Mixing Time-Frequency Distributions for Speech Command Recognition Using Convolutional Neural Networks.
Reemt HinrichsJonas DunkelJörn OstermannPublished in: ICFSP (2021)
Keyphrases
- convolutional neural networks
- convolutional network
- probability distribution
- speech recognition
- speech signal
- signal processing
- random variables
- joint distribution
- frequency domain
- text to speech
- audio visual
- spoken language
- speaker identification
- gaussian distribution
- automatic speech recognition
- language acquisition
- recognition engine
- short time fourier transform
- information retrieval