As part of Machine Learning Meat-Ups, I spoke with my colleague Jindra Matousek about speech technologies in practice. If you missed the talk on 1 April with the subtitle from research to practice, you can watch the video below.
In the presentation we introduce research topics in speech technologies that we work on at our department, especially text-to-speech (TTS) and automatic speech recognition (ASR). We then show both technologies in practical applications: automatic reading of textbooks for visually impaired pupils, automatic captioning of live television programmes for deaf and hard-of-hearing viewers, speech technologies in air traffic control, and search in spoken archives.
