Performance evaluation of acoustic scene classification using DNN-GMM and frame-concatenated acoustic features.
Gen TakahashiTakeshi YamadaNobutaka OnoShoji MakinoPublished in: APSIPA (2017)
Keyphrases
- acoustic features
- scene classification
- mel frequency cepstral coefficients
- speaker verification
- visual features
- speaker recognition
- gaussian mixture model
- object recognition
- image classification
- feature vectors
- speech signal
- natural scenes
- biologically inspired
- visual words
- speaker identification
- automatic speech recognition
- bag of features
- music information retrieval
- image representation
- environmental sounds
- natural images
- cross correlation
- video frames
- key frames
- mixture model
- speech recognition
- bag of words
- em algorithm
- image features
- feature space
- feature extraction
- audio features
- co occurrence
- object detection