Sitemap
- Odyssey 2014
- Keynotes (3)
- Opening & Closing (2)
- Calibration, Evaluation & Forensics (4)
- Effects of the New Testing Paradigm of the 2012 NIST Speaker Recognition Evaluation
- NFI-FRITS: A forensic speaker recognition database and some first experiments
- A comparison of linear and non-linear calibrations for speaker recognition
- Trial-based Calibration for Speaker Recognition in Unseen Conditions
- Speaker Modeling I (4)
- Discriminative PLDA training with application-specific loss functions for speaker verification
- What are we missing with i-vectors? A perceptual analysis of i-vector-based falsely accepted trials
- Exploring some limits of Gaussian PLDA modeling for i-vector distributions
- GMM Weights Adaptation Based on Subspace Approaches for Speaker Verification
- Language Recognition (4)
- Speaker Diarization (4)
- Text-dependent Speaker Recognition (3)
- Nist I-Vector Special Session (5)
- The NIST 2014 Speaker Recognition i-vector Machine Learning Challenge
- STC Speaker Recognition System for the NIST i-Vector Challenge
- Incorporating Duration Information into I-Vector-Based Speaker Recognition Systems
- Linearly Constrained Minimum Variance for Robust I-vector Based Speaker Recognition
- Hierarchical speaker clustering methods for the NIST i-vector Challenge
- Speaker Modeling II (4)
- Neural Nets for Speaker and Language Modeling (4)
- Application of Convolutional Neural Networks to Language Identification in Noisy Conditions
- Deep Neural Networks for extracting Baum-Welch statistics for Speaker Recognition
- Neural Network Bottleneck Features for Language Identification
- i-Vector Modeling with Deep Belief Networks for Multi-Session Speaker Recognition
