Replay to Remember: Continual Layer-Specific Fine-tuning for German Speech Recognition.
Theresa Pekarek-RosinStefan WermterPublished in: CoRR (2023)
Keyphrases
- speech recognition
- fine tuning
- hidden markov models
- language model
- speech synthesis
- speech signal
- speech processing
- automatic speech recognition
- noisy environments
- speech understanding
- speech recognition technology
- pattern recognition
- speech recognizer
- speech recognition systems
- domain specific
- fine tuned
- handwriting recognition
- speech recognizers
- speaker identification
- speaker independent
- keyword spotting
- audio visual speech recognition
- speech retrieval
- isolated word
- machine learning
- cepstral coefficients
- speaker adaptation
- speaker recognition
- image processing
- information retrieval