Shennong: a Python toolbox for audio speech features extraction.
Mathieu BernardMaxime PoliJulien KaradayiEmmanuel DupouxPublished in: CoRR (2021)
Keyphrases
- features extraction
- audio stream
- audio visual
- broadcast news
- audio signals
- speaker identification
- cepstral features
- emotion recognition
- feature extraction
- audio features
- text to speech
- digital audio
- audio recordings
- automatic classification
- speech recognition
- spoken documents
- speech music discrimination
- open source
- linear predictive coding
- prosodic features
- visual information
- acoustic features
- multimedia
- speech signal
- multi stream
- programming language
- wavelet transform
- automatic transcription
- character recognition
- extracted features
- automatic speech recognition
- visual speech
- speaker diarization
- spontaneous speech
- speech synthesis
- pattern recognition
- soccer video