Výsledky vyhledávání - "Voice conversion"

Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters

Autoři: Abrassart, Mathilde Obin, Nicolas Roebel, Axel

Přispěvatelé: Abrassart, Mathilde Obin, Nicolas Roebel, Axel

Zdroj: 13th edition of the Speech Synthesis Workshop. :181-188

Témata: Controllability, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], FOS: Computer and information sciences, Sound (cs.SD), [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO] Computer Science [cs], Durations Control, [INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD], Pitch, Sound, Artificial Intelligence (cs.AI), Artificial Intelligence, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Phonemes Control, Speech Synthesis, Audio and Speech Processing, Voice conversion

Popis souboru: application/pdf

Přístupová URL adresa: http://arxiv.org/abs/2507.04817
https://hal.science/hal-05148026v1

VoiceQualityVC: A Voice Conversion System for Studying the Perceptual Effects of Voice Quality in Speech

Autoři: Lameris, Harm Gustafsson, Joakim, Professor Székely, Éva

Zdroj: Interspeech 2025. :2295-2299

Témata: Paralinguistics, Pragmatics, Voice conversion, Voice quality

Popis souboru: print

Přístupová URL adresa: https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-372784
https://doi.org/10.21437/Interspeech.2025-902

Accent conversion method with real-time voice cloning based on a nonautoregressive neural network model

Autoři: V. A. Nechaev S. V. Kosyakov

Zdroj: Российский технологический журнал, Vol 13, Iss 3, Pp 7-20 (2025)

Témata: machine learning, Information theory, speech synthesis, voice conversion, neural network, accent conversion, text-to-speech, Q350-390

Přístupová URL adresa: https://doaj.org/article/be956bcefc684296b8f8ceb69f6e22ac

ICRCycleGAN-VC: a robust one-to-one voice conversion method based on CycleGAN and inception-ResNet blocks

Autoři: Nayereh Seyed Afiuny Amir Lakizadeh

Zdroj: EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-14 (2025)

Témata: Voice conversion (VC), Deep learning, Non-parallel VC, Inception module, Cycle-consistent adversarial network, CycleGAN-VC, Acoustics. Sound, QC221-246, Electronic computers. Computer science, QA75.5-76.95

Popis souboru: electronic resource

Relation: https://doaj.org/toc/1687-4722

Přístupová URL adresa: https://doaj.org/article/0b6322f310b54eb4a1936542ec9a981f

DeepLASD countermeasure for logical access audio spoofing

Autoři: Hamed Al-Tairi Ali Javed Tasawer Khan a další

Zdroj: Scientific Reports, Vol 15, Iss 1, Pp 1-10 (2025)

Témata: Automatic speaker verification, Deep learning, Logical access attacks, Spoof detection, Text-to-speech synthesis, Voice conversion, Medicine, Science

Popis souboru: electronic resource

Relation: https://doaj.org/toc/2045-2322

Přístupová URL adresa: https://doaj.org/article/a172e9dc5ce24e4cb616b8d446964545

The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation

Autoři: Michele Panariello Natalia Tomashenko Xin Wang a další

Přispěvatelé: Michele Panariello Natalia Tomashenko Xin Wang a další

Zdroj: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 32:3477-3491

Témata: anonymisation, voice conversion, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, attack model, 16. Peace & justice, 7. Clean energy, 3. Good health, speech synthesis, Audio and Speech Processing (eess.AS), 13. Climate action, voice privacy, anonymisation pseudonymisation voice privacy speech synthesis voice conversion attack model, FOS: Electrical engineering, electronic engineering, information engineering, pseudonymisation, 10. No inequality, Electrical Engineering and Systems Science - Audio and Speech Processing

Popis souboru: application/pdf

Přístupová URL adresa: http://arxiv.org/abs/2407.11516
https://inria.hal.science/hal-04667625v1
https://inria.hal.science/hal-04667625v1/document
https://doi.org/10.1109/taslp.2024.3430530

Voice Synthesis, Transformations, and Sound Effects: A portfolio

Autoři: Erkut, Cumhur

Zdroj: Erkut, C 2025, 'Voice Synthesis, Transformations, and Sound Effects: A portfolio', DAS|DAGA 2025-51st Annual Meeting on Acoustics, Copenhagen, Denmark, 17/03/2025-20/03/2025.

Témata: Deep Learning, voice conversion, name=SDG 9 - Industry, Innovation, and Infrastructure

Popis souboru: application/pdf

Přístupová URL adresa: https://vbn.aau.dk/ws/files/790701108/DASDAGA25-Poster-Erkut.pdf
https://vbn.aau.dk/da/publications/1f41c45c-2825-489c-9a3b-ed6411782702

Singing to speech conversion with generative flow

Autoři: Jiawen Huang Emmanouil Benetos

Zdroj: EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-14 (2025)

Témata: Singing voice conversion, Generative flow, Duration manipulation, Lyrics transcription, Phonetic similarity, Acoustics. Sound, QC221-246, Electronic computers. Computer science, QA75.5-76.95

Popis souboru: electronic resource

Relation: https://doaj.org/toc/1687-4722

Přístupová URL adresa: https://doaj.org/article/031d827b01ef45809ff133741233af54

Spectro-Temporal-CNN Fusion for Deepfake Speech Detection and Spoof System Attribution

Autoři: Zuhal Can Buket Soyhan

Zdroj: IEEE Access, Vol 13, Pp 185802-185817 (2025)

Témata: Convolutional neural networks, deepfake audio detection, ensemble classification, spectro-temporal features, speech synthesis, voice conversion, Electrical engineering. Electronics. Nuclear engineering, TK1-9971

Popis souboru: electronic resource

Relation: https://ieeexplore.ieee.org/document/11218048/; https://doaj.org/toc/2169-3536

Přístupová URL adresa: https://doaj.org/article/1aadaf5bfeaa4b9cb6b6f3a6484880f4

The Application of Generative Artificial Intelligence Technology in Voice Conversion

Autoři: Anon Bangsan

Témata: Generative Artificial Intelligence, Cyber Warfare, Voice Conversion, Generative Adversarial Network

STRAIGHTMORPH: A Voice Morphing Tool for Research in Voice Communication Sciences [version 2; peer review: 2 approved, 1 approved with reservations]

Autoři: P Belin H Kawahara

Zdroj: Open Research Europe, Vol 4 (2025)

Témata: eng, voice, voice conversion, morphing, voice identity, voice affect, animal vocalizations, Science, Social Sciences

Přístupová URL adresa: https://doaj.org/article/78543e58191a4dcab0f54afcdb62c30d

A noise-robust voice conversion method with controllable background sounds

Autoři: Lele Chen Xiongwei Zhang Yihao Li a další

Zdroj: Complex & Intelligent Systems, Vol 10, Iss 3, Pp 3981-3994 (2024)

Témata: Dual-decoder structure, Noise-robust voice conversion, Electronic computers. Computer science, 0103 physical sciences, Cycle loss, 0202 electrical engineering, electronic engineering, information engineering, QA75.5-76.95, Information technology, 02 engineering and technology, Bridge module, T58.5-58.64, 01 natural sciences, Speech disentanglement

Přístupová URL adresa: https://doaj.org/article/7aa48dec97f54bab9a1585965cf39cdd

Joint Speech-Text Embeddings for Multitask Speech Processing

Autoři: Michael Gian Gonzales Peter Corcoran Naomi Harte a další

Přispěvatelé: Michael Gian Gonzales Peter Corcoran Naomi Harte a další

Zdroj: IEEE Access, Vol 12, Pp 145955-145967 (2024)

Témata: joint speech-text, voice conversion, speaker recognition, Automatic speech recognition, Electrical engineering. Electronics. Nuclear engineering, text-to-speech, TK1-9971, speech processing

Popis souboru: application/pdf

Přístupová URL adresa: https://doaj.org/article/351d1fbfd3be4abfa53e00946ba37d3e
https://hdl.handle.net/10379/18466
https://doi.org/10.13025/29260

A hybrid CNN-LSTM model with adaptive instance normalization for one shot singing voice conversion

Autoři: Assila Yousuf David Solomon George

Zdroj: AIMS Electronics and Electrical Engineering, Vol 8, Iss 3, Pp 282-300 (2024)

Témata: hybrid cnn-lstm model, again, one-shot singing voice conversion, instance normalization, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, 01 natural sciences, adain, TK1-9971

Přístupová URL adresa: https://doaj.org/article/84c69169f5174828a94a2c30d3f3298c

Streaming ASR Encoder for Whisper-to-Speech Online Voice Conversion

Autoři: Anastasia Avdeeva Aleksei Gusev Tseren Andzhukaev a další

Zdroj: IEEE Open Journal of Signal Processing, Vol 5, Pp 160-167 (2024)

Témata: voice conversion, disordered speech, whisper-to-speech processing, 05 social sciences, 0501 psychology and cognitive sciences, Electrical engineering. Electronics. Nuclear engineering, Speech recognition, 0503 education, TK1-9971

Přístupová URL adresa: https://doaj.org/article/30407658f0b24a5ab22ec7c860caed63

Hear Me Out: Interactive evaluation and bias discovery platform for speech-to-speech conversational AI

Autoři: Bokkahalli Satish, Shree Harsha Henter, Gustav Eje, Assistant Professor Székely, Éva

Zdroj: Interspeech 2025. :2151-2152

Témata: bias in conversational AI, speech-to-speech conversational AI, voice conversion

Popis souboru: print

Přístupová URL adresa: https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-372786
https://www.isca-archive.org/interspeech_2025/bokkahallisatish25_interspeech.html

Audio Deepfake Detection:What Has Been Achieved and What Lies Ahead

Autoři: Zhang, Bowen Cui, Hui Nguyen, Van a další

Zdroj: Zhang, B, Cui, H, Nguyen, V & Whitty, M 2025, 'Audio Deepfake Detection : What Has Been Achieved and What Lies Ahead', Sensors, vol. 25, no. 7, 1989. https://doi.org/10.3390/s25071989

Témata: audio deepfake detection, survey, text to speech (TTS), voice conversion (VC)

Popis souboru: application/pdf

Dostupnost: https://research.monash.edu/en/publications/9c6cffb8-77b7-4ff2-b7cf-509725a7c869
https://doi.org/10.3390/s25071989
https://researchmgt.monash.edu/ws/files/725098090/687212443-oa.pdf
http://www.scopus.com/inward/record.url?scp=105002282696&partnerID=8YFLogxK

Advancements in End-to-End Audio Style Transformation: A Differentiable Approach for Voice Conversion and Musical Style Transfer

Autoři: Shashwat Aggarwal Shashwat Uttam Sameer Garg a další

Zdroj: AI ; Volume 6 ; Issue 1 ; Pages: 16

Témata: voice conversion, musical style transfer, audio transformations, end-to-end audio pipeline

Popis souboru: application/pdf

Relation: https://dx.doi.org/10.3390/ai6010016

Dostupnost: https://doi.org/10.3390/ai6010016

Interpretable Latent Space Using Space-Filling Curves for Phonetic Analysis in Voice Conversion

Autoři: Vali, Mohammadhassan Bäckström Tom

Zdroj: Interspeech. :306-310

Témata: ta113, space-filling curves, vector quantization, voice conversion, phonetic analysis, Interpretable latent space

Přístupová URL adresa: http://juuli.fi/Record/0676569223

Robust Disentangled Variational Speech Representation Learning for Zero-Shot Voice Conversion

Autoři: Lian, Jiachen Zhang, Chunlei Yu, Dong

Témata: Self-supervised Disentangled representation learning, zero-shot style transfer, voice conversion, variational autoencoder

Popis souboru: application/pdf

Přístupová URL adresa: https://escholarship.org/uc/item/6dh2h056
https://escholarship.org/content/qt6dh2h056/qt6dh2h056.pdf