Abstract: A system and method of speech transcription may include applying a machine-learning (ML) based encoder module to an audio data element representing a recording of speech, to obtain one or more encoding vectors, representing said recording in an audio encoding space. Embodiments of the invention may include performing an iterative transcription process on the one or more encoding vectors, to generate a token sequence representing a transcription of the recording. In each iteration, an ML-based multilayered decoder may be inferred on (i) the one or more encoding vectors and (ii) a current version of the token sequence, to a candidate token set that includes two or more candidate tokens, each representing a transcription of a respective word in the recording. The two or more candidate tokens may be appended to the current version of the token sequence, thereby updating the token sequence for a subsequent iteration.

Abstract: There is provided a system and method of data prediction. The method includes obtaining a hierarchical data structure comprising a plurality of layers, each including one or more nodes; obtaining one or more machine learning (ML) models each corresponding to a respective node of at least some of the nodes in at least a given layer, in response to a user's request of prediction related to a given node in the given layer; generating a prediction result using a given ML model corresponding to the given node; upon receiving the user's feedback, selecting one or more configuration parameters of the given ML model related to the feedback; updating the selected configuration parameters according to additional factors in the feedback, and re-training the given ML model to obtain a re-trained ML model,—and using the re-trained ML model to generate an updated prediction result to be sent to the user.