Speaker Discrimination Using Long-Term Spectrum of Speech.
Milan SigmundPublished in: Inf. Technol. Control. (2019)
Keyphrases
- long term
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- speaker identification
- speaker verification
- prosodic features
- short term
- speaker dependent
- speech signal
- vocal tract
- automatic speech recognition systems
- speech synthesis
- speaker diarization
- speech sounds
- audio stream
- broadcast news
- acoustic features
- gaussian mixture model
- multi modal
- noisy environments
- hidden markov models
- phoneme recognition
- text to speech
- speaker adaptation
- automatic transcription
- recognition engine
- power spectrum
- synthesized speech
- speaker independent
- multimedia
- spontaneous speech
- speech recognizer
- linear prediction
- emotion recognition
- visual information
- vector quantization
- data sets
- probabilistic neural network
- audio features