Unimodal Aggregation for CTC-Based Speech Recognition.
Ying FangXiaofei LiPublished in: ICASSP (2024)
Keyphrases
- speech recognition
- language model
- hidden markov models
- speech processing
- speech synthesis
- speech signal
- automatic speech recognition
- speaker identification
- speech recognizer
- pattern recognition
- handwriting recognition
- speech recognizers
- speech understanding
- speech recognition systems
- noisy environments
- keyword spotting
- speaker independent
- speaker dependent
- speech recognition technology
- cepstral coefficients
- speech recognition errors
- speech retrieval
- principal component analysis
- image processing
- machine learning