Hosted voice recognition system for wireless devices

A computer-readable, non-transitory storage medium storing computer executable instructions that, when executed by a first computing device, configure the first computing device to perform operations comprising:

• receiving a first portion of audio input captured via a microphone of the first computing device;
• in direct response to receiving the first portion of the audio input, transmitting to a second computing device, first data representing the first portion of the audio input;
• receiving a next portion of the audio input that directly follows the first portion of the audio input, the next portion captured via the microphone;
• in direct response to receiving the next portion of the audio input, transmitting to the second computing device, next data representing the next portion of the audio input;
• receiving from the second computing device, first partial speech recognition results determined from the first data representing the first portion of the audio input,
• wherein the first partial speech recognition results are received prior to the transmitting of the next data;
• receiving from the second computing device, next partial speech recognition results determined from the next data representing the next portion of the audio input;
• and
• initiating display of the first partial speech recognition results on a display of the first computing device,
• wherein the display of the first partial speech recognition results on the display of the first computing device is initiated by the first computing device prior to the receiving of the next partial speech recognition results.

A system comprising:

• an electronic data store configured to at least store computer-executable instructions;
• and
• a second computing device including at least one processor, the second computing device in communication with the electronic data store and configured to execute the computer-executable instructions to at least:
• receive, from a first computing device, first data representing a first portion of an audio input;
• in response to receiving the first data, determine first partial speech recognition results from the first data;
• receive, from the first computing device, next data representing a next portion of the audio input that directly follows the first portion of the audio input;
• in response to receiving the next data, determine next partial speech recognition results from the next data;
• prior to determining the next partial speech recognition results from the next data, transmit the first partial speech recognition results to the first computing device, for display by the first computing device;
• and
• transmit the next partial speech recognition results to the first computing device for display by the first computing device,
• wherein, at the first computing device, the display of the first partial speech recognition results by the first computing device is initiated prior to the display of the next partial speech recognition results.