Method and apparatus for recognizing speech by lip reading

• US 9,741,342 B2
• Filed: 08/13/2015
• Issued: 08/22/2017
• Est. Priority Date: 11/26/2014
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Inventors: Takayanagi, Yuichiro, Kusaka, Masashi
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Le, Thuykhanh
• Application Number:
  US14/826,151
• Publication Number:
  US 20160148616A1
• Time in Patent Office: 740 Days
• Field of Search: None
• CPC Class Codes: G10L 15/25 using position of the lips, movement of the lips or face analysis
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

A dictation device includes: an audio input device configured to receive a voice utterance including a plurality of words; a video input device configured to receive video of lip motion during the voice utterance; a memory portion; a controller configured according to instructions in the memory portion to generate first data packets including an audio stream representative of the voice utterance and a video stream representative of the lip motion; and a transceiver for sending the first data packets to a server end device and receiving second data packets including combined dictation based upon the audio stream and the video stream from the server end device. In the combined dictation, first dictation generated based upon the audio stream has been corrected by second dictation generated based upon the video stream.

Claims

1. A dictation device comprising:

an audio input device configured to receive a voice utterance including a plurality of words;

a video input device configured to receive video of lip motion during the voice utterance;

a memory portion;

a controller configured according to instructions in the memory portion to generate first data packets including an audio stream representative of the voice utterance and a video stream representative of the lip motion; and

a transceiver for sending the first data packets to a remote apparatus and receiving second data packets including combined dictation based upon the audio stream and the video stream from the remote apparatus,

wherein in the combined dictation, at least one word in first dictation generated based upon the audio stream which has a predetermined characteristic has been corrected by second dictation generated based upon the video stream,

wherein the controller uses the second dictation when a user disable the audio input device,

wherein the controller uses the first dictation when a number of syllables in a word in first dictation is greater than a threshold, and uses the second dictation when the number of syllable in the word in first dictation is equal or less than the threshold.

2. The dictation device of claim 1, further comprising a display, wherein the controller is further configured to render the combined dictation as text on the display.

3. The dictation device of claim 1, wherein the transceiver is further configured to send the second data packets to a downstream application.

4. A server end device comprising:

a transceiver configured to receive first data packets from and send second data packets to a remote mobile station via a connection to a network;

an interface for adding formatting information to the second data packets to be sent and removing formatting information from received first data packets, the received first data packets including an audio stream and a video stream associated with a voice utterance of a plurality of words;

a controller coupled to the interface;

an audio based speech recognition device coupled to the controller and configured to generate first dictation based upon the audio stream received from the remote mobile station;

a video based speech recognition device coupled to the controller and configured to generate second dictation based upon the video stream received from the remote mobile station; and

a memory including instructions for configuring the controller to generate a combined dictation based upon a comparison between the first dictation and the second dictation and include the combined dictation in the second data packets to be sent,

wherein the controller is further configured to;

determine if at least one of the words in the first dictation has a predetermined characteristic; and

generate the combined dictation based upon the second dictation for the at least one of the words having the predetermined characteristic and based upon the first dictation for the other of the plurality of words,

wherein the controller uses the first dictation when a number of syllables in a word in first dictation is greater than a threshold, and uses the second dictation when the number of syllable in the word in first dictation is equal or less than the threshold.

5. The server end device of claim 4, wherein the predetermined characteristic is that the at least one word is not similar to the corresponding at least one word in the second dictation.

6. The server end device of claim 4, wherein the predetermined characteristic is further the at least one word has less than a predetermined number of syllables or less than a predetermined length or time duration.

7. The server end device of claim 4, wherein the audio based speech recognition device generates the first dictation by:

extracting a feature signal associated with the audio stream;

for each of a plurality of candidate prototype words, determining the probability that the respective candidate prototype word generates the feature signal; and

choosing the candidate prototype word having highest probability among the plurality of candidate prototype words,

wherein the predetermined characteristic is that the probability associated with the chosen candidate prototype word is less than a predetermined standard.

8. The server end device of claim 4, wherein the video based speech recognition device generates the second dictation based upon the video stream by:

extracting a sequence of image frames from a predetermined portion of the video stream;

generating a local binary pattern (LBP) from a series of images;

matching the LBP to a feature signal vector stored in the memory;

determining a probability for each of a plurality of candidate prototype words generating the feature signal vector;

selecting a candidate prototype word of the plurality of candidate prototype words of highest probability to be the second dictation.

9. A system for performing speech-to-text services comprising:

the server end device of claim 4,

wherein the remote mobile station includes;

an audio input device configured to receive the voice utterance including the plurality of words;

a video input device configured to receive video of lip motion during the voice utterance;

a memory portion;

a controller configured according to instructions in the memory portion to generate first data packets including the audio stream which is representative of the voice utterance and the video stream which is representative of the lip motion; and

a transceiver for sending the first data packets to the server end device and receiving second data packets including the combined dictation from the server end device.

10. A dictation device for generating text based on a voice utterance and lip movement associated with the voice utterance, comprising:

an audio input device that receives an audio signal representing the voice utterance;

a video input device that receives a video signal representative of the lip movement;

a controller configured according to instructions stored in a memory, the controller configured to;

generate a first dictation based on the audio signal and assign a first conversion value based on a first set of conversion criteria;

generate a second dictation based on the video signal and assign a second conversion value based on a second set of conversion criteria; and

generate a variable text conversion value based on the first conversion value and the second conversion value and generate a third dictation based on the variable text conversion value,

wherein the controller is configured to prioritize either the first conversion value or the second conversion value by a predetermined setting,

wherein the controller generates the variable text conversion value based on the first conversion value when a number of syllables in a word in first dictation is greater than a threshold, and based on the second conversion value when the number of syllable in the word in first dictation is equal or less than the threshold.

11. The dictation device of claim 10, wherein:

the audio input device is disabled when a signal to noise ratio between the audio signal and a background noise is below a predetermined threshold; and

the video input device is disabled when a signal to brightness ratio is below a predetermined threshold.

12. The dictation device of claim 10, wherein if the volume of the audio signal is lower than a predetermined value, the controller generates the variable text conversion value without the first conversion value.

13. The dictation device of claim 10, wherein when the video input device detects no lip movement, the audio input device is disabled.

14. The dictation device of claim 10, wherein the controller generates the variable text conversion value based on global positioning system (GPS) data.

15. The dictation device of claim 10, wherein:

the first set of conversion criteria includes pre-registered data representing a value associated with the user voice; and

the second set of conversion criteria includes pre-registered data representing a value associated with the user voice.

16. The dictation device of claim 10, wherein the variable text conversion value is generated based on a predetermined criteria which includes pre-registered data representing a value of the user voice.

17. The dictation device of claim 10, wherein the predetermined setting can be assigned by a user.

18. The dictation device of claim 10, wherein the controller generates the second dictation based on the video signal by:

extracting a sequence of image frames from a predetermined portion of the video signal;

generating a local binary pattern (LBP) from a series of images;

matching the LBP to a feature signal vector stored in the memory;

determining a probability for each of a plurality of candidate prototype words generating the feature signal vector;

selecting a candidate prototype word of the plurality of candidate prototype words of highest probability to be the second dictation.