Google deep learning audio-visual model can pinpoint one voice in many

Photo of Google deep learning audio-visual model can pinpoint one voice in many
Facebook
VKontakte
share_fav
Google says that people are very good at separating out other voices and hearing the one we are looking at, this is called the cocktail party effect. Machines not so much. Google wants to make computers better at hearing the voice that we want to hear and has developed a new deep learning audio-visual model for isolating single speech signal … Continue reading
view Slash Gear
#archive
#research
#google
#artificial intelligence