Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation.
Emiru TsunooHayato FutamiYosuke KashiwagiSiddhant AroraShinji WatanabePublished in: CoRR (2023)
Keyphrases
- speech recognition
- text data
- text classification
- text mining
- hidden markov models
- high dimensional
- automatic speech recognition
- pattern recognition
- speech synthesis
- speech recognizer
- language model
- structured data
- speech signal
- document collections
- high dimensional data
- speech recognition systems
- text documents
- speech recognition technology
- speaker identification
- data sets
- text categorization
- question answering
- information retrieval systems
- nearest neighbor
- semi supervised
- training set
- speaker independent
- web pages