Improved Single System Conversational Telephone Speech Recognition with VGG Bottleneck Features.
William HartmannRoger HsiaoTim NgJeff Z. MaFrancis KeithMan-Hung SiuPublished in: INTERSPEECH (2017)
Keyphrases
- speech recognition
- speech recognition systems
- hidden markov models
- speech synthesis
- handwriting recognition
- automatic speech recognition
- cepstral coefficients
- speech understanding
- speech signal
- noisy environments
- pattern recognition
- speech recognition technology
- speech recognizer
- classification accuracy
- speaker identification
- low level
- keyword spotting
- feature vectors
- multi modal
- speech processing
- language model
- feature space
- speech recognition errors
- neural network
- isolated word
- audio visual speech recognition