TDOA Estimation of Speech Source in Noisy Reverberant Environments.
Suliang BuTuo ZhaoYunxin ZhaoPublished in: SLT (2022)
Keyphrases
- speech signal
- noisy environments
- speech recognition
- speaker identification
- estimation algorithm
- text to speech
- machine learning
- speech synthesis
- spoken language
- missing data
- noisy data
- automatic speech recognition
- noisy measurements
- real world
- estimation accuracy
- accurate estimation
- audio visual
- computing environments
- parameter estimation
- dynamic environments
- denoising
- least squares
- hidden markov models
- user interface
- feature extraction