Speech-to-text processing assisted with language models for conversational ai systems and applications

A method comprising:

• generating a training input, wherein the training input comprises:
• a first portion comprising a training audio input in a first language,
• a second portion comprising a text context associated with the training audio input, and
• a third portion identifying a type of a speech-to-text (S2T) conversion of the training audio input to be generated using a machine learning model (MLM);
• and
• applying the training input to the MLM to generate a training output, wherein the training output comprises the S2T conversion of the training audio input, and wherein the MLM comprises:
• an audio model that processes the first portion and generates an intermediate output, and
• a language model (LM) that processes the intermediate output, the second portion, and the third portion;
• and
• using the training output and a ground truth associated with the training audio input to train the audio model.