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