HEARING ASSISTANCE SYSTEM FOR PROVIDING CONSISTENT HUMAN SPEECH

• US 20120215532A1
• Filed: 02/22/2011
• Published: 08/23/2012
• Est. Priority Date: 02/22/2011
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Foo, Edwin W., Hughes, Gregory F.
• Granted Patent: US 8,781,836 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: H04R 25/505 using digital signal processing
• CPC Class Codes: H04R 25/554 using a wireless connection, e.g. between microphone and amplifier or using Tcoils

Abstract

Broadly speaking, the embodiments disclosed herein describe an apparatus, system, and method that allows a user of a hearing assistance system to perceive consistent human speech. The consistent human speech can be based upon user specific preferences.

Claims

1. A method performed by a portable computing device for providing consistent speech, wherein the portable computing device includes an audio processing component coupled with an audio input device, comprising:

(a) receiving human speech at the audio input device;

(b) converting the human speech to text;

(c) converting the text directly to a consistent speech using a text to speech protocol; and

(d) passing the consistent speech to an output device.

2. The method as recited in claim 1, further comprising:

presenting the consistent speech by the output device.

3. The method as recited in claim 2, further comprising:

receiving an end user evaluation of the consistent speech presented by the output device;

identifying the text to speech protocol as a preferred text to speech protocol when the evaluation indicates that the presented consistent speech is acceptable;

selecting another text to speech conversion protocol when the evaluation indicates that the presented consistent speech is not acceptable; and

repeating (c)-(d).

4. The method as recited in claim 3, wherein the output device is incorporated into a hearing aid and wherein the portable computing device is in wireless communication with the hearing aid.

5. The method as recited in claim 4, further comprising:

storing an indication of the preferred text to speech conversion protocol at the portable computing device.

6. A hearing assistance system, comprising:

a portable computing device, the portable computing device comprising;

a user input interface,

an audio input device arranged to receive human speech,

a speech consistency engine coupled to the audio input device, the speech consistency engine arranged to receive the human speech from the audio input device and condition the received human speech into consistent human speech, and

an interface arranged to facilitate the establishment of a communication link between the speech consistency engine and an output device, wherein the consistent human speech is passed from the speech consistency engine to the output device.

7. The hearing assistance system as recited in claim 6, wherein the consistent human speech is presented by the output device.

8. The hearing assistance system as recited in claim 7 wherein the output device is incorporated into a hearing aid physically apart from the portable computing device.

9. The hearing assistance system as recited in claim 8 wherein an end user provides an evaluation of the presented consistent human speech at the user input interface.

10. The hearing assistance system as recited in claim 9, wherein the end user provided evaluation is used by the portable computing device to update a text to speech protocol used by the speech consistency engine when the evaluation indicates that the presented consistent speech is not acceptable to the end user.

11. The hearing assistance system as recited in claim 10, wherein the end user provided evaluation is used by the portable computing device to identify the text to speech conversion protocol used by the speech consistency engine as a preferred text to speech conversion protocol when the evaluation indicates that the presented consistent speech is acceptable to the end user.

12. The hearing assistance system as recited in claim 11, wherein the speech consistency engine includes a speech to text (STT) engine used to convert the human speech to text and a text to speech (TTS) engine coupled to the SST engine used to convert the text to consistent human speech using the preferred text to speech conversion protocol.

13. The hearing assistance system as recited in claim 6, wherein the portable computing device is a smartphone.

14. Non-transitory computer readable medium for storing a computer program executable by a processor in a portable computing device for providing consistent speech, wherein the portable computing device includes an audio processing component coupled with an audio input device, comprising:

computer code for receiving human speech at the audio input device;

computer code for converting the human speech to text;

computer code for converting the text directly to a consistent speech using a text to speech protocol; and

computer code for passing the consistent speech to an output device.

15. The computer readable medium as recited in claim 14, further comprising:

computer code for presenting the consistent speech by the output device.

16. The computer readable medium as recited in claim 15, further comprising:

computer code for receiving an end user evaluation of the consistent speech presented by the output device;

computer code for identifying the text to speech protocol as a preferred text to speech protocol when the evaluation indicates that the presented consistent speech is acceptable;

computer code for selecting another text to speech conversion protocol when the evaluation indicates that the presented consistent speech is not acceptable; and

computer code for repeating the converting and passing.

17. The computer readable medium as recited in claim 16, wherein the output device is incorporated into a hearing aid and wherein the portable computing device is in wireless communication with the portable computing device.

18. A method of calibrating a hearing assistance system for providing a consistent human speech at an output device of the hearing assistance system, comprising:

(a) receiving a human speech calibration file at a venue, the human speech calibration file including at least an idiosyncratic human speech artifact;

(b) converting the human speech calibration file to the consistent human speech using at least a current consistent speech preference;

(c) receiving an evaluation of the consistent human speech; and

(d) associating the current consistent speech preference with the venue when the evaluation indicates that the consistent human speech is acceptable.

19. The method as recited in claim 18, further comprising:

updating the current consistent speech preference; and

repeating (b)-(d) until the evaluation indicates that the consistent human speech is acceptable.

20. The method as recited in claim 19, wherein the human speech calibration file includes a human speech presented at varying cadences and volume.

21. The method as recited in claim 18, wherein the processing device is a portable computing device in communication with the hearing aid.