On the issues of intra-speaker variability and realism in speech, speaker, and language recognition tasks.
John H. L. HansenHynek BorilPublished in: Speech Commun. (2018)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- speaker verification
- speaker identification
- speaker diarization
- prosodic features
- speaker dependent
- automatic speech recognition systems
- text to speech
- vocal tract
- speech signal
- language learning
- automatic transcription
- language acquisition
- speech synthesis
- gaussian mixture model
- pattern recognition
- emotion recognition
- natural language
- audio stream
- hidden markov models
- programming language
- synthesized speech
- acoustic models
- multi modal
- speaker adaptation
- mel frequency cepstral coefficients
- speech sounds
- spoken language
- probabilistic neural network
- broadcast news
- noisy environments
- vector quantization
- acoustic features
- information retrieval
- key issues
- mixture model
- probabilistic model
- multimedia