Speech recognition in living rooms: Integrated speech enhancement and recognition system based on spatial, spectral and temporal modeling of sounds.
Marc DelcroixKeisuke KinoshitaTomohiro NakataniShoko ArakiAtsunori OgawaTakaaki HoriShinji WatanabeMasakiyo FujimotoTakuya YoshiokaTakanobu ObaYotaro KuboMehrez SoudenSeong-Jun HahmAtsushi NakamuraPublished in: Comput. Speech Lang. (2013)
Keyphrases
- speech recognition
- noisy speech
- speech enhancement
- spectral subtraction
- speech signal
- noisy environments
- isolated word
- hidden markov models
- speaker independent
- linear prediction
- pattern recognition
- spectral analysis
- language model
- speech recognizer
- automatic speech recognition
- background noise
- sound source
- speaker adaptation
- signal to noise ratio
- speaker identification
- spectral features
- acoustic features
- speech synthesis
- speaker verification
- speech recognition systems
- single channel
- noise reduction
- neural network
- vocal tract
- machine learning
- speaker recognition
- independent component analysis
- wiener filter
- bayesian networks
- image processing