Discovering Articulatory Speech Targets from Synthesized Random Babble.
Heikki RasiloYannick JadoulPublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- vocal tract
- speech signal
- speech synthesis
- multi stream
- formant frequencies
- automatic speech recognition
- vowel phonemes
- hidden markov models
- acoustic features
- speaker identification
- broadcast news
- neural network
- speech recognizer
- audio visual
- randomly generated
- image acquisition
- language model
- dialogue system
- multi target
- text to speech
- speech processing
- linear prediction
- spoken language
- emotion recognition
- uniformly distributed
- visual information
- endpoint detection
- hearing impaired
- real time