Latest

• Speech generation for indigenous language education
• Improving curriculum learning for target speaker extraction with synthetic speakers
• Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion
• The VoiceMOS Challenge 2024: Beyond Speech Quality Prediction
• Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion
• Spoofing-Aware Speaker Verification Robust Against Domain and Channel Mismatches
• A Preliminary Case Study on Long-Form In-the-Wild Audio Spoofing Detection
• Quantifying Source Speaker Leakage in One-to-One Voice Conversion
• Exploring Active Data Selection Strategies for Continuous Training in Deepfake Detection
• ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale
• Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis
• An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios
• Generating Speakers by Prompting Listener Impressions for Pre-trained Multi-Speaker Text-to-Speech Systems
• Spoof Diarization:" What Spoofed When" in Partially Spoofed Audio
• Target Speaker Extraction with Curriculum Learning
• To what extent can ASV systems naturally defend against spoofing attacks?
• Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?
• DDSP-based Neural Waveform Synthesis of Polyphonic Guitar Performance from String-wise MIDI Input
• SPOOFING ATTACK AUGMENTATION: CAN DIFFERENTLY-TRAINED ATTACK MODELS IMPROVE GENERALISATION?
• SynVox2: Towards a privacy-friendly VoxCeleb2 dataset
• Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction
• A review on subjective and objective evaluation of synthetic speech
• Analysis of Fine-Grained Counting Methods for Masked Face Counting: A Comparative Study
• Bridging Textual and Tabular Worlds for Fact Verification: A Lightweight, Attention-Based Model
• eKYC-DF: A Large-Scale Deepfake Dataset for Developing and Evaluating eKYC Systems
• Partial Rank Similarity Minimization Method for Quality MOS Prediction of Unseen Speech Synthesis Systems in Zero-Shot and Semi-supervised setting
• The VoiceMOS Challenge 2023:Zero-shot Subjective Speech Quality Prediction for Multiple Domains
• XFEVER: Exploring Fact Verification across Languages
• Speaker Anonymization Using Orthogonal Householder Neural Network
• How Close are Other Computer Vision Tasks to Deepfake Detection?
• Controlling Multi-Class Human Vocalization Generation via a Simple Segment-based Labeling Scheme
• Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms
• Investigating Range-Equalizing Bias in Mean Opinion Score Ratings of Synthesized Speech
• Range-Based Equal Error Rate for Spoof Localization
• Towards Single Integrated Spoofing-aware Speaker Verification Embeddings
• Exploring Isolated Musical Notes as Pre-training Data for Predominant Instrument Recognition in Polyphonic Music
• BodyFormer: Semantics-Guided 3D Body Gesture Synthesis with Transformer
• Revisiting Pathologies of Neural Models under Input Reduction
• ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
• Analysis of Master Vein Attacks on Finger Vein Recognition Systems
• Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?
• Hiding Speaker’s Sex in Speech Using Zero-Evidence Speaker Representation in an Analysis/Synthesis Pipeline
• Joint Noise Reduction and Listening Enhancement for Full-End Speech Enhancement
• Spoofed Training Data for Speech Spoofing Countermeasure Can Be Efficiently Created Using Neural Vocoders
• Cyber Vaccine for Deepfake Immunity
• Investigating Active-Learning-Based Training Data Selection for Speech Spoofing Countermeasure
• Speaker-Text Retrieval via Contrastive Learning
• The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance
• ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations
• Outlier-Aware Training for Improving Group Accuracy Disparities
• A Practical Guide to Logical Access Voice Presentation Attack Detection
• Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditions
• Attention Back-End for Automatic Speaker Verification with Multiple Enrollment Utterances
• Automatic Speaker Verification Spoofing and Deepfake Detection Using Wav2vec 2.0 and Data Augmentation
• Capsule-Forensics Networks for Deepfake Detection
• DDS: A new device-degraded speech dataset for speech enhancement
• Estimating the Confidence of Speech Spoofing Countermeasure
• Future Trends in Digital Face Manipulation and Detection
• Generalization Ability of MOS Prediction Networks
• Investigating Self-Supervised Front Ends for Speech Spoofing Countermeasures
• Language-Independent Speaker Anonymization Approach Using Self-Supervised Pre-Trained Models
• Master Face Attacks on Face Recognition Systems
• Mitigating the Diminishing Effect of Elastic Weight Consolidation
• On the Interplay between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
• Optimizing Tandem Speaker Verification and Anti-Spoofing Systems
• Robust Deepfake on Unrestricted Media: Generation and Detection
• Spoofing-Aware Attention based ASV Back-end with Multiple Enrollment Utterances and a Sampling Strategy for the SASV Challenge 2022
• SVSNet: An End-to-End Speaker Voice Similarity Assessment Model
• The VoiceMOS Challenge 2022
• The VoicePrivacy 2020 Challenge: Results and findings
• Use of Speaker Recognition Approaches for Learning and Evaluating Embedding Representations of Musical Instrument Sounds
• A Multi-Level Attention Model for Evidence-Based Fact Checking
• A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection
• An Initial Investigation for Detecting Partially Spoofed Audio
• ASVspoof 2019: Spoofing Countermeasures for the Detection of Synthesized, Converted and Replayed Speech
• ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
• Benchmarking and challenges in security and privacy for voice biometrics
• Denoising-and-Dereverberation Hierarchical Neural Vocoder for Robust Waveform Generation
• Effectiveness of Detection-based and Regression-based Approaches for Estimating Mask-Wearing Ratio
• Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model
• Exploring Disentanglement with Multilingual and Monolingual VQ-VAE
• How do Voices from Past Speech Synthesis Challenges Compare Today?
• How Similar or Different is Rakugo Speech Synthesizer to Professional Performers?
• Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm
• Multi-Metric Optimization Using Generative Adversarial Networks for Near-End Speech Intelligibility Enhancement
• Multi-task Learning in Utterance-level and Segmental-level Spoof Detection
• OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild
• Revisiting Speech Content Privacy
• Text-to-Speech Synthesis Techniques for MIDI-to-Audio Synthesis
• Introduction to Voice Presentation Attack Detection and Recent Advances
• User Generated Dialogue Systems: uDialogue
• Speaker Recognition Anti-spoofing
• Building personalized synthetic voices for individuals with dysarthria using the HTS toolkit
• A review on subjective and objective evaluation of synthetic speech