Sitemap
- Odyssey 2016
- Keynotes (3)
- Text Dependent Speaker Verification (4)
- A Low-Power Text-Dependent Speaker Verification System with Narrow-Band Feature Pre-Selection and Weighted Dynamic Time Warping
- Deep Neural Network based Text-Dependent Speaker Verification : Preliminary Results
- Uncertainty Modeling Without Subspace Methods For Text-Dependent Speaker Recognition
- Deep Neural Networks and Hidden Markov Models in i-vector-based Text-Dependent Speaker Verification
- Speaker Recognition: i-vector approaches (5)
- Fast Scoring for PLDA with Uncertainty Propagation
- I-vector transformation and scaling for PLDA based speaker recognition
- Rapid Computation of I-vector
- Constrained discriminative speaker verification specific to normalized i-vectors
- Iterative Bayesian and MMSE-based noise compensation techniques for speaker recognition in the i-vector space
- Poster Session 1: Language Recognition (10)
- Between-Class Covariance Correction For Linear Discriminant Analysis in Language Recognition
- Incorporating uncertainty as a Quality Measure in I-Vector Based Language Recognition
- Discriminating Languages in a Probabilistic Latent Subspace
- Automatic Accent Recognition Systems and the Effects of Data on Performance
- The ‘Sprekend Nederland’ project and its application to accent location
- Deep Language: a comprehensive deep learning approach to end-to-end language recognition
- On the use of phone-gram units in recurrent neural networks for language identification
- Language Recognition for Dialects and Closely Related Languages
- Identification of British English regional accents using fusion of i-vector and multi-accent phonotactic systems
- Improvements on Deep Bottleneck Network based I-Vector Representation for Spoken Language Identification
- Speaker Recognition in Multimedia Content (3)
- Speaker & Language Recognition Systems (5)
- Speaker & Language Recognition: Deep learning approaches (5)
- Augmented Data Training of Joint Acoustic/Phonotactic DNN i-vectors for NIST LRE15
- LID-senone Extraction via Deep Neural Networks for End-to-End Language Identification
- On autoencoders in the i-vector space for speaker recognition
- Channel Compensation for Speaker Recognition using MAP Adapted PLDA and Denoising DNNs
- Evaluation of an LSTM-RNN System in Different NIST Language Recognition Frameworks
- Poster Session 2: Speaker Recognition I (10)
- Feature-based likelihood ratios for speaker recognition from linguistically-constrained formant-based i-vectors
- Improving Robustness of Speaker Verification Against Mimicked Speech
- Multi-channel i-vector combination for robust speaker verification in multi-room domestic environments
- VOICE LIVENESS DETECTION FOR SPEAKER VERIFICATION BASED ON A TANDEM SINGLE/DOUBLE-CHANNEL POP NOISE DETECTOR
- A PLDA Approach for Language and Text Independent Speaker Recognition
- Spoofing Detection on the ASVspoof2015 Challenge Corpus Employing Deep Neural Networks
- Age-Related Voice Disguise and its Impact on Speaker Verification Accuracy
- A New Feature for Automatic Speaker Verification Anti-Spoofing: Constant Q Cepstral Coefficients
- Multi-Bit Allocation: Preparing Voice Biometrics for Template Protection
- Analysis and Optimization of Bottleneck Features for Speaker Recognition
- Industry & Forensics Track (Short Talks + Panel Session) (2)
- NIST 2015 Language Recognition i-Vector Machine Learning Challenge (4)
- Poster Session 3: Speaker Recognition II (7)
- Cantonese forensic voice comparison with higher-level features: likelihood ratio-based validation using F-pattern and tonal F0 trajectories over a disyllabic hexaphone
- I-Vectors for speech activity detection
- Compensation for phonetic nuisance variability in speaker recognition using DNNs
- Local binary patterns as features for speaker recognition
- Robustness of Quality-based Score Calibration of Speaker Recognition Systems with respect to low-SNR and short-duration conditions
- From Features to Speaker Vectors by means of Restricted Boltzmann Machine Adaptation
- Reducing Noise Bias in the i-Vector Space for Speaker Recognition
- Speaker Clustering and Diarization (5)
- Semi-supervised On-line Speaker Diarization for Meeting Data with Incremental Maximum A-posteriori Adaptation
- Influence of transition cost in the segmentation stage of speaker diarization
- Analysis of the Impact of the Audio Database Characteristics in the Accuracy of a Speaker Clustering System
- Short- and Long-Term Speech Features for Hybrid HMM-i-Vector based Speaker Diarization System
- On the Use of PLDA i-vector Scoring for Clustering Short Segments
- Opening & Closing (2)
