Frequency offset correction in speech without detecting pitch.
Pascal ClarkSri Harish Reddy MallidiAren JansenHynek HermanskyPublished in: ICASSP (2013)
Keyphrases
- fundamental frequency
- formant frequencies
- speech signal
- speech recognition
- automatic detection
- low frequency
- audio visual
- spoken language
- acoustic features
- multiscale
- information systems
- automatic speech recognition
- audio stream
- frequency distribution
- spontaneous speech
- speech synthesis
- text to speech
- language acquisition
- natural language processing
- hidden markov models
- feature extraction
- feature selection