Quantifying Informational Masking due to Masker Intelligibility in Same-talker Speech-in-speech Perception.
Mingyue HuoYinglun SunDaniel FogertyYan TangPublished in: INTERSPEECH (2023)
Keyphrases
- speech recognition
- speech signal
- audio visual
- recognition engine
- speech synthesis
- text to speech
- text to speech synthesis
- speech recognizer
- speech processing
- speaker recognition
- automatic speech recognition
- broadcast news
- spoken language
- endpoint detection
- speaker identification
- language model
- computer vision
- data sets
- noisy environments
- spoken dialogue systems
- speaker verification
- error rate
- multi modal
- hidden markov models
- pattern recognition
- vocal tract
- multiscale
- learning algorithm