Ocr through voice recognition

Patent metadata

Field	Value
Publication number	US-2016253992-A1
Application number	US-201514633875-A
Country	US
Kind code	A1
Filing date	Feb 27, 2015
Priority date	Feb 27, 2015
Publication date	Sep 1, 2016
Grant date	—

Abstract

One embodiment provides a method, including: receiving, at an input and display device, handwriting input; receiving, using a processor, voice input; generating, using a processor, at least one first word based on the handwriting input; generating, using a processor, at least one second word based on the voice input; and determining, using a processor, a highest probability word based on the at least one first word and the at least one second word. Other aspects are described and claimed.

First claim

What is claimed is:

1 . A method, comprising:
receiving, at an input and display device, handwriting input; receiving, using a processor, voice input; generating, using a processor, at least one first word based on the handwriting input; generating, using a processor, at least one second word based on the voice input; and determining, using a processor, a highest probability word based on the at least one first word and the at least one second word.

2 . The method of claim 1 , further comprising:
displaying, on the input and display device, at least one high probability word prior to the handwriting input being complete.

3 . The method of claim 2 , further comprising:
receiving user input selecting one of the at least one high probability words.

4 . The method of claim 1 , wherein the voice input comprises receiving a verbal representation of the handwriting input being substantially concurrently input.

5 . The method of claim 1 , wherein the voice input comprises receiving a general discussion relating to the handwriting input being substantially concurrently input.

6 . The method of claim 1 , wherein the voice input comprises receiving a lecture relating to the handwriting input being substantially concurrently input.

7 . The method of claim 1 , further comprising:
storing, on a memory device, a recording of the voice input.

8 . The method of claim 7 , wherein the highest probability word is linked to a retrievable time in the recording of the voice input.

9 . The method of claim 1 , further comprising:
weighting, using the processor, each of the words from the at least one first word based on a handwriting recognition score; and weighting, using the processor, each of the words from the at least one second word based on a voice recognition score.

10 . The method of claim 9 , wherein the highest probability word is determined using a combination of the weighting of the at least one first word and the at least one second word.

11 . An information handling device, comprising:
an input device; a display device; an audio capture device; a processor; a memory device that stores instructions executable by the processor to: receive handwriting input; receive voice input; generate at least one first word based on the handwriting input; generate at least one second word based on the voice input; and determine a highest probability word based on the at least one first word and the at least one second word.

12 . The information handling device of claim 11 , further comprising:
displaying, on the input and display device, at least one high probability words prior to the handwriting input being complete.

13 . The information handling device of claim 11 , wherein the voice input comprises receiving a verbal representation of the handwriting input being substantially concurrently input.

14 . The information handling device of claim 11 , wherein the voice input comprises receiving a general discussion relating to the handwriting input being substantially concurrently input.

15 . The information handling device of claim 11 , wherein the voice input comprises receiving a lecture relating to the handwriting input being concurrently input.

16 . The information handling device of claim 11 , further comprising:
storing, on the memory device, a recording of the voice input.

17 . The information handling device of claim 16 , wherein the highest probability word is linked to a retrievable time in the recording of the voice input.

18 . The information handling device of claim 11 , further comprising:
weighting, using the processor, each of the words from the at least one first word based on a handwriting recognition score; and weighting, using the processor, each of the words from the at least one second word based on a voice recognition score.

19 . The information handling device of claim 18 , wherein the highest probability word is determined using a combination of the weighting of the at least one first word and the at least one second word.

20 . A product, comprising:
a storage device having code stored therewith, the code being executable by a processor and comprising: code that receives, at an input and display device, handwriting input; code that receives voice input; code that generates at least one first word based on the handwriting input; code that generates at least one second word based on the voice input; and code that determines a highest probability word based on the at least one first word and the at least one second word.

Assignees

• Lenovo Singapore Pte Ltd

Inventors

• Raux Antoine Roland
• Zaitsev Grigori
• Vanblon Russell Speight
• Zhang Jianbang

Classifications

• G06K9/00402

  Physics · mapped topic

• G10L15/08 Primary

  Speech classification or search · CPC title

• G10L15/32 Primary

  Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems · CPC title

• G10L2015/226

  using non-speech characteristics · CPC title

• G06V30/32 Primary

  Digital ink · CPC title