Exploring the Impact of Pretrained Models and Web-Scraped Data for the 2022 NIST Language Recognition Evaluation.
Tanel AlumäeKunnar KukkViet Bac LeClaude BarrasAbdel MessaoudiWaad Ben KhederPublished in: INTERSPEECH (2023)
Keyphrases
- data sets
- data collection
- experimental data
- historical data
- data sources
- data analysis
- object recognition
- databases
- database
- data structure
- statistical methods
- end users
- knowledge discovery
- training data
- data processing
- recognition rate
- accurate models
- data mining techniques
- prior knowledge
- programming language
- statistical analysis
- information sources
- high dimensional data
- action recognition
- sensor data
- image data
- human activities
- probabilistic model
- relational databases