Speakers In The Wild (SITW): The QUT Speaker Recognition System.
Houman GhaemmaghamiMd. Hafizur RahmanIvan HimawanDavid DeanAhilan KanagasundaramSridha SridharanClinton FookesPublished in: INTERSPEECH (2016)
Keyphrases
- speech recognition
- speaker independent
- speaker dependent
- recognition engine
- speaker adaptation
- speaker identification
- automatic speech recognition systems
- hidden markov models
- automatic speech recognition
- speech recognizer
- recognition algorithm
- feature extraction
- language model
- speaker recognition
- audio visual
- noisy environments
- data sets
- speaker diarization
- recognition process
- decision trees
- speech signal
- maximum likelihood
- acoustic features
- feature vectors
- image sequences
- e learning
- machine learning
- data mining
- automatic transcription
- improve the recognition accuracy
- real time