Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions.
Santi PrietoAlfonso Ortega GiménezIván López-EspejoEduardo LleidaPublished in: CoRR (2020)
Keyphrases
- speaker verification
- noisy environments
- acoustic features
- emotion recognition
- speech signal
- speaker recognition
- prosodic features
- speech recognition
- audio visual
- automatic speech recognition
- noise reduction
- speaker identification
- language identification
- image data
- neural network
- using artificial neural networks
- gaussian mixture model
- human computer interaction
- multi modal
- text to speech
- probabilistic model
- genetic algorithm