ABSR |
Assistant-based speech recognition |
AED |
Attention-based encoder–decoder |
AM |
Acoustic model |
AMAN |
Arrival manager |
AP |
Average pooling |
ASR |
Automatic speech recognition |
ATC |
Air traffic control |
ATCos |
Air traffic controllers |
BERT |
Bidirectional encoder representations from transformers |
CER |
Character error rate |
CMVN |
Cepstral mean and variance normalization |
CNNs |
Convolutional neural networks |
CmdER |
Command error rate |
ConER |
Concept error rate |
CSA |
Callsign accuracy |
CTC |
Connectionist temporal classification |
DNN |
Deep neural networks |
E2E |
End-to-end |
FAA |
Federal Aviation Administration |
FBank |
Filter bank |
FC |
Fully connected |
GMM |
Gaussian mixture model |
HMM |
Hidden Markov model |
ICAO |
International Civil Aviation Organization |
LF-MMI |
Lattice-free maximum mutual information |
LM |
Language model |
LSTM |
Long short-term memory |
MCNN |
Multiscale CNN |
MFCC |
Mel frequency cepstrum coefficient |
MTPM |
Machine translation PM |
PLM |
Phoneme-based LM |
PM |
Pronunciation model |
PPR |
Parallel phone recognition |
RIA |
Repetition intention accuracy |
RNNs |
Recurrent neural networks |
RNN-T |
Recurrent neural network transducer |
RTF |
Real-time factor |
SER |
Sentence error rate |
STFT |
Short-time Fourier transform |
TDNN |
Time delay neural network |
VHF |
Very high frequency |
WER |
Word error rate |
WFST |
Weighted finite-state transducer |
WLM |
Word-based language model |