Prosodic hierarchy annotation method and device

Abstract

The invention discloses a prosodic hierarchy annotation method and a prosodic hierarchy annotation device. The prosodic hierarchy annotation method comprises the steps of: S1, acquiring a text sequence; S2, segmenting the text sequence into a plurality of participles, and extracting features of the participles; S3, regarding the features as input, and acquiring corresponding output results based on a two-way long / short-term memory model; and S4, annotating prosodic hierarchies of the text sequence according to the output results. According to the prosodic hierarchy annotation method and the prosodic hierarchy annotation device disclosed by the embodiment of the invention, the prosodic hierarchies are annotated based on the two-way long / short-term memory model, the problem of limited extension range of contextual features of the participles in the text sequence is effectively solved, and the prosodic hierarchies are annotated at one time, thus the problem of error transfer in annotation can be avoided.

Description

Technical field [0001] The present invention relates to the technical field of text-to-speech conversion, and in particular to a method and device for prosodic level marking. Background technique [0002] Speech synthesis, also known as text-to-speech technology, is a technology that can convert text information into speech and read it aloud. The main evaluation indexes of speech synthesis system performance mainly include intelligibility and fluency. The existing speech synthesis system has basically matured in terms of intelligibility, but there is still a certain gap between the fluency and the real pronunciation of people. The key factor affecting the fluency of the speech synthesis system is the accuracy of prosodic level prediction. The method of prosody-level prediction mainly uses the characteristics of people's pause in pronunciation, and divides the prosody into different prosody levels according to the length of the pause. The prosodic hierarchy usually includes pro...

AI Technical Summary

Problems solved by technology

For this reason, an object of the present invention is to propose a prosodic level labeling method, which is based on a two-way long-short-term memory model to label the prosodic level, effectively solving the problem of limited expansion of the contextual features of word segmentation in text sequences, and once Prosodic labeling of the prosodic level, avoiding the problem of wrong transmission during labeling

Images