On 2020-05-12 07:12 UTC I noted ideas for #edutech voice and speech solutions using TensorFlow: voice enhancement, automated calling, call routing, audio mining, candidate interview assessment, speech analysis.
On 2020‑05‑08 I shared a LinkedIn post highlighting common misconceptions about speech production: people think speech is a sequence of discrete words and static phones, but in reality it is a dynamic, continuous process without clearly separated parts. #misconceptions #speechrecognition #audioengineering #tensorflow #deeplearning #data4good
People rarely understand how speech is produced and perceived.
The naive perception is often that speech is built with words and each word consists of phones.
Speech is a dynamic process without clearly distinguished parts.