Mapa webu
- Odyssey 2020
- Keynotes (2)
- Live sessions (3)
- Tutorials (5)
- Speaker Recognition 1 (4)
- MagNetO: X-vector Magnitude Estimation Network plus Offset for Improved Speaker Recognition
- BERTphone: Phonetically-aware Encoder Representations for Utterance-level Speaker and Language Recognition
- Orthogonality Regularizations for End-to-End Speaker Verification
- Probabilistic Embeddings for Speaker Diarization
- Speaker and Language Recognition (9)
- Zero-Time Windowing Cepstral Coefficients for Dialect Classification
- Unsupervised Regularization of the Embedding Extractor for Robust Language Identification
- Compensation on x-vector for Short Utterance Spoken Language Identification
- Improving Embedding-based Neural-Network Speaker Recognition
- Information Preservation Pooling for Speaker Embedding
- Neural i-vectors
- Denoising x-vectors for Robust Speaker Recognition
- Adaptation Strategy and Clustering from Scratch for New Domains of Speaker Recognition
- Adaptive Mean Normalization for Unsupervised Adaptation of Speaker Embeddings
- Diarization (5)
- Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm
- DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team
- On Early-stop Clustering for Speaker Diarization
- Linguistically Aided Speaker Diarization Using Speaker Role Information
- Optimal Mapping Loss: A Faster Loss for End-to-End Speaker Diarization
- Spoofing and Countermeasure 1 (5)
- Generalization of Audio Deepfake Detection
- Using Multi-Resolution Feature Maps with Convolutional Neural Networks for Anti-Spoofing in ASV
- Novel Variable Length Teager Energy Profiles for Replay Spoof Detection
- An Initial Investigation on Optimizing Tandem Speaker Verification and Countermeasure Systems Using Reinforcement Learning
- Black-box Attacks on Automatic Speaker Verification using Feedback-controlled Voice Conversion
- Special Session: VOiCES 2020 (7)
- The VOiCES from a Distance Challenge 2019: Analysis of Speaker Verification Results and Remaining Challenges
- Selective Deep Speaker Embedding Enhancement for Speaker Verification
- Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances
- Utilizing VOiCES Dataset for Multichannel Speaker Verification with Beamforming
- An Empirical Analysis of Information Encoded in Disentangled Neural Speaker Representations
- NPLDA: A Deep Neural PLDA Model for Speaker Verification
- Learning Mixture Representation for Deep Speaker Embedding Using Attention
- Voice Conversion and Synthesis (6)
- Many-to-Many Voice Conversion Using Cycle-Consistent Variational Autoencoder with Multiple Decoders
- Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
- Transforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data
- Generative Adversarial Networks for Singing Voice Conversion with and without Parallel Data
- WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss
- Personalized Singing Voice Generation Using WaveRNN
- Evaluation and Benchmarking (5)
- The 2019 NIST Audio-Visual Speaker Recognition Evaluation
- The 2019 NIST Speaker Recognition Evaluation CTS Challenge
- Advances in Speaker Recognition for Telephone and Audio-Visual Data: the JHU-MIT Submission for NIST SRE19
- LEAP System for SRE 2019 CTS Challenge - Improvements and Error Analysis
- Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge
- Spoofing and Countermeasure 2 (7)
- A Multi-condition Training Strategy for Countermeasures Against Spoofing Attacks to Speaker Recognizers
- Analysis of Teager Energy Profiles for Spoof Speech Detection
- Effects of Waveform PMF on Anti-spoofing Detection for Replay Data - ASVspoof 2019
- Phase Spectrum of Time-flipped Speech Signals for Robust Spoofing Detection
- Residual Networks for Resisting Noise: Analysis of an Embeddings-based Spoofing Countermeasure
- An Explainability Study of the Constant Q Cepstral Coefficient Spoofing Countermeasure for Automatic Speaker Verification
- Subband Modeling for Spoofing Detection in Automatic Speaker Verification
- Speaker Recognition 2 (5)
- Delving into VoxCeleb: Environment Invariant Speaker Recognition
- Dropping Classes for Deep Speaker Representation Learning
- Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification
- A Speaker Verification Backend for Improved Calibration Performance across Varying Conditions
- Partial AUC Metric Learning Based Speaker Verification Back-End
- Speech Application (12)
- Joint Training End-to-End Speech Recognition Systems with Speaker Attributes
- Small Footprint Multi-channel Keyword Spotting
- Assessing Child Communication Engagement via Speech Recognition in Naturalistic Active Learning Spaces
- Exploring the Effects of Device Variability on Forensic Speaker Comparison Using VOCALISE and NFI-FRIDA, A Forensically Realistic Database
- On Open-Set Speaker Identification with I-Vectors
- Speaker Detection in the Wild: Lessons Learned from JSALT 2019
- Speaker Characterization Using TDNN, TDNN-LSTM, TDNN-LSTM-Attention based Speaker Embeddings for NIST SRE 2019
- Combined Vector Based on Factorized Time-delay Neural Network for Text-Independent Speaker Recognition
- Personal VAD: Speaker-Conditioned Voice Activity Detection
- Speech Bandwidth Expansion For Speaker Recognition On Telephony Audio
- Robust Speaker Recognition Using Speech Enhancement And Attention Model
- Analysis of Deep Feature Loss Based Enhancement for Speaker Verification
