Context-based dictionaries for multimedia audiobook systems including linguistic dictionary entries

A non-transitory computer-readable storage medium storing instructions for presenting context-based dictionaries in a multimedia device, the instructions when executed by a processor causing the processor to perform steps including:

• obtaining a multimedia file including speech content;
• obtaining at least one text file comprising first text corresponding to the speech content;
• obtaining synchronization metadata associated with the multimedia file and the at least one text file, the synchronization metadata specifying correspondence between respective word chunks of the speech content, and the first text;
• obtaining, for the respective word chunks, external reference data from one or more reference sources that at least includes respective definitions associated with each of the respective word chunks, wherein each of the definitions includes one or more word senses;
• performing a part-of-speech and semantic analysis of the respective word chunks to contextually rank the one or more word senses from the external reference data for each of the respective word chunks based at least in part on respective usage contexts of the respective word chunks in at least one of the speech content and the first text;
• generating a set of attributes corresponding to the respective word chunks, wherein the set of attributes for a word chunk includes at least a highest contextually ranked word sense for the word chunk and a position of the word chunk in the first text;
• generating one or more context-based dictionary entries for a context-based dictionary, the context-based dictionary entries including linguistic dictionary entries corresponding to the respective word chunks, the linguistic dictionary entries including the set of attributes corresponding to the respective word chunks;
• storing the one or more context-based dictionary entries to a storage medium associated with the context-based dictionary;
• outputting the multimedia file and the at least one text file to a multimedia device to enable the multimedia device to concurrently present the first text of the at least one text file in a text display window of a user interface screen in synchronization with the speech content of the multimedia file;
• while presenting the first text in synchronization with the speech content, obtaining, from the multimedia device, an input selecting a first word chunk in the first text;
• identifying a first entry from the context-based dictionary matching the first word chunk in the first text;
• and
• outputting the first entry including the set of attributes based on the respective usage contexts for presentation in a context-based dictionary window of the user interface screen displayed concurrently with the text display window on a display of the multimedia device.

A multimedia device comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium storing instructions for presenting context-based dictionaries in the multimedia device, the instructions when executed by the processor causing the processor to perform steps including:
• obtaining a multimedia file including speech content;
• obtaining at least one text file comprising first text corresponding to the speech content;
• obtaining synchronization metadata associated with the multimedia file and the at least one text file, the synchronization metadata specifying correspondence between respective word chunks of the speech content, and the first text;
• obtaining, for the respective word chunks, external reference data from one or more reference sources that at least includes respective definitions associated with each of the respective word chunks, wherein each of the definitions includes one or more word senses;
• performing a part-of-speech and semantic analysis of the respective word chunks to contextually rank the one or more word senses from the external reference data for each of the respective word chunks based at least in part on respective usage contexts of the respective word chunks in at least one of the speech content and the first text;
• generating a set of attributes corresponding to the respective word chunks, wherein the set of attributes for a word chunk includes at least a highest contextually ranked word sense for the word chunk and a position of the word chunk in the first text;
• generating one or more context-based dictionary entries for a context-based dictionary, the context-based dictionary entries including linguistic dictionary entries corresponding to the respective word chunks, the linguistic dictionary entries including the set of attributes corresponding to the respective word chunks;
• storing the one or more context-based dictionary entries to a storage medium associated with the context-based dictionary;
• outputting the multimedia file and the at least one text file to a multimedia device to enable the multimedia device to concurrently present the first text of the at least one text file in a text display window of a user interface screen in synchronization with the speech content of the multimedia file;
• while presenting the first text in synchronization with the speech content, obtaining, from the multimedia device, an input selecting a first word chunk in the first text;
• identifying a first entry from the context-based dictionary matching the first word chunk in the first text;
• and
• outputting the first entry including the set of attributes based on the respective usage contexts for presentation in a context-based dictionary window of the user interface screen displayed concurrently with the text display window on a display of the multimedia device.