Speech intelligibility derived from time-frequency and source smearing.
Toshio IrinoSatoru SatouShunsuke NomuraHideki BannoHideki KawaharaPublished in: INTERSPEECH (2005)
Keyphrases
- speech recognition
- speech signal
- automatic speech recognition
- speech synthesis
- text to speech
- signal analysis
- spoken language
- frequency domain
- signal processing
- wavelet transform
- data mining
- language model
- independent component analysis
- signal to noise ratio
- multiple sources
- probabilistic model
- hidden markov models
- noisy environments
- face recognition
- image processing
- neural network