Prosodic hierarchy labeling method and model training method and device

A technology of prosodic hierarchy and labeling models, which is applied in speech synthesis, speech analysis, instruments, etc., can solve problems such as short pauses without considering the length of time, affecting the quality of the speech synthesis corpus, and difficulty in simultaneously labeling the three-layer prosody hierarchy.

A technology of prosodic hierarchy and labeling models, which is applied in speech synthesis, speech analysis, instruments, etc., can solve problems such as short pauses without considering the length of time, affecting the quality of the speech synthesis corpus, and difficulty in simultaneously labeling the three-layer prosody hierarchy.

CN109697973APending Publication Date: 2019-04-30SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV +1
0 Cites 24 Cited by

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Prosodic hierarchy labeling method and model training method and device
  • Prosodic hierarchy labeling method and model training method and device
  • Prosodic hierarchy labeling method and model training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0092] Embodiments of the present invention provide a prosodic level labeling method, model training method and device, and combine text features and acoustic features to establish a prosodic level labeling model, which can provide richer features for prosodic level labeling and use more accurate prosody The hierarchical labeling model can improve the accuracy of prosodic labeling and improve the effect of speech synthesis.

[0093] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of practice in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "cor...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a prosodic hierarchy labeling method. The method comprises the steps as follows: acquiring to-be-labeled text data and audio data which have a corresponding relation; extracting a to-be-labeled text characteristic set of each word according to the to-be-labeled text data; extracting an acoustic characteristic set of each word according to the audio data; acquiring a prosodic hierarchy structure by a prosodic hierarchy labeling model according to a word identification of each word, the to-be-labeled text characteristic set of each word and the acoustic characteristic setof each word. The invention also discloses a model training method, a prosodic hierarchy labeling device and a model training device. The prosodic hierarchy labeling model is established by combination of text characteristics and acoustic characteristics, richer characteristics can be provided for prosodic hierarchy labeling, the prosodic hierarchy labeling accuracy can be improved, and the voicesynthesis effect can be enhanced.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a prosody-level labeling method, a model training method and related devices. Background technique [0002] In order to realize a high-quality speech synthesis system, it is very important to accurately label a large amount of data with a prosodic hierarchical structure. The prosodic hierarchical structure is to model the rhythm of the speech and its pauses. A method that can accurately and automatically label the prosodic hierarchical structure is helpful for fast It is of great significance to build a speech synthesis corpus and improve the naturalness of speech synthesis. [0003] At present, the automatic labeling of the prosodic hierarchical structure needs to use machine learning methods to train an automatic labeling model. There are two main types of feature selection. One is to use text features, first segment words, and then extract text features of words,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
30 Apr 2019
Publication
CN109697973A
IPC
G10L13/02; G10L13/08; G10L13/10
CPC
G10L13/02; G10L13/08; G10L13/10
Inventors
吴志勇; 杜耀