Improving Deep CNN Architectures with Variable-Length Training Samples for Text-Independent Speaker Verification.
Yanfeng WuJunan ZhaoChenkai GuoJing XuPublished in: Interspeech (2021)
Keyphrases
- training samples
- variable length
- speaker verification
- fixed length
- test sample
- noisy environments
- feature space
- supervised learning
- training set
- learning algorithm
- n gram
- high dimensional
- language identification
- face images
- information retrieval
- training data
- emotion recognition
- audio visual
- machine learning
- bitstream
- text mining
- neural network
- web documents
- language model
- multilayer perceptron
- support vector machine
- multiresolution
- keywords
- face recognition
- decision trees
- feature selection