Keyphrases
Speaker Verification
96%
Speaker Recognition
45%
Joint Analysis
42%
Gaussian Mixture Model
39%
Factor Analysis
34%
I-vector
34%
Equal Error Rate
33%
Speaker Identification
33%
Utterance
29%
Speaker Recognition System
29%
Speech Recognition
29%
Factor Analysis Model
28%
Graphics Processing Unit
27%
Speaker Recognition Evaluation
25%
Cepstral Features
24%
Emotion Recognition from Speech
24%
Speaker Diarization
23%
Speaker Variability
23%
Continuous Speech Recognition
23%
Speech Recognition System
22%
Spectrogram
22%
Detection Cost
21%
Support Vector Machine
21%
Audio Fingerprinting
20%
Emotion Recognition
20%
Copy Detection
20%
Large Vocabulary
19%
Telephone Speech
19%
Eigenvoice
18%
Audio
18%
Training Data
17%
Speaker Adaptation
17%
Audio Fingerprint
16%
Mean Shift Algorithm
16%
Speech Signal
15%
Automatic Emotion Recognition
15%
Audio Copy Detection
15%
Mel Frequency Cepstral Coefficients
15%
Diarization Error Rate
14%
Relative Improvement
14%
Speaker Clustering
14%
TRECVID
14%
Feature Parameter
14%
Parallel Architecture
14%
Anchor Model
14%
Broadcast News
13%
Large Vocabulary Speech Recognition
13%
Eigenchannels
13%
Viterbi
13%
Feature Extractor
13%
Computer Science
Speaker Verification
100%
Speaker Recognition
78%
Speech Recognition
55%
Gaussian Mixture Model
43%
Speaker Identification
39%
Equal Error Rate
36%
Analysis Model
34%
Mel-Frequency Cepstral Coefficients
32%
cepstral
30%
Telephone
27%
Support Vector Machine
26%
Core Condition
25%
Speaker Diarization
24%
Graphics Processing Unit
22%
maximum-likelihood
22%
Linear Discriminant Analysis
22%
Training Data
22%
Speech Recognition System
17%
Verification System
16%
Experimental Result
16%
Cepstral Coefficient
16%
Approximation (Algorithm)
14%
Graphics Processor
14%
Parallel Architectures
14%
Covariance Matrix
13%
Recognizer
12%
Speed-up
12%
Likelihood Score
12%
Searching Algorithm
11%
Distance Metric
11%
Speech Recognizer
10%
Likelihood Ratio
10%
Boltzmann Machine
9%
Telephone Conversation
9%
Broadcast News
9%
Robust Speech Recognition
9%
Dimensional Vector
9%
Recognition System
9%
Mean Shift
9%
Score Normalization
9%
Varying Degree
9%
Salient Region
9%
Parallelization
8%
Fourier Transform
8%
Modern Processor
8%
Euclidean Distance
7%
Speaker Variability
7%
Probability Density Function
7%
Channel Condition
7%
Information Theory
7%
