Transcribing Mandarin Broadcast Speech Using Multi-Layer Perceptron Acoustic Features.
Fabio ValenteMathew Magimai-DossChristian PlahlSuman V. RavuriWen WangPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2011)
Keyphrases
- acoustic features
- multi layer perceptron
- speech signal
- speech recognition
- automatic speech recognition
- neural network
- speaker verification
- broadcast news
- artificial neural networks
- visual features
- emotion recognition
- radial basis function
- music information retrieval
- neural network model
- mlp neural networks
- audio stream
- audio features
- neuro fuzzy
- cross correlation
- mel frequency cepstral coefficients
- support vector machine
- hidden markov models
- noisy environments
- speaker identification
- speaker recognition
- multimedia
- genetic algorithm
- information retrieval
- data sets
- visual data
- image processing
- reinforcement learning
- audio visual