Speaker identification using multi-modal i-vector approach for varying length speech in voice interactive systems.
Varun TiwariMohammad Farukh HashmiAvinash G. KeskarN. C. ShivaprakashPublished in: Cogn. Syst. Res. (2019)
Keyphrases
- multi modal
- speaker identification
- interactive systems
- mel frequency cepstral coefficients
- speech recognition
- speech signal
- speaker recognition
- gaussian mixture model
- broadcast news
- human computer interaction
- noisy environments
- audio visual
- speaker dependent
- video search
- feature extraction
- audio features
- user interface
- hidden markov models
- emotion recognition
- feature vectors
- mixture model
- learning systems
- pattern recognition
- automatic speech recognition
- uni modal
- face recognition
- expert systems
- high dimensional
- feature set
- model selection
- semantic concepts
- non stationary