Acoustic Model Adaptation on Speech and Audio Coding Distortion.
Ivan KraljevskiFrank DuckhornRüdiger HoffmannPublished in: ITG Conference on Speech Communication (2012)
Keyphrases
- audio stream
- audio visual
- linear predictive coding
- broadcast news
- audio signals
- adaptive quantization
- speaker identification
- text to speech
- linear prediction
- linear predictive
- cepstral features
- emotion recognition
- audio recordings
- digital audio
- speech processing
- audio features
- rate control algorithm
- prosodic features
- speech music discrimination
- speech recognition
- audio video
- embedded image
- multimedia
- multi modal
- coding scheme
- automatic transcription
- bit allocation
- acoustic signals
- signal processing
- vector quantizer
- image coding
- coding efficiency
- channel errors
- automatic speech recognition
- coding method
- speech signal
- distortion measure
- prediction error
- rate distortion
- mel frequency cepstral coefficients
- spontaneous speech
- speech synthesis
- visual information
- multi stream
- speaker diarization
- image compression
- spoken documents
- shape coding
- speaker adaptation
- video signals
- visual data
- bit rate
- bitstream
- rate allocation
- music information retrieval
- data hiding
- gaussian mixture model
- hidden markov models
- acoustic features