Context-based decoder correction
Disclosed in some examples are methods, systems, and machine-readable mediums for utilizing context information to create decoding feedback information to improve decoder accuracy and/or performance. In some examples, the context information is from layers of a network stack above the layers in which the decoders are present. The context information may be or be based upon information about previously received and decoded data and/or information about the sender to provide decoding feedback information to the decoder that is used either to correct a previous decoding error or to inform the decoder on which of a plurality of decoding choices is more likely to be correct. This may increase decoding performance by decreasing errors and in some examples, reducing the complexity of choices by eliminating certain decoding possibilities and thus increasing decoder efficiency.
1 . A method of improving channel decoding performance using language checking or predictive text, the method comprising:
receiving, over a transmission medium, encoded text encoded with a channel code;
decoding, by a channel decoder, at least a portion of the encoded text to produce a decoded text portion;
running a language check on the decoded text portion to produce a corrected decoded text portion, or inputting the decoded text portion into a predictive text generator, the predictive text generator generating subsequent text to produce a predicted decoded next text portion, the language check comprising a spelling check or a grammar check;
eliminating at least one potential decoding possibility for a second portion of the encoded text by utilizing the predicted decoded next text portion or the corrected decoded text portion when decoding, by the decoder, the second portion of the encoded text to create a second decoded text portion; and
displaying the second decoded text portion of the encoded text on a display.
2 . The method of claim 1 , wherein eliminating at least one potential decoding comprises trimming a trellis by eliminating choices inconsistent with the encoded feedback information.
3 . The method of claim 1 , wherein spell checking the decoded text portion comprises utilizing context sensitive spell checking that scans a plurality of words to determine improper spelling.
4 . The method of claim 3 , wherein the context sensitive spell checking utilizes historical usage of a transmitting user.
5 . The method of claim 1 , wherein the predictive text generator utilizes historical word choices of a transmitting user.
6 . The method of claim 1 , wherein the decoder is a trellis decoder.
7 . The method of claim 1 , wherein the language check comprises determining a most probable word based upon a word frequency usage of a transmitting user.
8 . A computing device for improving channel decoding performance using language checking or predictive text, the computing device comprising:
a hardware processor;
a memory, storing instructions, which when executed by the hardware processor causes the computing device to perform operations comprising:
receiving, over a transmission medium, encoded text encoded with a channel code;
decoding, by a channel decoder, at least a portion of the encoded text to produce a decoded text portion;
running a language check on the decoded text portion to produce a corrected decoded text portion, or inputting the decoded text portion into a predictive text generator, the predictive text generator generating subsequent text to produce a predicted decoded next text portion, the language check comprising a spelling check or a grammar check;
eliminating at least one potential decoding possibility for a second portion of the encoded text by utilizing the predicted decoded next text portion or the corrected decoded text portion when decoding, by the decoder, the second portion of the encoded text to create a second decoded text portion; and
displaying the second decoded text portion of the encoded text on a display.
9 . The computing device of claim 8 , wherein the operations of eliminating at least one potential decoding comprises trimming a trellis by eliminating choices inconsistent with the encoded feedback information.
10 . The computing device of claim 8 , wherein the operations of spell checking the decoded text portion comprises utilizing context sensitive spell checking that scans a plurality of words to determine improper spelling.
11 . The computing device of claim 10 , wherein the context sensitive spell checking utilizes historical usage of a transmitting user.
12 . The computing device of claim 8 , wherein the predictive text generator utilizes historical word choices of a transmitting user.
13 . The computing device of claim 8 , wherein the decoder is a trellis decoder.
14 . The computing device of claim 8 , wherein the language check comprises determining a most probable word based upon a word frequency usage of a transmitting user.
15 . A machine-readable medium, storing instructions for improving decoding performance using language checking or predictive text, the instructions, which when executed, cause a machine to perform operations comprising:
receiving, over a transmission medium, encoded text encoded with a channel code;
decoding, by a channel decoder, at least a portion of the encoded text to produce a decoded text portion;
running a language check on the decoded text portion to produce a corrected decoded text portion, or inputting the decoded text portion into a predictive text generator, the predictive text generator generating subsequent text to produce a predicted decoded next text portion, the language check comprising a spelling check or a grammar check;
eliminating at least one potential decoding possibility for a second portion of the encoded text by utilizing the predicted decoded next text portion or the corrected decoded text portion when decoding, by the decoder, the second portion of the encoded text to create a second decoded text portion; and
displaying the second decoded text portion of the encoded text on a display.
16 . The machine-readable medium of claim 15 , wherein the operations of eliminating at least one potential decoding comprises trimming a trellis by eliminating choices inconsistent with the encoded feedback information.
17 . The machine-readable medium of claim 15 , wherein the operations of spell checking the decoded text portion comprises utilizing context sensitive spell checking that scans a plurality of words to determine improper spelling.
18 . The machine-readable medium of claim 17 , wherein the context sensitive spell checking utilizes historical usage of a transmitting user.
19 . The machine-readable medium of claim 15 , wherein the predictive text generator utilizes historical word choices of a transmitting user.
20 . The machine-readable medium of claim 15 , wherein the decoder is a trellis decoder.