Hearing assistance system for providing consistent human speech
First Claim
Patent Images
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; and
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; and
passing the consistent speech to an output device.
2 Assignments
0 Petitions
Accused Products
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.
690 Citations
24 Claims
-
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; and 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; and passing the consistent speech to an output device. - View Dependent Claims (2, 3, 4)
-
-
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; and upon 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; and a 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; 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. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
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; and computer 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; and computer code for passing the consistent speech to an output device. - View Dependent Claims (18, 19, 20, 21, 22, 23, 24)
-
Specification