Nome |
# |
Parallel implementation of Artificial Neural Network training for speech recognition, file e384c42e-03db-d4b2-e053-9f05fe0a1d67
|
1.289
|
Pairwise Discriminative Speaker Verification in the I-Vector Space, file e384c42e-26db-d4b2-e053-9f05fe0a1d67
|
741
|
Nuance - Politecnico di Torino’s 2012 NIST Speaker Recognition Evaluation System, file e384c42e-2e40-d4b2-e053-9f05fe0a1d67
|
736
|
Analysis of Large-Scale SVM Training Algorithms for Language and Speaker Recognition, file e384c42e-181d-d4b2-e053-9f05fe0a1d67
|
716
|
Large scale training of Pairwise Support Vector Machines for speaker recognition, file e384c42e-351e-d4b2-e053-9f05fe0a1d67
|
635
|
Speaker recognition by means of Deep Belief Networks, file e384c42e-27fb-d4b2-e053-9f05fe0a1d67
|
611
|
Compensation of Nuisance Factors for Speaker and Language Recognition, file e384c42d-f637-d4b2-e053-9f05fe0a1d67
|
594
|
Comparison of speaker recognition approaches for real applications, file e384c42e-0dd1-d4b2-e053-9f05fe0a1d67
|
588
|
Fast and Memory Effective I-Vector Extraction Using a Factorized Sub-Space, file e384c42e-2e41-d4b2-e053-9f05fe0a1d67
|
588
|
Linear hidden transformations for adaptation of hybrid ANN/HMM models, file e384c42d-f955-d4b2-e053-9f05fe0a1d67
|
554
|
Factorized Sub-Space Estimation for Fast and Memory Effective I-vector Extraction, file e384c42e-2acf-d4b2-e053-9f05fe0a1d67
|
526
|
Channel Factors Compensation in Model and Feature Domain for Speaker Recognition, file e384c42d-f212-d4b2-e053-9f05fe0a1d67
|
504
|
Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting, file e384c42e-0538-d4b2-e053-9f05fe0a1d67
|
476
|
Parallel implementation of artificial neural network training, file e384c42e-0b57-d4b2-e053-9f05fe0a1d67
|
474
|
Loquendo - Politecnico di Torino's 2006 NIST Speaker Recognition Evaluation System, file e384c42d-f504-d4b2-e053-9f05fe0a1d67
|
456
|
Training pairwise Support Vector Machines with large scale datasets, file e384c42e-3353-d4b2-e053-9f05fe0a1d67
|
446
|
FAST DISCRIMINATIVE SPEAKER VERIFICATION IN THE I–VECTOR SPACE, file e384c42e-0c4e-d4b2-e053-9f05fe0a1d67
|
440
|
Memory-aware i-vector extraction by means of subspace factorization, file e384c42e-376b-d4b2-e053-9f05fe0a1d67
|
414
|
GENDER INDEPENDENT DISCRIMINATIVE SPEAKER RECOGNITION IN I–VECTOR SPACE, file e384c42e-181f-d4b2-e053-9f05fe0a1d67
|
410
|
Directory Assistance: Learning User Formulations for Business Listings, file e384c42d-f1ae-d4b2-e053-9f05fe0a1d67
|
378
|
Adaptation of Hybrid ANN/HMM Models using Linear Hidden Transformations and Conservative Training, file e384c42e-0539-d4b2-e053-9f05fe0a1d67
|
376
|
On the use of i-vector posterior distributions in Probabilistic Linear Discriminant Analysis, file e384c42e-9977-d4b2-e053-9f05fe0a1d67
|
374
|
Learning New User Formulations in Automatic Directory Assistance., file e384c42d-f1af-d4b2-e053-9f05fe0a1d67
|
357
|
Memory and computation trade-offs for efficient i-vector extraction, file e384c42e-96a2-d4b2-e053-9f05fe0a1d67
|
333
|
Learning Pronunciation and Formulation Variants in Continuous Speech Applications, file e384c42d-f1b2-d4b2-e053-9f05fe0a1d67
|
331
|
On the Use of a Multilingual Neural Network Front-End, file e384c42d-ff54-d4b2-e053-9f05fe0a1d67
|
329
|
LOQUENDO-POLITECNICO DI TORINO SYSTEM FOR THE 2009 NIST LANGUAGE RECOGNITION EVALUATION, file e384c42e-0b55-d4b2-e053-9f05fe0a1d67
|
322
|
Loquendo - Politecnico di Torino’s 2008 NIST Speaker Recognition Evaluation System, file e384c42e-086e-d4b2-e053-9f05fe0a1d67
|
303
|
Generative pairwise models for speaker recognition, file e384c42e-3355-d4b2-e053-9f05fe0a1d67
|
301
|
Acoustic Language Identification Using Fast Discriminative Training, file e384c42d-f503-d4b2-e053-9f05fe0a1d67
|
287
|
LOQUENDO - POLITECNICO DI TORINO’S 2010 NISTSPEAKER RECOGNITION EVALUATION SYSTEM, file e384c42e-0c4f-d4b2-e053-9f05fe0a1d67
|
282
|
Memory and computation effective approaches for i–vector extraction, file e384c42e-1c9c-d4b2-e053-9f05fe0a1d67
|
232
|
Experiments in Confidence Scoring for Word and Sentence Verification., file e384c42d-f1b0-d4b2-e053-9f05fe0a1d67
|
226
|
A Confidence Measure Invariant to Language and Grammar, file e384c42d-f20f-d4b2-e053-9f05fe0a1d67
|
219
|
Politecnico di Torino System for the 2007 NIST Language Recognition Evaluation, file e384c42d-ff53-d4b2-e053-9f05fe0a1d67
|
218
|
Speeding-up Neural Network Training Using Sentence and Frame Selection, file e384c42d-f505-d4b2-e053-9f05fe0a1d67
|
208
|
Language Recognition Using Language Factors, file e384c42e-04f6-d4b2-e053-9f05fe0a1d67
|
199
|
Language Identification Using Acoustic Models an Speaker Compensated Cepstral-Time Matrices, file e384c42d-f506-d4b2-e053-9f05fe0a1d67
|
167
|
Comparison of Large–scale SVM Training Algorithms for Language Recognition, file e384c42e-144a-d4b2-e053-9f05fe0a1d67
|
159
|
Adapting Hybrid ANN/HMM to Speech Variations, file e384c42e-3c9c-d4b2-e053-9f05fe0a1d67
|
159
|
Unsupervised Segmentation and Verification of Multi-Speaker Conversational Speech, file e384c42d-f210-d4b2-e053-9f05fe0a1d67
|
152
|
Joint estimation of PLDA and nonlinear transformations of speaker vectors, file e384c42f-b3c5-d4b2-e053-9f05fe0a1d67
|
148
|
Word Confidence Using Duration Models, file e384c42e-04f5-d4b2-e053-9f05fe0a1d67
|
146
|
Speaker Recognition using Channel Factor Feature Compensation, file e384c42d-f211-d4b2-e053-9f05fe0a1d67
|
144
|
Learning of User Formulations for Business Listings in Automatic Directory Assistance, file e384c42d-f1b1-d4b2-e053-9f05fe0a1d67
|
139
|
Synergy of Spectral and Perceptual Features in Multi-source Connectionist Speech Recognition, file e384c42d-f1ac-d4b2-e053-9f05fe0a1d67
|
126
|
Toward Automatic Adaptationof the Acoustic Models and of the Formulation Variants in a Directory Assistance Application, file e384c42d-f1ad-d4b2-e053-9f05fe0a1d67
|
97
|
Speaker Recognition Using e–Vectors, file e384c42f-f1a0-d4b2-e053-9f05fe0a1d67
|
87
|
Scoring heterogeneous speaker vectors using nonlinear transformations and tied PLDa models, file e384c430-1843-d4b2-e053-9f05fe0a1d67
|
45
|
Exact memory–constrained UPGMA for large scale speaker clustering, file e384c431-55df-d4b2-e053-9f05fe0a1d67
|
13
|
Nuance - Politecnico di Torino’s 2016 NIST Speaker Recognition Evaluation System, file e384c42f-b88c-d4b2-e053-9f05fe0a1d67
|
4
|
Exact memory–constrained UPGMA for large scale speaker clustering, file e384c431-67c7-d4b2-e053-9f05fe0a1d67
|
4
|
Speaker recognition by means of acoustic and phonetically informed GMMs, file e384c42d-4cd0-d4b2-e053-9f05fe0a1d67
|
3
|
I–vector transformation and scaling for PLDA based speaker recognition, file e384c42e-cd37-d4b2-e053-9f05fe0a1d67
|
2
|
Tied Normal Variance-Mean Mixtures for Linear Score Calibration, file e384c430-eec2-d4b2-e053-9f05fe0a1d67
|
2
|
On the use of i-vector posterior distributions in Probabilistic Linear Discriminant Analysis, file e384c431-aa47-d4b2-e053-9f05fe0a1d67
|
2
|
Stream-Based Speaker Segmentation Using Speaker Factors and Eigenvoices, file e384c42d-fd41-d4b2-e053-9f05fe0a1d67
|
1
|
FAST SPEAKER RECOGNITION SCORING USING I-VECTOR POSTERIORS AND PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS, file e384c42e-f4ff-d4b2-e053-9f05fe0a1d67
|
1
|
Nonlinear i-vector transformations for PLDA-based speaker recognition, file e384c42f-6ac1-d4b2-e053-9f05fe0a1d67
|
1
|
E--vectors: JFA and i--vectors revisited, file e384c42f-7547-d4b2-e053-9f05fe0a1d67
|
1
|
Joint estimation of PLDA and nonlinear transformations of speaker vectors, file e384c432-21f5-d4b2-e053-9f05fe0a1d67
|
1
|
Scoring heterogeneous speaker vectors using nonlinear transformations and tied PLDa models, file e384c433-287c-d4b2-e053-9f05fe0a1d67
|
1
|
Totale |
18.078 |