Speech-VGG: A deep feature extractor for speech processing.
Pierre BeckmannMikolaj KeglerHugues SaltiniMilos CernakPublished in: CoRR (2019)
Keyphrases
- speech processing
- feature extractor
- speech recognition
- feature extraction
- speaker identification
- signal processing
- natural language processing
- multimedia systems
- english text
- recognition scheme
- artificial intelligence
- variable length
- feature values
- speech signal
- texture descriptors
- hidden markov models
- multimedia
- image processing
- edge detector
- automatic speech recognition
- pattern recognition
- gaussian mixture model
- image classification
- noisy environments
- language model
- broadcast news
- image features
- language identification