The Coding Strategy for the Mandarin Speech Conveying Sarcasm in Acoustic and Articulatory Domain.
Puyang GengShaopei ShiHong GuoPublished in: ICDSP (2021)
Keyphrases
- speech recognition
- speaker independent
- prosodic features
- speech recognition systems
- acoustic features
- speech synthesis
- speech signal
- speech recognizers
- speech recognizer
- vocal tract
- acoustic models
- linear prediction
- automatic speech recognition
- hidden markov models
- speaker identification
- pattern recognition
- coding scheme
- multi stream
- speech sounds
- text to speech
- language model
- formant frequencies
- speaker verification
- broadcast news
- music information retrieval
- visual features
- domain specific
- spoken document retrieval
- spontaneous speech
- human computer interaction