Converted Mel-Cepstral Coefficients for Gender Variability Reduction in Query-by-Example Spoken Document Retrieval.
Paula Lopez-OteroLaura Docío FernándezPublished in: IberSPEECH (2018)
Keyphrases
- cepstral coefficients
- spoken document retrieval
- speech recognition
- speech signal
- linear prediction
- feature set
- information retrieval
- broadcast news
- audio signal
- test collection
- language model
- automatic speech recognition
- hidden markov models
- retrieval method
- cross language
- video retrieval
- out of vocabulary
- noisy environments
- image retrieval
- speaker identification
- relevance feedback
- pattern recognition