Fundamental frequency of child-directed speech using automatic speech recognition.
Mark VanDamPaul De PalmaPublished in: SCIS&ISIS (2014)
Keyphrases
- speech signal
- automatic speech recognition
- fundamental frequency
- speech recognition
- vocal tract
- word error rate
- broadcast news
- speaker identification
- hidden markov models
- linear prediction
- noisy environments
- non stationary
- conversational speech
- acoustic features
- speech corpus
- speech enhancement
- speech recognizers
- recognition errors
- spoken words
- speech sounds
- word recognition
- spontaneous speech
- speech segments
- acoustic models
- speaker independent
- language model