US 12,135,958 B2
Attributing meaning to utterance terms based on context
Rahul Pandita, Arvada, CO (US); Priyankar Kumar, New Delhi (IN); Aneesh Bose, West Bengal (IN); and Abhishek Masand, Ithaca, NY (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jan. 12, 2023, as Appl. No. 18/096,466.
Claims priority of provisional application 63/420,887, filed on Oct. 31, 2022.
Prior Publication US 2024/0143289 A1, May 2, 2024
Int. Cl. G10L 15/183 (2013.01); G06F 8/33 (2018.01); G06F 9/445 (2018.01); G06F 9/455 (2018.01); G06F 16/33 (2019.01); G06F 40/20 (2020.01); G10L 15/22 (2006.01); G10L 15/26 (2006.01)
CPC G06F 8/33 (2013.01) [G10L 15/26 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for facilitating voice based dictation of programming code within a context of an integrated development environment (IDE) such that vocabulary specific to the programming code is recognizable, said method comprising:
feeding programming code to a text-to-speech (TTS) model, wherein the TTS model generates at least one audio file that is associated with the programming code;
feeding the at least one audio file to a speech-to-text (STT) model, wherein the STT model generates at least one transcription file that is associated with the at least one audio file;
mapping each respective line of code included in the programming code to a corresponding line of code included in the at least one transcription file, resulting in generation of a list of phrase pairings, where the phrase pairings represent relationships between actual code and how that actual code sounds if read out loud; and
causing a large language model (LLM) to ingest the list of phrase pairings, wherein the LLM identifies correlations between programming vocabulary that has specific meaning within the context of the IDE and how that programming vocabulary sounds if read out loud.