Short-time instantaneous frequency and bandwidth features for speech recognition.
Pirros TsiakoulisAlexandros PotamianosDimitrios DimitriadisPublished in: ASRU (2009)
Keyphrases
- speech recognition
- speech recognition systems
- speech synthesis
- hidden markov models
- language model
- cepstral coefficients
- speech recognizer
- speech processing
- speech signal
- speech recognition technology
- feature vectors
- automatic speech recognition
- pattern recognition
- noisy environments
- feature space
- feature extraction
- extracting features
- speaker identification
- machine learning
- mel frequency cepstral coefficients
- information retrieval