ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks | Paper Citation Record

Observation 9e5a30ec-3594-45ef-bf92-95f36cb98e06 · outbound

This paper cites ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T13:35:26.558280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation fa8845e3-fb0b-44c2-9a41-6f4a0dfa77b1 · outbound

This paper cites However, their robustness to emotional and expressive synthetic speech remains limited.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks However, their robustness to emotional and expressive synthetic speech remains limited

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.506249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 3bc26c09-d6ba-4234-8986-db625148b079 · outbound

This paper cites Figure 1 illustrates the over- all architecture.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Figure 1 illustrates the over- all architecture

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.515130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 600e0139-d7d6-49d1-9829-5884dd95017e · outbound

This paper cites Dataset.We group data into training, standard bench- marks, and emotional/expressive benchmarks.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Dataset.We group data into training, standard bench- marks, and emotional/expressive benchmarks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.523770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation edebf2f0-0267-41a5-88d4-af1ef1a0dcc9 · outbound

This paper cites w/o MP- SI.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks w/o MP- SI

Reference 5

Resolution: malformed identifier; raw_fallback, observed 2026-05-18T23:42:53.498498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 1fa00bee-772a-46be-b9eb-61487b2660a1 · outbound

This paper cites an unresolved cited work.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Unresolved cited work

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.534458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation ac5a5d5e-df16-4948-ba37-5b1902697db2 · outbound

This paper cites • The Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via the ARTS Program, Contract #D2023-2308110001.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks • The Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via the ARTS Program, Contract #D2023-2308110001

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.531000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation dbc9ff40-8bd3-40f9-abf1-01701a1524b8 · outbound

This paper cites These tools were not used to generate scientific content, results, experimental designs, anal- yses, or conclusions.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks These tools were not used to generate scientific content, results, experimental designs, anal- yses, or conclusions

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.520063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation a73089cb-c7d0-4555-9d1d-7e0253229f02 · outbound

This paper cites Battling voice spoofing: a review, comparative analysis, and generalizability evaluation of state-of-the-art voice spoofing counter measures.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Battling voice spoofing: a review, comparative analysis, and generalizability evaluation of state-of-the-art voice spoofing counter measures

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.510845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 928da945-d534-4a2a-b934-cf187dddc1f4 · outbound

This paper cites A survey on speech deep- fake detection.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks A survey on speech deep- fake detection

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.501779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation ed2ec76b-78e1-48da-9e9f-4ebfd0cfaaa1 · outbound

This paper cites Can emotion fool anti-spoofing?.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Can emotion fool anti-spoofing?

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.527167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation b59ca0d8-09f4-4174-a8f3-ed06fe72d2b5 · outbound

This paper cites Emofake: An initial dataset for emotion fake audio detection.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Emofake: An initial dataset for emotion fake audio detection

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.192306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 2a1bd8ef-ed14-4851-9a14-8de1620b4f74 · outbound

This paper cites Mlaad: The multi- language audio anti-spoofing dataset.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Mlaad: The multi- language audio anti-spoofing dataset

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.196437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 242f3cd2-e8e7-46e8-8136-ca5dc167f9bb · outbound

This paper cites Does audio deep- fake detection generalize?.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Does audio deep- fake detection generalize?

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.578566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 393d1e49-c82a-4598-a107-2eeab94a2383 · outbound

This paper cites Asvspoof 2015: Automatic speaker verification spoofing and countermea- sures challenge evaluation plan.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Asvspoof 2015: Automatic speaker verification spoofing and countermea- sures challenge evaluation plan

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.200338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation b933451b-d9a4-4ba2-ac57-959cd180f315 · outbound

This paper cites Add 2022: the first audio deep synthe- sis detection challenge.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Add 2022: the first audio deep synthe- sis detection challenge

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.185414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 3d7f83b2-38dd-4b09-91cd-cc247db8de29 · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks ADD 2023: the Second Audio Deepfake Detection Challenge

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.576142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 9ca82b15-c04d-498d-a882-61009eb9c5a6 · outbound

This paper cites Asvspoof 2019: A large-scale public database of synthesized, converted and replayed speech.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Asvspoof 2019: A large-scale public database of synthesized, converted and replayed speech

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.181517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 28c20390-ca0b-425e-abd3-682a2cb18a23 · outbound

This paper cites Asvspoof 2021: Towards spoofed and deepfake speech de- tection in the wild.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Asvspoof 2021: Towards spoofed and deepfake speech de- tection in the wild

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.204343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation bf630327-c7e9-4765-9adb-7790f3137f51 · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.555145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 3be9227f-bb8f-4b04-9eaf-9eed07129820 · outbound

This paper cites Hula: Prosody-aware anti-spoofing with multi-task learning for expressive and emo- tional synthetic speech.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Hula: Prosody-aware anti-spoofing with multi-task learning for expressive and emo- tional synthetic speech

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.581251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 840dd24c-b01e-4bfd-a416-7f56e13ab105 · outbound

This paper cites End-to-end anti-spoofing with rawnet2.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks End-to-end anti-spoofing with rawnet2

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.248236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation b500f070-cda1-4d01-821b-ea1f94b98bcb · outbound

This paper cites Aasist: Audio anti-spoofing using in- tegrated spectro-temporal graph attention networks.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Aasist: Audio anti-spoofing using in- tegrated spectro-temporal graph attention networks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.241790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation fad7278b-d9c8-4504-a1fc-0d994fb57727 · outbound

This paper cites Light Convolutional Neural Network with Feature Genuinization for Detection of Synthetic Speech Attacks.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Light Convolutional Neural Network with Feature Genuinization for Detection of Synthetic Speech Attacks

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.560856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation a2274403-6905-4a7a-9251-299eb359c147 · outbound

This paper cites ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-04T23:31:23.938248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation bdc9491d-f8c3-4f5d-a6fe-96feba97124e · outbound

This paper cites Spoof detection using voice contribution on lfcc features and resnet-34.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Spoof detection using voice contribution on lfcc features and resnet-34

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.174471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 12161f26-616b-4891-8e62-a1ea1f255381 · outbound

This paper cites Audio deepfake detection with self-supervised xls-r and sls classifier.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Audio deepfake detection with self-supervised xls-r and sls classifier

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.167451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 015e6f13-537d-4af5-a3a5-92adc3cc21cc · outbound

This paper cites Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.573529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 671f2b13-b9ff-49f7-a151-da80a7cc0bc6 · outbound

This paper cites Pitch Imperfect: Detecting Audio Deepfakes Through Acoustic Prosodic Analysis.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Pitch Imperfect: Detecting Audio Deepfakes Through Acoustic Prosodic Analysis

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.568518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation bbb14465-e56f-461b-a0df-1c215310babf · outbound

This paper cites Deepfake speech detection through emotion recognition: a semantic approach.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Deepfake speech detection through emotion recognition: a semantic approach

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.208615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 57438390-3ff0-4e05-aa76-82f55845c8ee · outbound

This paper cites Combining automatic speaker verification and prosody analysis for synthetic speech detection.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Combining automatic speaker verification and prosody analysis for synthetic speech detection

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.224601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 01ad08ff-6181-4303-a8bd-0189ccb577c5 · outbound

This paper cites Emoanti: audio anti-deepfake with refined emotion-guided representations.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Emoanti: audio anti-deepfake with refined emotion-guided representations

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.563364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 73762340-e2a6-4ecf-b83e-1faa23b50e64 · outbound

This paper cites Finding the human voice in ai: Insights on the perception of ai-voice clones from naturalness and similarity ratings.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Finding the human voice in ai: Insights on the perception of ai-voice clones from naturalness and similarity ratings

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.920779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 0c3a64e5-1e0d-4d29-bc57-c7c0f8c87c2f · outbound

This paper cites How do users perceive deepfake personas? investigating the deepfake user perception and its implications for human-computer interaction.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks How do users perceive deepfake personas? investigating the deepfake user perception and its implications for human-computer interaction

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.177907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 2140a1b0-8c36-4d10-bc5b-381f17429400 · outbound

This paper cites Subjective perception and objective evaluation of speech naturalness for deepfake de- tection.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Subjective perception and objective evaluation of speech naturalness for deepfake de- tection

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.188964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 3ee59924-101a-4b2b-87ff-323db7403872 · outbound

This paper cites Slim: Style- linguistics mismatch model for generalized audio deepfake de- tection.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Slim: Style- linguistics mismatch model for generalized audio deepfake de- tection

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.212073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation d5dbffa9-4e17-4953-ab22-09fdd7bae1de · outbound

This paper cites Xlsr-mamba: A dual-column bidirec- tional state space model for spoofing attack detection.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Xlsr-mamba: A dual-column bidirec- tional state space model for spoofing attack detection

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.164218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 052237ae-9d05-4f3c-a2d9-3577ec4b9dd0 · outbound

This paper cites Emoq-tts: Emo- tion intensity quantization for fine-grained controllable emotional text-to-speech.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Emoq-tts: Emo- tion intensity quantization for fine-grained controllable emotional text-to-speech

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.171036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation b92da716-8065-4bed-a6e7-c43f7f96c450 · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Glow-tts: A genera- tive flow for text-to-speech via monotonic alignment search

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.227948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 31716ffd-6c08-48dd-8ef0-3fc45e234fff · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:06:41.789827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation b2fb1132-7212-40c9-af15-6d2580d91af1 · outbound

This paper cites Laugh now cry later: Controlling time-varying emotional states of flow- matching-based zero-shot text-to-speech.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Laugh now cry later: Controlling time-varying emotional states of flow- matching-based zero-shot text-to-speech

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.917060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 55e3a807-585b-49e7-885c-4ba31c08ebbd · outbound

This paper cites Expressive-vc: Highly expressive voice conversion with attention fusion of bottleneck and perturbation features.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Expressive-vc: Highly expressive voice conversion with attention fusion of bottleneck and perturbation features

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.912626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 633a179e-f38f-4f57-8af6-9cbf59eba136 · outbound

This paper cites Pmvc: Data augmentation-based prosody modeling for expres- sive voice conversion.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Pmvc: Data augmentation-based prosody modeling for expres- sive voice conversion

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.892948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 777c5018-b016-4396-ae66-aad89045a20b · outbound

This paper cites Emotion intensity and its control for emotional voice conversion.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Emotion intensity and its control for emotional voice conversion

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.913946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 380ef486-5941-4d03-a4a5-6250cd6b7d04 · outbound

This paper cites Prosody in context: A review.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Prosody in context: A review

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.910436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 09544bd3-e124-44f6-b076-9a9488216683 · outbound

This paper cites Learning second language suprasegmentals: Effect of l2 experience on prosody and fluency characteristics of l2 speech.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Learning second language suprasegmentals: Effect of l2 experience on prosody and fluency characteristics of l2 speech

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.255490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation b76087d9-f571-42bf-bc05-57d30c81fa6d · outbound

This paper cites Variation adds to prosodic typology.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Variation adds to prosodic typology

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.245021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 3d969383-0453-441d-9a95-354b1554956f · outbound

This paper cites De- tection of cross-dataset fake audio based on prosodic and pronun- ciation features.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks De- tection of cross-dataset fake audio based on prosodic and pronun- ciation features

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.258289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 5102fd9d-21e6-4e6f-b8d6-da0725afe8e6 · outbound

This paper cites Investigating voiced and unvoiced regions of speech for audio deepfake detection.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Investigating voiced and unvoiced regions of speech for audio deepfake detection

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.231335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation ec33642e-90b0-4553-81f2-ef65d3ca2879 · outbound

This paper cites ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.583962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation d7cc8f92-7129-4540-b693-18d5efae5d6b · outbound

This paper cites Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.588829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation a20fb279-f4d5-44e9-96f6-7e1bef465366 · outbound

This paper cites Lib- rispeech: An asr corpus based on public domain audio books.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Lib- rispeech: An asr corpus based on public domain audio books

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.234450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 5c22e4d0-4c19-4604-aa1f-f28ffa50fee2 · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.238562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 00793784-0913-4347-8e8e-541819072528 · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.593634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 0b696d15-adca-4e7b-98ae-2e8e87af26f6 · outbound

This paper cites Fastpitch: Parallel text-to-speech with pitch pre- diction.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Fastpitch: Parallel text-to-speech with pitch pre- diction

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.251350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 75f0f241-0cf5-4b66-8675-6f332dbaf7d8 · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Grad-tts: A diffusion probabilistic model for text-to-speech

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:42:53.907462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation bc491533-8746-43ae-8f01-dc89efd8725c · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.591203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 34b47704-6210-4aa4-804a-daf81940ccf7 · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:35:26.586414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 38084b70-c446-401f-9eac-34132e3ef105 · outbound

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

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks V oice conversion using speech-to- speech neuro-style transfer

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.215566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Observation 2ff81406-0527-4ac5-b4f9-22bc14076e05 · outbound

This paper cites Raw- boost: A raw data boosting and augmentation method applied to automatic speaker verification anti-spoofing.

ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks Raw- boost: A raw data boosting and augmentation method applied to automatic speaker verification anti-spoofing

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T23:41:56.218897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-27T06:30:09.085275+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers