ANN |
Artificial Neural Network. The framework that
is used in the hybrid HMM/ANN recognizer to compute local phoneme probabilities. |
ASR |
Automatic Speech Recognition. |
CDHMM |
Continuous Density Hidden Markov Model.
Currently the most popular flavor of the HMM for ASR. |
CSR |
Continuous (automatic) Speech Recognition |
CTT |
Centrum för talteknologi (Centre for Speech
Technology), based at KTH, Stockholm. |
DAG |
Directed acyclic graph |
DFA |
Deterministic Finite State Automaton. |
DP |
Dynamic Programming. An computationally efficient scheme
for solving certain optimization problems. |
EM |
Expectation Maximization. Statistical method for parameter
estimation. |
EUROSPEECH |
European Conference on Speech Communication and Technology. |
FSA |
Finite State Automaton. |
HMM |
Hidden Markov Model. A statistical time-series
model that forms the basis of most contemporary state-of-the-art
ASR systems. |
ICASSP |
International Conference on Acoustics, Speech,
and Signal Processing. |
ICSLP |
International Conference on Spoken Language
Processing. |
IEEE |
The Institute of Electrical and Electronic Engineers,
Inc. |
JASA |
Journal of the Acoustic Society of America. |
KTH |
Kungliga Tekniska Högskolan (Royal Institute
of Technology), Stockholm, Sweden. |
MAP |
Maximum a posteriori. Optimization criterion
for the estimation of statistical parameters. |
MCE |
Minimum Classification Error. General optimization
criterion for statistical classifiers. |
ML |
Maximum Likelihood. Optimization criterion for
the estimation of statistical parameters. |
NFA |
Non-deterministic Finite State Automaton. |
SD |
Speaker Dependent. |
SI |
Speaker Independent. |
STL-QPSR |
Speech Transmission Laboratory - Quarterly
Progress and Status Report, THM, KTH. |
TMH |
Institutionen för tal, musik och hörsel
(Department of Speech, Music and Hearing), KTH, Stockholm. |
TIMIT |
Speech database recorded and processed by Texas Instruments
and Massachusetts Institute of Technology. |