Text-dependent and text-independent speaker recognition of reverberant speech based on CNN.
Samia Abd El-MoneimAhmed SedikMohamed Abd-Elsalam NassarAdel S. El-FishawyA. M. SharsharShaimaa E. A. HassanAdel Zaghloul MahmoudMoawad I. DessoukyGhada M. El BanbyFathi E. Abd El-SamieEl-Sayed M. El-RabaieBadawi NeyaziH. S. SeddeqNabil A. IsmailAshraf A. M. KhalafG. S. M. ElabyadPublished in: Int. J. Speech Technol. (2021)
Keyphrases
- speech signal
- text recognition
- recognition engine
- spoken words
- convolutional neural network
- automatic speech recognition systems
- text to speech synthesis
- recognition rate
- text to speech
- recognition accuracy
- automatic speech recognition
- speech recognition
- speech sounds
- document analysis
- speech corpus
- object recognition
- text input
- english text
- lexical features
- information retrieval
- noisy environments
- pattern recognition
- multi lingual
- handwritten text
- handwriting recognition
- text mining
- digit recognition
- recognition algorithm
- optical character recognition
- neural network
- keywords
- text retrieval
- spontaneous speech
- gesture recognition
- conversational speech
- language generation
- audio signals
- word recognition
- handwritten documents
- speaker recognition
- feature extraction
- text detection