Keyphrases
Automatic Speech Recognition
51%
Speech Recognition
40%
Audio
34%
Phoneme
27%
Prosody
23%
Hidden Markov Model
21%
Error Rate
21%
Target Language
21%
Speech Recognition System
19%
Gaussian Mixture Model
18%
Acoustics
17%
Mismatched Crowdsourcing
17%
Acoustic Modeling
16%
Cross-lingual
16%
Vowels
15%
Under-resourced Languages
15%
Acoustic Features
15%
Consonants
13%
Word Error Rate
13%
Speech Corpus
13%
Deep Neural Network
12%
Adaptation
11%
Acoustic Cues
11%
Recognition Accuracy
11%
Utterance
11%
Dysarthria
11%
Language Model
11%
Probabilistic Transcription
11%
Phonetics
11%
Acoustic Event Detection
10%
Support Vector Machine
10%
Transcriber
10%
Mismatched Transcription
9%
American English
9%
Speech Technology
9%
Speech Signal
9%
Dysarthric Speech
9%
Recognizer
9%
Hindi
8%
Training Data
8%
Unlabeled Data
8%
Distinctive Features
8%
Vector Representation
8%
Low-resource
8%
TIMIT
8%
Token
8%
Multi-task Learning
8%
Labeled Data
8%
Landmark-based
8%
Spectrogram
8%
Computer Science
Speech Recognition
100%
Speech Recognition System
26%
Gaussian Mixture Model
22%
Target Language
21%
Support Vector Machine
18%
Language Modeling
17%
Word Error Rate
15%
Text To Speech
15%
Deep Neural Network
14%
Annotation
13%
Acoustic Feature
13%
Speech Recognizer
12%
Recognition Accuracy
12%
Convolutional Neural Network
12%
Distinctive Feature
12%
speech corpus
11%
Speech Synthesis
11%
Mutual Information
11%
Recognizer
11%
Neural Network
11%
Spoken Language
10%
Training Data
10%
Phonology
9%
Unlabeled Data
9%
Spontaneous Speech
9%
Experimental Result
9%
Event Detection
9%
Information Retrieval
8%
maximum-likelihood
8%
Source Language
8%
Multitask Learning
8%
Feature Extraction
7%
Human Speech Perception
7%
Language Understanding
7%
Art Performance
7%
Speech Understanding
6%
Transfer Learning
6%
Low-resource Languages
6%
Linear Discriminant Analysis
6%
Dysarthric Speech Recognition
6%
Information Criterion
6%
Dynamic Bayesian Network
6%
Visual Feature
5%
Machine Translation
5%
Native Language
5%
Model Architecture
5%
Recognition Performance
5%
Learning Framework
5%
Large Language Model
5%
Language Development
5%
