Aerial Acoustic Modem with Decoding Capabilities Using a CELP-Based Speech Encoder.
Akira NishimuraPublished in: IIH-MSP (2010)
Keyphrases
- decoding process
- error control
- speech sounds
- speech recognition
- acoustic features
- speech signal
- speech recognition systems
- prosodic features
- bit rate
- emotional speech
- speech quality
- rate distortion
- linear predictive
- linear prediction
- acoustic signal
- noisy channel
- speaker independent
- speech recognizers
- text to speech
- motion estimation
- acoustic models
- network architecture
- error correction
- formant frequencies
- speech synthesis
- finite state transducers
- speaker recognition
- broadcast news
- emotion recognition
- automatic speech recognition
- audio visual
- video compression
- visual speech
- vocal tract
- pixel domain
- hidden markov models
- turbo codes
- decoding algorithm
- error resilience
- speech segments
- visual features
- vowel phonemes