Transcribing Speech as Spoken and Written Dual Text Using an Autoregressive Model.
Mana IhoriHiroshi SatoTomohiro TanakaRyo MasumuraSaki MizunoNobukatsu HojoPublished in: INTERSPEECH (2023)
Keyphrases
- autoregressive model
- spoken documents
- speech recognition
- spoken words
- spoken language
- automatic speech recognition
- spontaneous speech
- broadcast news
- text to speech
- conversational speech
- spoken document retrieval
- speech signal
- information retrieval
- autoregressive
- wavelet analysis
- keywords
- hidden markov models
- linear combination
- information extraction
- multiscale