Classifying Non-speech Vocals: Deep vs Signal Processing Representations.
Fatemeh PishdadianPrem SeetharamanBongjun KimBryan PardoPublished in: DCASE (2019)
Keyphrases
- signal processing
- speech processing
- image processing
- speech recognition
- fourier transform
- symbolic representation
- deep learning
- speech signal
- pattern recognition
- computer vision
- spontaneous speech
- text to speech
- recognition engine
- signal analysis
- digital signal processing
- endpoint detection
- information retrieval
- automatic speech recognition
- automatic classification
- multi modal
- audio features
- spoken language
- broadcast news
- watermarking algorithm
- filter bank
- speech synthesis
- low level
- similarity measure
- data sets