Acoustic model with hybrid Deep Bidirectional Single Gated Unit (DBSGU) for low resource speech recognition.
S. GirirajanA. PandianPublished in: Multim. Tools Appl. (2022)
Keyphrases
- speech recognition
- hidden markov models
- speech signal
- language model
- speech processing
- speech recognizer
- speech synthesis
- speech recognition systems
- pattern recognition
- automatic speech recognition
- speaker identification
- speech understanding
- keyword spotting
- speaker dependent
- noisy environments
- speech retrieval
- speech recognition technology
- speaker independent
- speech recognition errors
- computer vision