|
gptkbp:instanceOf
|
gptkb:academic
gptkb:technology
|
|
gptkbp:alsoKnownAs
|
gptkb:Automatic_Speech_Recognition
gptkb:ASR
|
|
gptkbp:application
|
gptkb:Google_Assistant
gptkb:Siri
gptkb:Otter.ai
gptkb:YouTube_auto-captioning
gptkb:Zoom_transcription
gptkb:Dragon_NaturallySpeaking
gptkb:Cortana
gptkb:Windows_Speech_Recognition
gptkb:Alexa
|
|
gptkbp:assesses
|
gptkb:Real-Time_Factor
gptkb:Sentence_Error_Rate
gptkb:Word_Error_Rate
|
|
gptkbp:challenge
|
code-switching
domain adaptation
speaker diarization
accent variation
background noise
homophones
|
|
gptkbp:developedBy
|
1950s
|
|
gptkbp:earlySystem
|
gptkb:Audrey_(Bell_Labs)
gptkb:Harpy_(CMU)
|
|
gptkbp:enables
|
conversion of spoken language to text
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Speech Recognition
|
|
gptkbp:notableCompany
|
gptkb:Amazon
gptkb:Apple
gptkb:Google
gptkb:IBM
gptkb:Microsoft
gptkb:Nuance_Communications
|
|
gptkbp:output
|
gptkb:text
transcript
|
|
gptkbp:relatedTo
|
gptkb:Signal_Processing
gptkb:Machine_Learning
gptkb:Natural_Language_Processing
Deep Learning
|
|
gptkbp:standardDataset
|
gptkb:Aurora
gptkb:Common_Voice
gptkb:AMI_Meeting_Corpus
gptkb:Aishell
gptkb:CALLHOME
gptkb:CHiME_Challenge
gptkb:Fisher_Corpus
gptkb:Libri-Light
gptkb:LibriSpeech
gptkb:Mozilla_Common_Voice
gptkb:OpenSLR
gptkb:Switchboard
gptkb:TED-LIUM
gptkb:TIMIT
gptkb:VCTK_Corpus
gptkb:VoxForge
gptkb:WSJ_Corpus
|
|
gptkbp:supportsAlgorithm
|
gptkb:Connectionist_Temporal_Classification
gptkb:Deep_Neural_Networks
gptkb:Hidden_Markov_Models
gptkb:Transformer_models
Recurrent Neural Networks
End-to-end models
|
|
gptkbp:supportsLanguage
|
gptkb:French
gptkb:German
gptkb:Mandarin
gptkb:Spanish
English
Japanese
many other languages
|
|
gptkbp:type
|
audio
speech waveform
|
|
gptkbp:usedIn
|
call centers
voice search
virtual assistants
accessibility tools
dictation software
|
|
gptkbp:bfsParent
|
gptkb:Signal_Processing
gptkb:Language_Technologies
gptkb:convolutional_neural_network
gptkb:Windows_Vista
|
|
gptkbp:bfsLayer
|
5
|