Transport sound profile
An example operation includes one or more of associating a vehicle with an impact, saving media captured before and after the impact as a media segment, transmitting, by a computing device associated with the vehicle, the media segment to another computing device, and building a sound profile from the media segment.
1. A method, comprising:
receiving, by a server, sounds and video captured before and after a vehicle impact from audio sensors of a plurality of different transports;
synchronizing, by the server, the sounds with the video to generate synchronized content;
identifying, by the server, a plurality of audio capturing sources of a plurality of sounds within the synchronized content, where the plurality of audio capturing sources are included within the plurality of different transports;
storing unique identifiers of the plurality of sounds and identifiers of the plurality of audio capturing sources of the plurality of sounds within a sound profile;
identifying a voice sound among the plurality of sounds based on the sound profile;
performing speech recognition on the voice sound via execution of a speech recognition application to generate recognized speech associated with the vehicle impact; and
transmitting, by the server, the recognized speech to a computing device associated with the vehicle impact.
2. The method of claim 1 , wherein the sounds and video further comprise one or more of:
a text file, an image file, vehicle telemetry, environmental data, traffic data, and sensor data.
3. The method of claim 1 , wherein the sounds and video further comprise data related to one or more of:
ambient temperature, road conditions, weather, wind speed or direction, time of day, and light sources.
4. The method of claim 1 , wherein the sounds and video further comprise directions for the sounds, and
wherein the synchronizing further comprises:
synchronizing the sounds with the video based on the directions of the sounds.
5. The method of claim 1 , wherein the sound profile comprises:
a unique identifier of a respective sound;
a starting timestamp of the respective sound;
an ending timestamp of the respective sound; and
an indication of a source of the respective sound.
6. The method of claim 1 , further comprising:
providing the sound profile to one of an emergency services provider or an insurance provider based on the determination.
7. A computer device, comprising:
a processor that when executing instructions stored in a memory is configured to:
receive sounds and video captured before and after a vehicle impact from audio sensors of a plurality of different transports;
synchronize the sounds with the video to generate synchronized content;
identify a plurality of audio capturing sources of a plurality of sounds within the synchronized content, where the plurality of audio capturing sources are included within the plurality of different transports;
store unique identifiers of the plurality of sounds and identifiers of the plurality of audio capturing sources of the plurality of sounds within a sound profile;
identify a voice sound among the plurality of sounds based on the sound profile;
perform speech recognition on the voice sound via execution of a speech recognition application to generate recognized speech associated with the vehicle impact; and
transmit the recognized speech to a computing device associated with the vehicle impact.
8. The computer device of claim 7 , wherein the sounds and video further comprise one or more of:
a text file, an image file, vehicle telemetry, environmental data, traffic data, and sensor data.
9. The computer device of claim 7 , wherein the sounds and video further comprise data related to one or more of:
ambient temperature, road conditions, weather, wind speed or direction, time of day, and light sources.
10. The computer device of claim 7 , wherein the sounds and video further comprise directions for the sounds, and
the processor is further configured to:
synchronize the sounds with the video based on the directions of the sounds.
11. The computer device of claim 7 , wherein the sound profile comprise:
a unique identifier of a respective sound;
a starting timestamp of the respective sound;
an ending timestamp of the respective sound; and
an indication of a source of the respective sound.
12. The computer device of claim 8 , wherein the processor is further configured to:
provide the sound profile to one of an emergency services provider or an insurance provider based on the determination.
13. A non-transitory computer readable medium comprising instructions that when executed by a processor cause the processor to perform:
receiving sounds and video captured before and after a vehicle impact from audio sensors of a plurality of different transports;
synchronizing the sounds with the video to generate synchronized content;
identifying a plurality of audio capturing sources of a plurality of sounds within the synchronized content, where the plurality of audio capturing sources are included within the plurality of different transports;
storing unique identifiers of the plurality of sounds and identifiers of the plurality of audio capturing sources of the plurality of sounds within a sound profile;
performing speech recognition on the voice sound via execution of a speech recognition application to generate recognized speech associated with the vehicle impact; and
transmitting the recognized speech to a computing device associated with the vehicle impact.
14. The non-transitory computer readable medium of claim 13 , wherein the sounds and video further comprise one or more of:
a text file, an image file, vehicle telemetry, environmental data, traffic data, and sensor data.
15. The non-transitory computer readable medium of claim 13 , wherein the sounds and video further comprise data related to one or more of:
ambient temperature, road conditions, weather, wind speed or direction, time of day, and light sources.
16. The non-transitory computer readable medium of claim 13 , wherein the sound profile comprise:
a unique identifier of a respective sound;
a starting timestamp of the respective sound;
an ending timestamp of the respective sound; and
an indication of a source of the respective sound.
17. The non-transitory computer readable medium of claim 13 , wherein the sounds further comprise directions of the sounds, and
wherein the synchronizing further comprises:
synchronizing the sounds with the video based on the directions of the sounds.