Recognizing handwritten text by combining neural networks

A computing device, comprising:

• a processor;
• and
• a memory storing instructions that, when executed by the processor, configure the processor to:
• receive data representing the user input, the data comprising a sequence of ink points;
• apply the received data to a neural network-based sequence classifier trained with a Connectionist Temporal Classification (CTC) output layer using forced alignment to generate an output, wherein the output of the CTC output layer comprises, for a given character of a pre-defined alphabet, the probabilities of observing the given character at each ink point of the sequence of ink points;
• generate a character hypothesis as a portion of the sequence of ink points;
• apply the character hypothesis to a character classifier to obtain a first probability corresponding to the probability that the character hypothesis includes the given character;
• process the output of the CTC output layer to determine a second probability corresponding to the probability that the given character is observed within the character hypothesis;
• and
• combine the first probability and the second probability to obtain a combined probability corresponding to the probability that the character hypothesis includes the given character.

A non-transitory computer-readable storage medium having instructions embodied thereon, the instructions being executable by one or more processors to perform a method for recognizing handwritten text in user input applied onto a touch-based user interface, comprising:

• receiving data representing the user input, the data comprising a sequence of ink points;
• applying the received data to a neural network-based sequence classifier trained with a Connectionist Temporal Classification (CTC) output layer using forced alignment to generate an output, wherein the output of the CTC output layer comprises, for a given character of a pre-defined alphabet, the probabilities of observing the given character at each ink point of the sequence of ink points;
• generating a character hypothesis as a portion of the sequence of ink points;
• applying the character hypothesis to a character classifier to obtain a first probability corresponding to the probability that the character hypothesis includes the given character;
• processing the output of the CTC output layer to determine a second probability corresponding to the probability that the given character is observed within the character hypothesis;
• and
• combining the first probability and the second probability to obtain a combined probability corresponding to the probability that the character hypothesis includes the given character.