The Acoustic Realization of Mandarin Tones in Fast Speech.
Ping TangShanpeng LiPublished in: INTERSPEECH (2020)
Keyphrases
- speaker independent
- speech recognition
- prosodic features
- speech recognition systems
- speech synthesis
- text to speech
- broadcast news
- speaker identification
- speech recognizer
- acoustic models
- emotion recognition
- emotional speech
- hidden markov models
- speaker verification
- automatic speech recognition
- speech signal
- speech recognizers
- speech sounds
- spontaneous speech
- noisy speech
- acoustic features
- spoken document retrieval
- digit recognition
- noisy environments
- language model
- vowel phonemes
- acoustic signal
- vocal tract
- speaker recognition
- audio visual
- recognition engine
- gaussian mixture model
- wireless sensor networks
- multimedia
- speech segments
- formant frequencies
- spoken language