Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no direct access to speech data.
Gasper BegusAlan ZhouPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- semantic information
- speech synthesis
- speech signal
- automatic speech recognition
- speech processing
- speech recognizer
- hidden markov models
- pattern recognition
- wordnet
- noisy environments
- speaker identification
- speech recognition technology
- language model
- semantic analysis
- speech recognizers
- domain knowledge
- training data
- databases
- broadcast news
- visual information
- syntactic information
- prior knowledge
- keywords
- speech recognition errors
- information retrieval