Separation of speech sources using an Acoustic Vector Sensor.
Muawiyath ShujauChristian H. RitzIan S. BurnettPublished in: MMSP (2011)
Keyphrases
- sound source
- speech signal
- source localization
- speech recognition
- audio visual
- audio features
- speech sounds
- acoustic features
- speech recognition systems
- sensor networks
- information sources
- blind separation
- blind source separation
- source separation
- automatic speech recognition
- sensor data
- emotional speech
- underwater acoustic
- databases
- feature vectors
- prosodic features
- acoustic signal
- audio stream
- source signals
- speaker independent
- speech segments
- real time
- formant frequencies
- text to speech
- vector space
- multi sensor
- emotion recognition
- noisy speech
- data sources
- linear prediction
- speaker identification
- mel frequency cepstral coefficients
- speaker verification
- vocal tract
- recognition engine
- speech synthesis
- noisy environments
- human computer interaction
- feature space
- pattern recognition