Don't multiply lightly: Quantifying problems with the acoustic model assumptions in speech recognition.
Dan GillickLarry GillickSteven WegmannPublished in: ASRU (2011)
Keyphrases
- speech recognition
- hidden markov models
- speech signal
- speech synthesis
- pattern recognition
- speech recognition technology
- language model
- keyword spotting
- speech understanding
- speech processing
- automatic speech recognition
- audio visual speech recognition
- neural network
- speech recognizer
- speaker identification
- handwriting recognition
- signal processing
- character recognition
- natural language processing
- speech recognition systems
- feature vectors
- machine learning