A Comparative Study of 3D and 1D Acoustic Simulations of the Higher Frequencies of Speech.
Rémi BlandinSimon StoneAngélique RemacleVincent DidonePeter BirkholzPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2023)
Keyphrases
- speech recognition
- acoustic features
- speech sounds
- speech recognizers
- speech recognition systems
- audio visual
- speech signal
- automatic speech recognition
- speech recognizer
- recognition engine
- speaker independent
- acoustic models
- simulation environment
- comparative study
- prosodic features
- emotional speech
- noisy speech
- multi stream
- frequency distribution
- source localization
- feature extraction
- text to speech
- speaker recognition
- speaker verification
- higher quality
- multi agent