6d4a · outbound

This paper cites FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.936338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d982a4d-dd04-43fe-aefa-9a157736cb05 · outbound

This paper cites LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.941207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f28b4e50-e54e-4914-9f46-e38c04a1701d · outbound

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

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.946026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e69b3f1-9967-4f29-a24c-7bec2826ece7 · outbound

This paper cites Sust tts corpus: A phonetically-balanced corpus for bangla text-to-speech synthe- sis,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Sust tts corpus: A phonetically-balanced corpus for bangla text-to-speech synthe- sis,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.332904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 450938a1-a4ec-452c-898c-6109b589d405 · outbound

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

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Common voice: A massively-multilingual speech corpus,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.954912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 645aab21-c499-4830-bfed-09b8e3949e85 · outbound

This paper cites Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.959394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57541036-3cd9-4715-bcf0-1a4ee5db4acc · outbound

This paper cites The lj speech dataset,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset The lj speech dataset,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.963940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fdfbc13-05c2-4ede-8623-14b204f9ec04 · outbound

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

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.968102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cef3d5ab-fc46-4b03-b321-45170fb9226a · outbound

This paper cites An Introduction to Variational Inference.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset An Introduction to Variational Inference

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.972115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2f9da2c-ced7-4776-9c19-ca9d760721cb · outbound

This paper cites Glow-tts: A genera- tive flow for text-to-speech via monotonic alignment search,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Glow-tts: A genera- tive flow for text-to-speech via monotonic alignment search,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.979037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2404488-d71a-4cd8-8dde-72a9e6a2793f · outbound

This paper cites Short term spectral analysis, synthesis, and modification by discrete fourier transform,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Short term spectral analysis, synthesis, and modification by discrete fourier transform,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.285898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 88139a42-b6ec-442b-b243-c8efde9b1854 · outbound

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

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Hifi-gan: Generative adversarial net- works for efficient and high fidelity speech synthesis,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.988258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43806927-28f0-4c00-9566-ca0afdd2e2f7 · outbound

This paper cites Flow++: Improving flow-based generative models with variational dequan- tization and architecture design,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Flow++: Improving flow-based generative models with variational dequan- tization and architecture design,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.263217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 82316559-1591-44cc-ae74-77695ac532a4 · outbound

This paper cites Common Voice: A Massively-Multilingual Speech Corpus.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Common Voice: A Massively-Multilingual Speech Corpus

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:29.997915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84bc5763-7635-40ca-8ba0-d5b2937249e4 · outbound

This paper cites Mean opinion score (mos) revis- ited: methods and applications, limitations and alternatives,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Mean opinion score (mos) revis- ited: methods and applications, limitations and alternatives,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.249399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0c3b493b-2a03-48bb-afa6-08217f9e5a99 · outbound

This paper cites Visualizing data using t-sne,.

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Visualizing data using t-sne,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:30.235735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 06be47ec-fc50-4cc2-b352-3f58fdfd18e6 · inbound