Mi-Go: tool which uses YouTube as data source for evaluating general-purpose speech recognition machine learning models.
Tomasz WojnarJaroslaw HryszkoAdam RomanPublished in: EURASIP J. Audio Speech Music. Process. (2024)
Keyphrases
- speech recognition
- machine learning models
- data sources
- hidden markov models
- automatic speech recognition
- pattern recognition
- speech synthesis
- language model
- machine learning algorithms
- speech processing
- speech recognizer
- speech signal
- spam filtering
- noisy environments
- machine learning approaches
- speech recognition technology
- speech recognition systems
- machine learning
- support vector
- learning models
- predictive model
- speaker identification
- isolated word
- classification accuracy
- decision trees
- learning algorithm
- genetic algorithm