Speech Signal Processing (1949)
This was not a real speech recognizer but an oscilloscope that would put the beam at a different spot depending of the content of the speech.
Raymond Kurzweil: "[Bell's] insights into separating the speech signal into different frequency components and rendering those components as visible traces were not successfully implemented until Potter, Kopp, and Green designed the spectrogram and Dreyfus-Graf developed the steno-sonograph in the late 1940s. These devices generated interest in the possibility of automatically recognizing speech because they made the invariant features of speech visible for all to see."