Speech fluency evaluation and feedback
Speech fluency evaluation and feedback tools are described. A computing device such as a smartphone may be used to collect speech (and/or other data). The collected data may be analyzed to detect various speech events (e.g., stuttering) and feedback may be generated and provided based on the detected speech events. The collected data may be used to generate a fluency score or other performance metric associated with speech. Collected data may be provided to a practitioner such as a speech therapist or physician for improved analysis and/or treatment.
1. A device, comprising:
one or more processors configured to:
collect audio data;
extract speech information from the collected audio data;
extract environment information from the collected audio data;
analyze the extracted speech information and the extracted environment information;
identify at least one speech event based on the analysis of the extracted speech information and the extracted environment information; and
generate a performance metric based at least partly on the at least one speech event.
2. The device of claim 1 , wherein analyzing the extracted speech information comprises application of a speech pattern model.
3. The device of claim 1 , wherein analyzing the extracted speech information comprises transforming the extracted speech information from a time domain to a frequency domain.
4. The device of claim 1 , wherein the one or more processors are further configured to provide feedback associated with the at least one speech event wherein providing feedback comprises at least one of displaying text, displaying graphics, and providing haptic feedback.
5. The device of claim 4 , wherein feedback is provided in real time during collection of audio data.
6. The device of claim 1 , wherein collecting audio data comprises capturing audio received via a user device microphone.
7. The device of claim 1 , wherein the performance metric comprises a fluency score calculated by dividing fluent speech by total speech.
8. A non-transitory computer-readable medium, storing a plurality of processor executable instructions to:
collect audio data;
extract speech information from the collected audio data;
extract environment information from the collected audio data;
analyze the extracted speech information and the extracted environment information;
identify at least one speech event based on the analysis of the extracted speech information and the extracted environment information; and
generate a performance metric based at least partly on the at least one speech event.
9. The non-transitory computer-readable medium of claim 8 , wherein analyzing the extracted speech information comprises application of a speech pattern model.
10. The non-transitory computer-readable medium of claim 8 , wherein analyzing the extracted speech information comprises transforming the extracted speech information from a time domain to a frequency domain.
11. The non-transitory computer-readable medium of claim 8 , wherein the plurality of processor-executable instructions are further to provide feedback associated with the at least one speech event wherein providing feedback comprises at least one of displaying text, displaying graphics, and providing haptic feedback.
12. The non-transitory computer-readable medium of claim 11 , wherein feedback is provided in real time during collection of audio data.
13. The non-transitory computer-readable medium of claim 8 , wherein collecting audio data comprises capturing audio received via a user device microphone.
14. The non-transitory computer-readable medium of claim 8 , wherein the performance metric comprises a fluency score calculated by dividing fluent speech by total speech.
15. A method comprising:
collecting audio data;
extracting speech information from the collected audio data;
extracting environment information from the collected audio data;
analyzing the extracted speech information and the extracted environment information;
identifying at least one speech event based on the analysis of the extracted speech information and the extracted environment information; and
generating a performance metric based at least partly on the at least one speech event.
16. The method of claim 15 , wherein analyzing the extracted speech information comprises application of a speech pattern model.
17. The method of claim 15 , wherein analyzing the extracted speech information comprises transforming the extracted speech information from a time domain to a frequency domain.
18. The method of claim 15 further comprising providing feedback associated with the at least one speech event, wherein providing feedback comprises at least one of displaying text, displaying graphics, and providing haptic feedback, and wherein feedback is provided in real time during collection of audio data.
19. The method of claim 15 , wherein collecting audio data comprises capturing audio received via a user device microphone.
20. The method of claim 15 , wherein the performance metric comprises a fluency score calculated by dividing fluent speech by total speech.