최소 단어 이상 선택하여야 합니다.
최대 10 단어까지만 선택 가능합니다.
다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
NTIS 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
DataON 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Edison 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Kafe 바로가기국가/구분 | United States(US) Patent 등록 |
---|---|
국제특허분류(IPC7판) |
|
출원번호 | US-0032525 (2011-02-22) |
등록번호 | US-8781836 (2014-07-15) |
발명자 / 주소 |
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 | 피인용 횟수 : 3 인용 특허 : 515 |
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.
1. A method performed by a portable computing device for providing consistent speech, wherein the portable computing device includes a processor, memory and an audio processing component coupled with an audio input device, comprising: receiving human speech at the audio input device, the human speec
1. A method performed by a portable computing device for providing consistent speech, wherein the portable computing device includes a processor, memory and an audio processing component coupled with an audio input device, comprising: receiving human speech at the audio input device, the human speech including one or more inconsistent components;converting the human speech into consistent speech, including: converting the human speech to text; andconverting the text directly to consistent speech based at least in part on a text to speech protocol that renders at least one of the one or more inconsistent components consistent, wherein the one or more inconsistent components include varying speech patterns or speech artifacts; andpassing 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, wherein the text to speech protocol is a first text to speech protocol; and the method, further comprising: receiving an end user evaluation of the consistent speech presented by the output device;upon determining that the end user evaluation indicates that the presented consistent speech is acceptable, identifying the first text to speech protocol as a preferred text to speech protocol;upon determining that the end user evaluation indicates that the presented consistent speech is not acceptable: selecting a second text to speech conversion protocol, wherein the second text to speech protocol is different from the first speech to text protocol;converting the text directly to consistent speech based at least in part on the second speech to text protocol; andpassing the consistent speech based at least in part on the second speech to text protocol to the output device. 4. The method as recited in claim 1, 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 of 1, wherein the human speech and the consistent speech are in the same language. 6. The method of 1, wherein the consistent speech includes less than all of the one or more inconsistent components in the human speech. 7. The method of 1, further comprising, prior to the converting: determining a degree of consistency of the human speech;comparing the degree of consistency of the human speech to a predefined consistency threshold; andupon determining that the degree of consistency does not meet the predefined consistency threshold, performing the converting of the human speech into consistent speech. 8. The method of 7, wherein the comparing indicates an amount of processing and one or more types of processing required to convert the human speech into consistent speech. 9. A hearing assistance system, comprising: a portable computing device, comprising: a processor;memory;a user input interface;an audio input device arranged to receive human speech, the human speech including one or more inconsistent components;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 to condition the received human speech into consistent human speech, wherein the speech consistency engine includes: a speech to text (STT) engine arranged to convert the human speech to text; anda text to speech (TTS) engine coupled to the SST engine used to convert the text to consistent human speech based at least in part on a text to speech conversion protocol that renders at least one of the one or more inconsistent components consistent, wherein the one or more inconsistent components include varying speech patterns or speech artifacts; andan 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. 10. The hearing assistance system as recited in claim 9, wherein the consistent human speech is presented by the output device. 11. The hearing assistance system as recited in claim 9, wherein the output device is incorporated into a hearing aid physically apart from the portable computing device. 12. The hearing assistance system as recited in claim 10, wherein the user input interface is arranged to receive an end user evaluation of the presented consistent human speech; and wherein the portable computing device is arranged to: identify the text to speech conversion protocol used by the speech consistency engine as a preferred text to speech conversion protocol when the end user evaluation indicates that the presented consistent speech is acceptable to the end user; andupdate the text to speech protocol used by the speech consistency engine when the end user evaluation indicates that the presented consistent speech is not acceptable to the end user. 13. The hearing assistance system of claim 9, wherein the received human speech and the consistent human speech are in the same language. 14. The hearing assistance system of claim 9, wherein the consistent human speech includes less than all of the one or more inconsistent components in the received human speech. 15. The hearing assistance system of claim 9, wherein, prior to the conditioning, the speech consistency engine is arranged to: determine a degree of consistency of the received human speech;compare the degree of consistency of the received human speech to a predefined consistency threshold; andupon determining that the degree of consistency does not meet the predefined consistency threshold, perform the conditioning of the received human speech into consistent human speech. 16. The hearing assistance system of claim 15, wherein the comparing indicates an amount of processing and one or more types of processing required to convert the received human speech into consistent human speech. 17. A 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, the computer readable medium comprising: computer code for receiving human speech at the audio input device, the human speech including one or more inconsistent components;computer code for converting the human speech into consistent speech, including: computer code for converting the human speech to text; andcomputer code for converting the text directly to consistent speech based at least in part on a text to speech protocol that renders at least one of the one or more inconsistent components consistent, wherein the one or more inconsistent components include varying speech patterns or speech artifacts; andcomputer code for passing the consistent speech to an output device. 18. The computer readable medium as recited in claim 17, further comprising: computer code for presenting the consistent speech by the output device. 19. The computer readable medium as recited in claim 18, wherein the text to speech protocol is a first text to speech protocol; and the computer readable medium, further comprising: computer code for receiving an end user evaluation of the consistent speech presented by the output device;computer code for identifying the first text to speech protocol as a preferred text to speech protocol when the end user evaluation indicates that the presented consistent speech is acceptable;computer code for selecting a second text to speech conversion protocol when the end user evaluation indicates that the presented consistent speech is not acceptable;computer code for converting the text directly to consistent speech based at least in part on the second speech to text protocol; andcomputer code for passing the consistent speech based at least in part on the second speech to text protocol to the output device. 20. The computer readable medium as recited in claim 17, 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. 21. The computer readable medium of claim 17, wherein the human speech and the consistent speech are in the same language. 22. The computer readable medium of claim 17, wherein the consistent speech includes less than all of the one or more inconsistent components in the human speech. 23. The computer readable medium of claim 17, further comprising: computer code for, prior to the converting, determining a degree of consistency of the human speech;computer code for, prior to the converting, comparing the degree of consistency of the human speech to a predefined consistency threshold; andcomputer code for, prior to the converting, performing the converting of the human speech into consistent speech when the degree of consistency does not meet the predefined consistency threshold. 24. The computer readable medium of claim 23, wherein the comparing indicates an amount of processing and one or more types of processing required to convert the human speech into consistent speech.
Copyright KISTI. All Rights Reserved.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.