Virtual reality guide hypnosis speech processing method and apparatus

Patent metadata

Field	Value
Publication number	US-10665221-B2
Application number	US-201715856349-A
Country	US
Kind code	B2
Filing date	Dec 28, 2017
Priority date	Sep 29, 2016
Publication date	May 26, 2020
Grant date	May 26, 2020

Abstract

A virtual reality guide hypnosis speech processing method and apparatus, wherein the method comprises: performing a text analysis for a hypnosis guide language, so as to obtain text hierarchical information of the hypnosis guide language; performing a speech analysis for the hypnosis guide language, so as to obtain speech rhythm information of the hypnosis guide language; searching a hypnosis speech library for corresponding speech units, according to the text hierarchical information and the speech rhythm information of the hypnosis guide language, the hypnosis speech library storing speech units generated according to corpus data recorded by a user's susceptible person; synthesizing found speech units into hypnosis speech data; and synthesizing the hypnosis speech data with a virtual reality hypnosis scene, and outputting a virtual reality guide hypnosis speech. The present disclosure can improve the user's hypnosis susceptibility and optimize the hypnosis effect.

First claim

What is claimed is:

1. A virtual reality guide hypnosis speech processing method, comprising:
performing a text analysis for a hypnosis guide language, so as to obtain text hierarchical information of relations between words, word groups and sentences in the hypnosis guide language;
performing a speech analysis for the hypnosis guide language, so as to obtain speech rhythm information in a phonetic level of the hypnosis guide language;
searching a hypnosis speech library for corresponding speech units, according to the text hierarchical information and the speech rhythm information of the hypnosis guide language, the hypnosis speech library storing speech units generated according to corpus data recorded by a user's susceptible person;
synthesizing found speech units into hypnosis speech data; and
synthesizing the hypnosis speech data with a virtual reality hypnosis scene, and outputting a virtual reality guide hypnosis speech;
wherein,
the text analysis for the hypnosis guide language comprises analyzing at least one of aspects of language level, grammatical level, and semantic level of the hypnosis guide language;
the speech analysis for the hypnosis guide language comprises analyzing at least one of timbre, intonation, and loudness of sounds corresponding to the hypnosis guide language; and
the hypnosis speech library is established and updated in real time according to the corpus data recorded by the user's susceptible person.

2. The method according to claim 1 , wherein the corpus data is recorded by the user's susceptible person according to hypnosis speech features, and/or the corpus data is recorded by the user's susceptible person at a specified sampling rate and speech resolution.

3. The method according to claim 1 , wherein the corpus data is recorded by the user's susceptible person with a dialect, and/or the corpus data is recorded by the user's susceptible person with a personalized language.

4. The method according to claim 1 , wherein a Hidden Markov Model is used to divide the corpus data in the hypnosis speech library, so as to construct the speech units; and
wherein synthesizing found speech units into hypnosis speech data comprises using the Hidden Markov Model to select, splice and synthesize the found speech units.

5. A virtual reality guide hypnosis speech processing apparatus, comprising:
a memory,
a processor and
a computer program stored in the memory and executable in the processor,
wherein the processor performs the following operations when executing the computer program:
performing a text analysis for a hypnosis guide language, so as to obtain text hierarchical information of relation s between words, word groups and sentences in the hypnosis guide language;
performing a speech analysis for the hypnosis guide language, so as to obtain speech rhythm information in a phonetic level of the hypnosis guide language;
searching a hypnosis speech library for corresponding speech units, according to the text hierarchical information and the speech rhythm information of the hypnosis guide language, the hypnosis speech library storing speech units generated according to corpus data recorded by a user's susceptible person;
synthesizing found speech units into hypnosis speech data; and
synthesizing the hypnosis speech data with a virtual reality hypnosis scene, and outputting a virtual reality guide hypnosis speech;
wherein,
the text, analysis for the hypnosis guide language comprises analyzing at least one of aspects of language level, grammatical level, and semantic level of the hypnosis guide language;
the speech analysis for the hypnosis guide language comprises analyzing at least one of timbre, intonation, and loudness of sounds corresponding to the hypnosis guide language; and
the hypnosis speech library is established and updated in real time according to the corpus data recorded by the user's susceptible person.

6. The apparatus according to claim 5 , wherein the corpus data is recorded by the user's susceptible person according to hypnosis speech features, and/or the corpus data is recorded by the user's susceptible person at a specified sampling rate and speech resolution.

7. The apparatus according to claim 5 , wherein the corpus data is recorded by the user's susceptible person with a dialect, and/or the corpus data is recorded by the user's susceptible person with a personalized language.

8. The apparatus according to claim 5 , wherein a Hidden Markov Model is used to divide the corpus data in the hypnosis speech library, so as to construct the speech units; and using the Hidden Markov Model to select, splice and synthesize the found speech units.

9. A non-transitory computer readable storage medium, wherein the non-transitory computer readable storage medium stores a computer program which causes a processor to perform the following operations when being executed:
performing a text analysis for a hypnosis guide language, so as to obtain text hierarchical information of relations between words, word groups and sentences in the hypnosis guide language;
performing a speech analysis for the hypnosis guide language, so as to obtain speech rhythm information in a phonetic level of the hypnosis guide language;
searching a hypnosis speech library for corresponding speech units, according to the text hierarchical information and the speech rhythm information of the hypnosis guide language, the hypnosis speech library storing speech units generated according to corpus data recorded by a user's susceptible person;
synthesizing found speech units into hypnosis speech data; and
synthesizing the hypnosis speech data with a virtual reality hypnosis scene, and outputting a virtual reality guide hypnosis speech;
wherein,
the text, analysis for the hypnosis guide language comprises analyzing at least one of aspects of language level, grammatical level, and semantic level of the hypnosis guide language;
the speech analysis for the hypnosis guide language comprises analyzing at least one of timbre, intonation, and loudness of sounds corresponding to the hypnosis guide language; and
the hypnosis speech library is established and updated in real time according to the corpus data recorded by the user's susceptible person.

10. The non-transitory computer readable storage medium according to claim 9 , wherein the corpus data is recorded by the user's susceptible person according to hypnosis speech features, and/or the corpus data is recorded by the user's susceptible person at a specified sampling rate and speech resolution.

11. The non-transitory computer readable storage medium according to claim 9 , wherein the corpus data is recorded by the user's susceptible person with a dialect, and/or the corpus data is recorded by the user's susceptible person with a personalized language.

12. The non-transitory computer readable storage medium according to claim 9 , wherein a Hidden Markov Model is used to divide the corpus data in the hypnosis speech library, so as to construct the speech units; and using the Hidden Markov Model to select, splice and synthesize the found speech units.

Assignees

• Shenzhen Inst Of Adv Tech Cas

Inventors

• Li Rongmao
• Zang Shanshan
• Liu Yanjun
• Chen Yili
• Zhu Yanchun
• Chen Mingmin
• Xie Yaoqin

Classifications

• G10L13/047

  Architecture of speech synthesisers · CPC title

• G06F40/30

  Semantic analysis · CPC title

• A61M2021/0027

  by the hearing sense · CPC title

• G09B9/00

  Simulators for teaching or training purposes (for the use of weapons F41; computing aspects G06; {protocols for games, networked simulations or virtual reality H04L67/131}) · CPC title

• G06F40/253

  Grammatical analysis; Style critique · CPC title