A 16, 24, 32 kbit/s wideband speech codec based on ATCELP.
Pierre CombescureJürgen SchnitzlerKyrill A. FischerRalf KirchherrClaude LamblinAlain Le GuyaderDominique MassalouxCatherine QuinquisJoachim StegmannPeter VaryPublished in: ICASSP (1999)
Keyphrases
- speech signal
- speaker dependent
- speech recognition
- speaker identification
- speech quality
- automatic speech recognition
- speaker independent
- vocal tract
- bitstream
- noisy environments
- speaker recognition
- hidden markov models
- frequency band
- spoken language
- video codec
- text to speech
- speech recognizer
- signal to noise ratio
- recognition engine
- video coding
- non stationary
- audio visual
- speech synthesis
- distributed video coding
- language model