Systems and Methods for Adding Punctuations

摘要

Systems and methods are provided for adding punctuations. For example, one or more first feature units are identified in a voice file taken as a whole; the voice file is divided into multiple segments: one or more second feature units are identified in the voice file; a first aggregate weight of first punctuation states of the voice file and a second aggregate weight of second punctuation states of the voice file are determined, using a language model established based on word separation and third semantic features; a weighted calculation is performed to generate a third aggregate weight based on at least information associated with the first aggregate weight and the second aggregate weight; and one or more final punctuations are added to the voice file based on at least information associated with the third aggregate weight.

主权项

1. A method for adding punctuations, the method comprising:
identifying one or more first feature units in a voice file taken as a whole based on at least information associated with one or more first words in the voice file and one or more first semantic features related to the first words; dividing the voice file into multiple segments based on at least information associated with a silence detection; identifying one or more second feature units in the voice file based on at least information associated with one or more second words in the segments and one or more second semantic features related to the second words; determining, using a language model established based on word separation and third semantic features, a first aggregate weight of first punctuation states of the voice file based on at least information associated with the first feature units and a second aggregate weight of second punctuation states of the voice file based on at least information associated with the second feature units; performing a weighted calculation to generate a third aggregate weight based on at least information associated with the first aggregate weight and the second aggregate weight; and adding one or more final punctuations to the voice file based on at least information associated with the third aggregate weight.