WO2018058425A1 - 虚拟现实引导催眠语音处理方法及装置 - Google Patents

虚拟现实引导催眠语音处理方法及装置 Download PDF

Info

Publication number
WO2018058425A1
WO2018058425A1 PCT/CN2016/100780 CN2016100780W WO2018058425A1 WO 2018058425 A1 WO2018058425 A1 WO 2018058425A1 CN 2016100780 W CN2016100780 W CN 2016100780W WO 2018058425 A1 WO2018058425 A1 WO 2018058425A1
Authority
WO
WIPO (PCT)
Prior art keywords
hypnotic
speech
voice
corpus
guide
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2016/100780
Other languages
English (en)
French (fr)
Inventor
李荣茂
臧珊珊
刘燕君
陈昳丽
朱艳春
陈鸣闽
谢耀钦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Priority to PCT/CN2016/100780 priority Critical patent/WO2018058425A1/zh
Priority to US15/856,349 priority patent/US10665221B2/en
Publication of WO2018058425A1 publication Critical patent/WO2018058425A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
    • A61M21/02—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis for inducing sleep or relaxation, e.g. by direct nerve stimulation, hypnosis, analgesia
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/253—Grammatical analysis; Style critique
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B9/00—Simulators for teaching or training purposes
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
    • G10L13/10—Prosody rules derived from text; Stress or intonation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
    • A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
    • A61M2021/0027—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the hearing sense
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • G10L13/04—Details of speech synthesis systems, e.g. synthesiser structure or memory management
    • G10L13/047—Architecture of speech synthesisers

Definitions

  • the present invention relates to the field of virtual reality guided hypnosis technology, and in particular to a virtual reality guided hypnosis speech processing method and apparatus.
  • Existing virtual reality guided hypnosis techniques are typically synthesized with a fixed, standardized hypnotic voice (recorded by a professional announcer) and a virtual reality hypnotic scene to guide the user into hypnosis.
  • the user's hypnosis is guided by the fixed standardized hypnotic voice.
  • it can be close to the hypnosis process voice requirements in various aspects such as tone and tone, it can not satisfy the user's faster and better hypnosis demand, and the hypnosis effect is not good.
  • the embodiment of the invention provides a virtual reality guided hypnotic speech processing method for improving the hypnotic susceptibility of the user and optimizing the hypnotic effect, and the method comprises:
  • the hypnotic speech data is synthesized with the virtual reality hypnotic scene, and the virtual reality is used to guide the hypnotic speech.
  • the text analysis of the hypnotic guide language is performed to obtain text level information of the hypnotic guide language, including: text language, grammar and semantic analysis of the hypnotic guide language, obtaining word information, phrase information, and hypnotic guidance words, Sentence information, and relationship information between words, phrases, and sentences.
  • the corpus is entered by a user susceptible according to hypnotic speech features; and/or the corpus is entered by a user susceptible at a specified sampling rate and speech resolution.
  • the corpus is entered by a user susceptor using a dialect; and/or the corpus is entered by a user susceptor using a personalized language.
  • the method further includes: establishing, and updating, in real time, the hypnotic speech library according to a corpus entered by a user susceptible; wherein the hidden corpus is used to disassemble the corpus in the hypnotic speech library.
  • a speech unit To construct a speech unit;
  • the synthesized speech unit synthesizes hypnotic speech data, including: selecting, splicing, and synthesizing the found speech units using a hidden Markov model.
  • the embodiment of the invention further provides a virtual reality guided hypnosis speech processing device, which is used for improving the hypnotic susceptibility of the user and optimizing the hypnotic effect.
  • the device comprises:
  • a text analysis module configured to perform text analysis on the hypnotic guide language, and obtain text level information of the hypnotic guide language
  • a speech analysis module configured to perform speech analysis on the hypnotic guide language, and obtain speech prosody information of the hypnotic guide language;
  • a voice query module configured to search for a corresponding voice unit from the hypnotic voice library according to the text level information and the voice prosody information of the hypnotic guide language, where the hypnotic voice library stores a voice unit generated according to a corpus entered by the user susceptible person ;
  • a speech synthesis module configured to synthesize hypnotic voice data by the found speech unit
  • the voice output module is configured to synthesize the hypnotic voice data and the virtual reality hypnotic scene, and output the virtual reality to guide the hypnotic voice.
  • the text analysis module is further configured to: perform text language, grammar, and semantic analysis on the hypnotic guide language, obtain word information, phrase information, sentence information, and words, phrases, and sentences between hypnotic guide words. Relationship information.
  • the corpus is entered by a user susceptible according to hypnotic speech features; and/or the corpus is entered by a user susceptible at a specified sampling rate and speech resolution.
  • the corpus is entered by a user susceptor using a dialect; and/or the corpus is entered by a user susceptor using a personalized language.
  • the apparatus further includes: a corpus processing module, configured to establish, and update the hypnotic speech library in real time according to a corpus entered by a user susceptible; wherein the hypnosis is performed using a hidden Markov model
  • the speech library splits the corpus to construct a speech unit
  • the speech synthesis module is further configured to: select, splicing, and synthesizing the found speech units using a hidden Markov model.
  • the hypnotic process speech is matched with the hypnotic susceptibility of the user, and the speech synthesis technology is used to change the original standardized hypnotic speech, and the user's sensibility speech is synthesized, and the characteristics of the hypnosis guidance are combined.
  • the hypnotic voice sensitive to the user is output, thereby enhancing the hypnotic susceptibility of the user and optimizing the hypnotic effect.
  • the embodiment of the invention provides a scheme for automatically synthesizing speech, which eliminates the cumbersome manual recording on the spot and satisfies the user's needs, can help the crowd without any hypnotic knowledge background to automatically output the hypnotic voice, complete the hypnosis process, and help the use. Better enter the hypnosis state.
  • FIG. 1 is a schematic diagram of a virtual reality guided hypnosis voice processing method according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a specific example of a virtual reality guided hypnosis voice processing method according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of a virtual reality guided hypnotic voice processing device according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a specific example of a virtual reality guided hypnotic speech processing apparatus according to an embodiment of the present invention.
  • a virtual reality guided hypnotic speech processing method which optimizes the hypnotic effect by improving the hypnotic susceptibility of the user.
  • FIG. 1 is a schematic diagram of a virtual reality guided hypnosis voice processing method according to an embodiment of the present invention. As shown in FIG. 1, the method may include:
  • Step 101 Perform text analysis on the hypnotic guide language to obtain text level information of the hypnosis guide language;
  • Step 102 performing voice analysis on the hypnotic guide language to obtain voice prosody information of the hypnotic guide language
  • Step 103 Search, according to the text level information and the phonetic prosody information of the hypnotic guide, the corresponding voice unit from the hypnotic voice library, where the hypnotic voice library stores a voice unit generated according to the corpus entered by the user susceptible;
  • Step 104 Synthesize hypnotic voice data into the found voice unit
  • Step 105 Synthesize the hypnotic voice data with the virtual reality hypnosis scene, and output the virtual reality to guide the hypnotic voice.
  • the embodiment of the present invention fully considers that different hypnotic sound characteristics are applied to the user during the guiding hypnosis process, which will have different effects on the hypnotic effect, wherein the user is susceptible.
  • the voice makes it easier to get into a specific hypnosis state for better hypnosis.
  • the embodiment of the invention provides a scheme for automatically synthesizing speech, which eliminates the cumbersome manual recording on the spot, realizes the phased result that the hypnosis is completely generated by the machine, and can output the hypnotic voice with the characteristics of the user's susceptible voice. Meet user needs.
  • the embodiment of the present invention can help the crowd without any hypnotic knowledge to automatically output hypnotic speech by using the speech synthesis technology, complete the hypnosis process, and help the user to enter the hypnosis state better.
  • corpus gathering may be performed on the user susceptible in the early stage to establish a hypnotic speech library.
  • the hypnotic voice library stores a voice unit generated based on a corpus entered by the user's susceptible person.
  • the corpus can be designed according to the hypnotic speech feature to be outputted, and then the user is allowed to record the corpus under specific requirements, and then the recorded corpus is analyzed, set, and the required hypnotic speech library is established.
  • the corpus entered by the user susceptible person may be entered by the user susceptible person according to the hypnotic voice feature. According to the hypnotic voice feature, the user susceptible should enter the corpus under specific requirements.
  • the recorder when recording the corpus, the recorder is required to have the same volume, gentle speech, clear pronunciation, and gentle feelings.
  • the corpus entered by the user's susceptible person may also be entered by the user's susceptible person at a specified sampling rate and speech resolution.
  • the recorder is required to record high SNR speech at a specific sampling rate and speech resolution, making the corpus more standard.
  • the embodiment of the present invention aims to solve the problem that the hypnotic effect is affected by the unfamiliarity and insensitivity of the user to the hypnotist voice in the virtual reality guiding hypnosis process by using the speech synthesis technology, and the speech synthesis technology is used to realize Automatically output the user's hypnotic sound during the virtual reality guided hypnosis process, thereby establishing an emotional connection with the user in terms of language traits, optimizing the hypnotic effect; and the user's dialect, or the voice of the person they trust is easier. It can enter a specific hypnotic state to achieve better hypnosis effect.
  • the corpus entered by the user susceptor can be entered by the user's susceptor in the dialect, and/or is susceptible to the user. Entered in a personalized language. In this way, the user is satisfied by outputting a hypnotic voice with local characteristics and individuality. Demand.
  • the recorder of the previous corpus suggests a specific selection.
  • the hypnotic speech library is created and updated in real time according to the corpus entered by the user susceptible.
  • the hidden Markov model can be used to split the corpus in the hypnotic speech library to construct a speech unit.
  • the text analysis of the hypnotic guide language and the text level information of the hypnosis guide language may include, for example, performing text language, grammar and semantic analysis on the hypnotic guide language, obtaining word information, phrase information, sentence information, and hypnotic guide words. And the relationship between words, phrases, and sentences.
  • the text version of the hypnotic guide can be first analyzed, and analyzed in the language layer, the grammar layer, and the semantic layer to obtain hypnosis.
  • the hierarchical information of the guiding language that is, the hierarchical relationship of phrases, phrases, sentences, etc.; for example, combined with the hypnotic characteristics of virtual reality, the hypnotic guiding language completed in consultation with the professional hypnotist mainly includes progressive relaxation guidance, hypnosis scene guidance, etc.
  • the text information is analyzed by grammar and semantics, and the words, phrases and sentences in the hypnotic guide are obtained.
  • the prosody analysis is performed on the basis of the voice layer of the hypnosis guide, for example, analyzing the tone, tone, loudness and the like of the sound corresponding to the hypnotic guide, and obtaining prosody information at the speech level.
  • the corresponding voice unit is searched from the hypnotic voice library, and then the searched voice unit is synthesized into the hypnotic voice data.
  • the hidden Markov model can be used to select, splicing and synthesizing the found speech units.
  • Corresponding synthesis processing is performed on the speech unit extracted from the hypnotic speech library to obtain the required speech data, that is, hypnotic speech data that is user-susceptible.
  • the hypnotic leader is output in a modest and emotional manner, so in the speech synthesis process, it is necessary to control the speed and impart emotion to the hypnotic speech.
  • the hypnotic speech data is synthesized with the virtual reality hypnotic scene, and the virtual reality is used to guide the hypnotic speech.
  • the synthesized hypnotic voice data can be adjusted, optimized, and finally formed, and then imported into a virtual reality hypnosis scene, and the virtual reality guide hypnotic voice is output.
  • FIG. 2 is a schematic diagram of a specific example of a virtual reality guided hypnosis speech processing method according to an embodiment of the present invention.
  • a corpus is first designed, and the user is input by the susceptor.
  • the corpus in order to establish a hypnotic speech library, using the hidden Markov model (HMM) to construct the speech unit in the hypnotic speech library
  • HMM hidden Markov model
  • the text analysis of the hypnotic guide, the text level information of the hypnotic guide, the speech analysis of the hypnotic guide, the speech prosody information of the hypnotic guide In the storage of the hypnotic guide, the text analysis of the hypnotic guide, the text level information of the hypnotic guide, the speech analysis of the hypnotic guide, the speech prosody information of the hypnotic guide; and then, according to the hypnosis guide Text level information and phonetic prosody information, find the corresponding phonetic unit from the hypnotic speech library, synthesize hypnotic speech data from the found speech unit; optimize the hypnotic speech data, synthesize with the virtual reality hypnosis scene, and finally output the virtual reality Guide the hypnotic voice.
  • HMM hidden Markov model
  • the voice synthesis technology is used in the embodiment of the present invention to collect a specific sentence of the user's hypnotic susceptible voice by collecting corpus of the user's susceptible person in the early stage, thereby establishing a hypnotic voice library, and then only It is necessary to provide text information, perform speech analysis, speech unit extraction and synthesis, and finally realize the hypnotic speech of the more sensitive person to enhance the hypnotic effect.
  • the hypnosis process will increase the emotional dimension and enhance the use based on the original hypnotic effect.
  • the emotional cognition of the person enhances the hypnotic effect.
  • an embodiment of the present invention further provides a virtual reality guided hypnotic speech processing device, as described in the following embodiments. Since the principle of the device solving problem is similar to the virtual reality guiding hypnotic speech processing method, the implementation of the device can be referred to the implementation of the virtual reality guided hypnotic speech processing method, and the repeated description is not repeated.
  • FIG. 3 is a schematic diagram of a virtual reality guided hypnotic speech processing apparatus according to an embodiment of the present invention. As shown in FIG. 3, the apparatus may include:
  • a text analysis module 301 configured to perform text analysis on the hypnotic guide language, and obtain text level information of the hypnotic guide language;
  • the voice analysis module 302 is configured to perform voice analysis on the hypnotic guide language to obtain voice prosody information of the hypnosis guide language;
  • the voice query module 303 is configured to search for a corresponding voice unit from the hypnotic voice library according to the text layer information and the voice prosody information of the hypnosis guide word, where the hypnotic voice library stores a voice generated according to a corpus entered by the user susceptible person. unit;
  • a speech synthesis module 304 configured to synthesize hypnotic voice data by the found speech unit
  • the voice output module 305 is configured to synthesize the hypnotic voice data and the virtual reality hypnotic scene, and output the virtual reality to guide the hypnotic voice.
  • the text analysis module 301 can be further configured to: perform text language, grammar, and semantic analysis on the hypnotic guide language, obtain word information, phrase information, sentence information, and relationship between words, phrases, and sentences in the hypnotic guide language. information.
  • the corpus may be entered by the user susceptible according to the hypnotic voice feature; and/or the corpus may be entered by the user susceptor at a specified sampling rate and speech resolution.
  • the corpus may be entered by a user susceptor using a dialect; and/or the corpus may be entered by a user susceptor using a personalized language.
  • FIG. 4 is a schematic diagram of a specific example of a virtual reality guided hypnotic speech processing device according to an embodiment of the present invention.
  • the device shown in FIG. 3 may further include: a corpus processing module 401, configured to be based on a user susceptible The entered corpus establishes and updates the hypnotic speech library in real time; wherein the hidden Markov model is used to split the corpus in the hypnotic speech library to construct a speech unit;
  • the speech synthesis module 304 can be further configured to: select, splicing, and synthesizing the found speech units using a hidden Markov model.
  • the speech traits of different sensitivities have different influences on the hypnotic effect of the user, and the speech synthesis technology and the virtual reality hypnosis scene are performed.
  • the original standardized (recorded by a professional announcer) hypnotic voice is improved, and finally the user's hypnotic susceptible guiding voice is output, thereby achieving a more effective hypnosis state.
  • the embodiment of the invention provides a scheme for automatically synthesizing speech, and can output various hypnotic voices with local characteristics to meet user requirements.
  • speech synthesis technology it is possible to synthesize and output standardized hypnotic susceptibility-specific hypnotic speech, complete the hypnosis process, and help the user to enter the hypnosis state better.
  • the embodiments of the present invention can be applied to a virtual reality guided hypnosis process of clinical respiratory control of radiotherapy for patients with thoracic and abdominal tumors.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Acoustics & Sound (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Anesthesiology (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Pain & Pain Management (AREA)
  • Psychology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Hematology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Educational Technology (AREA)
  • Educational Administration (AREA)
  • Business, Economics & Management (AREA)
  • Machine Translation (AREA)

Abstract

一种虚拟现实引导催眠语音处理方法及装置，其中方法包括：对催眠引导语进行文本分析，获得催眠引导语的文本层次信息（101）；对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息（102）；根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，所述催眠语音库存储有根据使用者易感者录入的语料生成的语音单元（103）；将查找到的语音单元合成催眠语音数据（104）；将催眠语音数据与虚拟现实催眠场景合成，输出虚拟现实引导催眠语音（105）。所述方法及装置可以提升使用者的催眠易感性，优化催眠效果。

Description

虚拟现实引导催眠语音处理方法及装置 技术领域
本发明涉及虚拟现实引导催眠技术领域，尤其涉及虚拟现实引导催眠语音处理方法及装置。
背景技术
现有的虚拟现实引导催眠技术，一般用固定的标准化的催眠语音(由专业播音员录制)与虚拟现实催眠场景合成，来引导使用者进入催眠状态。由固定的标准化的催眠语音引导使用者催眠虽然在音调、音色等各个方面能贴近催眠过程语音要求，但是却无法满足使用者更快、更好的催眠需求，催眠效果不佳。
发明内容
本发明实施例提供一种虚拟现实引导催眠语音处理方法，用以提升使用者的催眠易感性，优化催眠效果，该方法包括：
对催眠引导语进行文本分析，获得催眠引导语的文本层次信息；
对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息；
根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，所述催眠语音库存储有根据使用者易感者录入的语料生成的语音单元；
将查找到的语音单元合成催眠语音数据；
将催眠语音数据与虚拟现实催眠场景合成，输出虚拟现实引导催眠语音。
一个实施例中，所述对催眠引导语进行文本分析，获得催眠引导语的文本层次信息，包括：对催眠引导语进行文本语言、语法及语义分析，获得催眠引导语中词语信息、词组信息、句子信息、及词语、词组、句子之间的关系信息。
一个实施例中，所述语料是由使用者易感者根据催眠语音特征录入的；和/或，所述语料是由使用者易感者在指定的采样率和语音分辨率下录入的。
一个实施例中，所述语料是由使用者易感者使用方言录入的；和/或，所述语料是由使用者易感者使用个性化的语言录入的。
一个实施例中，所述的方法还包括：根据使用者易感者录入的语料建立、并实时更新所述催眠语音库；其中，使用隐马尔科夫模型在所述催眠语音库对语料进行拆分，构造语音单元；
所述将查找到的语音单元合成催眠语音数据，包括：使用隐马尔科夫模型对查找到的语音单元进行挑选、拼接及合成处理。
本发明实施例还提供一种虚拟现实引导催眠语音处理装置，用以提升使用者的催眠易感性，优化催眠效果，该装置包括：
文本分析模块，用于对催眠引导语进行文本分析，获得催眠引导语的文本层次信息；
语音分析模块，用于对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息；
语音查询模块，用于根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，所述催眠语音库存储有根据使用者易感者录入的语料生成的语音单元；
语音合成模块，用于将查找到的语音单元合成催眠语音数据；
语音输出模块，用于将催眠语音数据与虚拟现实催眠场景合成，输出虚拟现实引导催眠语音。
一个实施例中，所述文本分析模块进一步用于：对催眠引导语进行文本语言、语法及语义分析，获得催眠引导语中词语信息、词组信息、句子信息、及词语、词组、句子之间的关系信息。
一个实施例中，所述语料是由使用者易感者根据催眠语音特征录入的；和/或，所述语料是由使用者易感者在指定的采样率和语音分辨率下录入的。
一个实施例中，所述语料是由使用者易感者使用方言录入的；和/或，所述语料是由使用者易感者使用个性化的语言录入的。
一个实施例中，所述的装置还包括：语料库处理模块，用于根据使用者易感者录入的语料建立、并实时更新所述催眠语音库；其中，使用隐马尔科夫模型在所述催眠语音库对语料进行拆分，构造语音单元；
所述语音合成模块进一步用于：使用隐马尔科夫模型对查找到的语音单元进行挑选、拼接及合成处理。
本发明实施例中考虑催眠过程语音与使用者的催眠易感性匹配，使用语音合成技术，改变了原有的标准化的催眠语音，将使用者易感者的语音进行合成，同时结合催眠引导的特性，最后输出使用者所敏感的催眠语音，从而提升使用者的催眠易感性，优化催眠效果。同时，本发明实施例提供了一种自动化合成语音的方案，免去了现场人工录制的繁琐，满足使用者需求，可以帮助没有任何催眠知识背景的人群自动输出催眠语音，完成催眠过程，帮助使用者更好的进入催眠状态。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。在附图中：
图1为本发明实施例中虚拟现实引导催眠语音处理方法的示意图；
图2为本发明实施例中虚拟现实引导催眠语音处理方法的一个具体实例的示意图；
图3为本发明实施例中虚拟现实引导催眠语音处理装置的示意图；
图4为本发明实施例中虚拟现实引导催眠语音处理装置的一个具体实例的示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚明白，下面结合附图对本发明实施例做进一步详细说明。在此，本发明的示意性实施例及其说明用于解释本发明，但并不作为对本发明的限定。
发明人考虑到，目前的虚拟现实引导催眠技术，使用固定的标准化的催眠语音，无法满足使用者需求，对催眠效果有所影响。而如果考虑催眠过程语音与使用者的催眠易感性匹配，则能更快、更好地实现预期效果。另一方面，使用者的催眠易感声音对象往往没有专业的催眠技术背景，不能为使用者提供专业、有效的催眠引导过程。基于此，在本发明实施例中提供一种虚拟现实引导催眠语音处理方法，通过提升使用者的催眠易感性，来优化催眠效果。
图1为本发明实施例中虚拟现实引导催眠语音处理方法的示意图，如图1所示，该方法可以包括：
步骤101、对催眠引导语进行文本分析，获得催眠引导语的文本层次信息；
步骤102、对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息；
步骤103、根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，所述催眠语音库存储有根据使用者易感者录入的语料生成的语音单元；
步骤104、将查找到的语音单元合成催眠语音数据；
步骤105、将催眠语音数据与虚拟现实催眠场景合成，输出虚拟现实引导催眠语音。
由图1所示流程可以得知，本发明实施例充分考虑到在引导催眠过程中对使用者采用不同的催眠声音特质将对其进入催眠的效果产生不同的影响，其中采用使用者易感者的语音更容易使其进入特定的催眠状态，从而达到更好的催眠效果。同时，本发明实施例提供了一种自动化合成语音的方案，免去了现场人工录制的繁琐，实现催眠完全由机器生成的阶段性成果，可输出具有使用者易感者语音特色的催眠语音，满足使用者需求。另一方面，本发明实施例借助语音合成技术，可以帮助没有任何催眠知识背景的人群自动输出催眠语音，完成催眠过程，帮助使用者更好的进入催眠状态。
具体实施时，可以在前期对使用者易感者进行语料搜集，以建立催眠语音库。催眠语音库存储有根据使用者易感者录入的语料生成的语音单元。实施例中可以根据将要输出的催眠语音特征设计语料，接下来让使用者易感者在特定的要求下录制语料，然后对所录制的语料进行分析，设置，建立所需要的催眠语音库。具体实施时，使用者易感者录入的语料，可以是由使用者易感者根据催眠语音特征录入的。根据催眠语音特征，使用者易感者应在特定的要求下录入语料，例如，在录制语料时，要求录制者音量一致、语速平缓、发音清晰、感情和缓。使用者易感者录入的语料，也可以是由使用者易感者在指定的采样率和语音分辨率下录入的。例如要求录制者在特定的采样率、语音分辨率下录制高信噪比语音，使得语料更加标准。
此外，考虑到本发明实施例旨在借助语音合成技术解决在虚拟现实引导催眠过程中由于使用者对催眠师语音的不熟悉、不敏感，致使催眠效果受到影响的问题，使用语音合成技术，实现在虚拟现实引导催眠过程中自动输出使用者催眠易感的声音，从而在语言特质方面，与使用者建立起感情联结，优化催眠效果；而使用者的方言、或其信任的人的声音更容易使其进入特定的催眠状态，从而达到更好的催眠效果，因此，使用者易感者录入的语料可以是由使用者易感者使用方言录入的，和/或，是由使用者易感者使用个性化的语言录入的。这样，通过输出具有本地特色、个性化的催眠语音，满足使用者 的需求。鉴于本发明实施例引入语音合成技术的关键是为了输出使用者催眠易感者的语音，所以前期语料的录制者建议经过特定选择。
在使用者易感者录入语料后，根据使用者易感者录入的语料建立、并实时更新催眠语音库。在建立、更新催眠语音库的过程中，可以使用隐马尔科夫模型在所述催眠语音库对语料进行拆分，构造语音单元。
在需要输出虚拟现实引导催眠语音时，需要先对催眠引导语进行文本分析，获得催眠引导语的文本层次信息；对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息。其中，对催眠引导语进行文本分析，获得催眠引导语的文本层次信息，例如可以包括：对催眠引导语进行文本语言、语法及语义分析，获得催眠引导语中词语信息、词组信息、句子信息、及词语、词组、句子之间的关系信息。
在具体的实施例中，进行催眠引导语的文本分析和语音层韵律分析时，可以首先对文字版的催眠引导语进行文本分析，分别在语言层、语法层、语义层方面进行分析，得到催眠引导语的层次信息，也就是词组、短语、句子等的层次关系；例如结合虚拟现实催眠特点，与专业催眠师协商完成的催眠引导语主要包含有渐进式放松引导、催眠场景引导等，通过对文本信息进行语法、语义的分析，得到催眠引导语中词语、词组、句子等信息。然后，在催眠引导语的语音层的基础上进行韵律分析，例如分析催眠引导语对应声音的音色、语调、响度等信息，得到语音层面的韵律信息。
在获得催眠引导语的文本层次信息和语音韵律信息后，根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，然后将查找到的语音单元合成催眠语音数据。具体实施时，可以使用隐马尔科夫模型对查找到的语音单元进行挑选、拼接及合成处理。对从催眠语音库中提取的语音单元进行相应合成处理，得到所需要的语音数据，也即是使用者易感的催眠语音数据。在具体的实例中，催眠引导语以一种缓和且有感情的方式输出，所以在语音合成过程中，需要控制速度且将感情赋予催眠语音中。
最后，将催眠语音数据与虚拟现实催眠场景合成，输出虚拟现实引导催眠语音。例如可以在专业催眠师的指导下，对合成的催眠语音数据进行调整、优化，最后成型，再将其导入到虚拟现实催眠场景中，输出虚拟现实引导催眠语音。
图2为本发明实施例中虚拟现实引导催眠语音处理方法的一个具体实例的示意图，如图2所示，本例中，对于虚拟现实催眠场景，先设计语料，由使用者易感者输入录制语料，以此建立催眠语音库，使用隐马尔科夫模型(HMM)构造语音单元在催眠语音库 中进行存储；在确定催眠引导语后，对催眠引导语进行文本分析，获得催眠引导语的文本层次信息，对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息；然后，根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，将查找到的语音单元合成催眠语音数据；对催眠语音数据进行优化，与虚拟现实催眠场景合成，最后输出虚拟现实引导催眠语音。
由上述实施例可以得知，本发明实施例使用语音合成技术，通过前期对使用者易感者进行语料搜集，搜集到使用者催眠易感声音的特定语句，由此建立催眠语音库，然后只需提供文字信息，进行语音分析、语音单元提取及合成等工作，最后实现输出使用者更敏感的人的催眠语音，增强催眠效果，催眠过程将在原始催眠效果的基础上增加情感维度，提升使用者的情感认知，从而提升催眠效果。
基于同一发明构思，本发明实施例中还提供了一种虚拟现实引导催眠语音处理装置，如下面的实施例所述。由于该装置解决问题的原理与虚拟现实引导催眠语音处理方法相似，因此该装置的实施可以参见虚拟现实引导催眠语音处理方法的实施，重复之处不再赘述。
图3为本发明实施例中虚拟现实引导催眠语音处理装置的示意图，如图3所示，该装置可以包括：
文本分析模块301，用于对催眠引导语进行文本分析，获得催眠引导语的文本层次信息；
语音分析模块302，用于对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息；
语音查询模块303，用于根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，所述催眠语音库存储有根据使用者易感者录入的语料生成的语音单元；
语音合成模块304，用于将查找到的语音单元合成催眠语音数据；
语音输出模块305，用于将催眠语音数据与虚拟现实催眠场景合成，输出虚拟现实引导催眠语音。
具体实施时，文本分析模块301可以进一步用于：对催眠引导语进行文本语言、语法及语义分析，获得催眠引导语中词语信息、词组信息、句子信息、及词语、词组、句子之间的关系信息。
具体实施时，所述语料可以是由使用者易感者根据催眠语音特征录入的；和/或，所述语料可以是由使用者易感者在指定的采样率和语音分辨率下录入的。
具体实施时，所述语料可以是由使用者易感者使用方言录入的；和/或，所述语料可以是由使用者易感者使用个性化的语言录入的。
图4为本发明实施例中虚拟现实引导催眠语音处理装置的一个具体实例的示意图，如图4所示，图3所示装置还可以包括：语料库处理模块401，用于根据使用者易感者录入的语料建立、并实时更新所述催眠语音库；其中，使用隐马尔科夫模型在所述催眠语音库对语料进行拆分，构造语音单元；
语音合成模块304可以进一步用于：使用隐马尔科夫模型对查找到的语音单元进行挑选、拼接及合成处理。
综上所述，本发明实施例在现有的虚拟现实催眠技术的基础上，考虑到不同敏感度的语言特质对使用者的催眠效果有着不同的影响，将语音合成技术与虚拟现实催眠场景进行结合，在原有的标准化(由专业播音员录制)的催眠语音基础上进行改进，最后输出使用者催眠易感的引导语音，从而达到更有效的催眠的状态。本发明实施例提供了一种自动化合成语音的方案，并可输出各种具有本地特色的催眠语音、满足使用者需求。另一方面，借助语音合成技术，可以合成输出标准化的催眠易感特异性催眠语音，完成催眠过程，帮助使用者更好的进入催眠状态。
本发明实施例可以应用于胸腹部肿瘤患者放疗临床呼吸控制的虚拟现实引导催眠过程中。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产 生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述的具体实施例，对本发明的目的、技术方案和有益效果进行了进一步详细说明，所应理解的是，以上所述仅为本发明的具体实施例而已，并不用于限定本发明的保护范围，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种虚拟现实引导催眠语音处理方法，其特征在于，包括：
    对催眠引导语进行文本分析，获得催眠引导语的文本层次信息；
    对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息；
    根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，所述催眠语音库存储有根据使用者易感者录入的语料生成的语音单元；
    将查找到的语音单元合成催眠语音数据；
    将催眠语音数据与虚拟现实催眠场景合成，输出虚拟现实引导催眠语音。
  2. 如权利要求1所述的方法，其特征在于，所述对催眠引导语进行文本分析，获得催眠引导语的文本层次信息，包括：对催眠引导语进行文本语言、语法及语义分析，获得催眠引导语中词语信息、词组信息、句子信息、及词语、词组、句子之间的关系信息。
  3. 如权利要求1所述的方法，其特征在于，所述语料是由使用者易感者根据催眠语音特征录入的；和/或，所述语料是由使用者易感者在指定的采样率和语音分辨率下录入的。
  4. 如权利要求1所述的方法，其特征在于，所述语料是由使用者易感者使用方言录入的；和/或，所述语料是由使用者易感者使用个性化的语言录入的。
  5. 如权利要求1至4任一项所述的方法，其特征在于，还包括：根据使用者易感者录入的语料建立、并实时更新所述催眠语音库；其中，使用隐马尔科夫模型在所述催眠语音库对语料进行拆分，构造语音单元；
    所述将查找到的语音单元合成催眠语音数据，包括：使用隐马尔科夫模型对查找到的语音单元进行挑选、拼接及合成处理。
  6. 一种虚拟现实引导催眠语音处理装置，其特征在于，包括：
    文本分析模块，用于对催眠引导语进行文本分析，获得催眠引导语的文本层次信息；
    语音分析模块，用于对催眠引导语进行语音分析，获得催眠引导语的语音韵律信息；
    语音查询模块，用于根据催眠引导语的文本层次信息和语音韵律信息，从催眠语音库中查找相应的语音单元，所述催眠语音库存储有根据使用者易感者录入的语料生成的语音单元；
    语音合成模块，用于将查找到的语音单元合成催眠语音数据；
    语音输出模块，用于将催眠语音数据与虚拟现实催眠场景合成，输出虚拟现实引导催眠语音。
  7. 如权利要求6所述的装置，其特征在于，所述文本分析模块进一步用于：对催眠引导语进行文本语言、语法及语义分析，获得催眠引导语中词语信息、词组信息、句子信息、及词语、词组、句子之间的关系信息。
  8. 如权利要求6所述的装置，其特征在于，所述语料是由使用者易感者根据催眠语音特征录入的；和/或，所述语料是由使用者易感者在指定的采样率和语音分辨率下录入的。
  9. 如权利要求6所述的装置，其特征在于，所述语料是由使用者易感者使用方言录入的；和/或，所述语料是由使用者易感者使用个性化的语言录入的。
  10. 如权利要求6至9任一项所述的装置，其特征在于，还包括：语料库处理模块，用于根据使用者易感者录入的语料建立、并实时更新所述催眠语音库；其中，使用隐马尔科夫模型在所述催眠语音库对语料进行拆分，构造语音单元；
    所述语音合成模块进一步用于：使用隐马尔科夫模型对查找到的语音单元进行挑选、拼接及合成处理。
PCT/CN2016/100780 2016-09-29 2016-09-29 虚拟现实引导催眠语音处理方法及装置 Ceased WO2018058425A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2016/100780 WO2018058425A1 (zh) 2016-09-29 2016-09-29 虚拟现实引导催眠语音处理方法及装置
US15/856,349 US10665221B2 (en) 2016-09-29 2017-12-28 Virtual reality guide hypnosis speech processing method and apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/100780 WO2018058425A1 (zh) 2016-09-29 2016-09-29 虚拟现实引导催眠语音处理方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/856,349 Continuation US10665221B2 (en) 2016-09-29 2017-12-28 Virtual reality guide hypnosis speech processing method and apparatus

Publications (1)

Publication Number Publication Date
WO2018058425A1 true WO2018058425A1 (zh) 2018-04-05

Family

ID=61763557

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/100780 Ceased WO2018058425A1 (zh) 2016-09-29 2016-09-29 虚拟现实引导催眠语音处理方法及装置

Country Status (2)

Country Link
US (1) US10665221B2 (zh)
WO (1) WO2018058425A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180197438A1 (en) * 2017-01-10 2018-07-12 International Business Machines Corporation System for enhancing speech performance via pattern detection and learning
CN108877765A (zh) * 2018-05-31 2018-11-23 百度在线网络技术（北京）有限公司 语音拼接合成的处理方法及装置、计算机设备及可读介质
CN113545781B (zh) * 2021-07-20 2024-06-07 浙江工商职业技术学院 虚拟现实促眠的方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010005770A1 (en) * 1998-08-24 2001-06-28 Blumenthal Richard A. Method and apparatus to create and induce a self-created hypnosis
CN201286926Y (zh) * 2008-09-26 2009-08-12 周湘峻 催眠仪
CN102430182A (zh) * 2011-09-01 2012-05-02 汪卫东 反馈式催眠治疗仪
CN105536119A (zh) * 2016-02-22 2016-05-04 南京邮电大学 一种基于心音控制的自适应心音催眠音乐产生方法

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9649469B2 (en) * 2008-04-24 2017-05-16 The Invention Science Fund I Llc Methods and systems for presenting a combination treatment

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010005770A1 (en) * 1998-08-24 2001-06-28 Blumenthal Richard A. Method and apparatus to create and induce a self-created hypnosis
CN201286926Y (zh) * 2008-09-26 2009-08-12 周湘峻 催眠仪
CN102430182A (zh) * 2011-09-01 2012-05-02 汪卫东 反馈式催眠治疗仪
CN105536119A (zh) * 2016-02-22 2016-05-04 南京邮电大学 一种基于心音控制的自适应心音催眠音乐产生方法

Also Published As

Publication number Publication date
US20180122362A1 (en) 2018-05-03
US10665221B2 (en) 2020-05-26

Similar Documents

Publication Publication Date Title
Bigi SPPAS-multi-lingual approaches to the automatic annotation of speech
CN108806656B (zh) 歌曲的自动生成
US8825486B2 (en) Method and apparatus for generating synthetic speech with contrastive stress
CN108806655B (zh) 歌曲的自动生成
US8914291B2 (en) Method and apparatus for generating synthetic speech with contrastive stress
US9412359B2 (en) System and method for cloud-based text-to-speech web services
CN112382274B (zh) 音频合成方法、装置、设备以及存储介质
Płaza et al. Call transcription methodology for contact center systems
McAuliffe et al. ISCAN: A system for integrated phonetic analyses across speech corpora
Pravena et al. Significance of incorporating excitation source parameters for improved emotion recognition from speech and electroglottographic signals
El Ouahabi et al. Toward an automatic speech recognition system for amazigh-tarifit language
Knowles et al. Examining factors influencing the viability of automatic acoustic analysis of child speech
CN119669427A (zh) 一种双屏异显实时翻译机实现方法及设备
Kadyan et al. Prosody features based low resource Punjabi children ASR and T-NT classifier using data augmentation
CN111477210A (zh) 语音合成方法和装置
Chen et al. A proof-of-concept study for automatic speech recognition to transcribe AAC speakers’ speech from high-technology AAC systems
CN112382269B (zh) 音频合成方法、装置、设备以及存储介质
WO2018058425A1 (zh) 虚拟现实引导催眠语音处理方法及装置
Labied et al. DARIJA-C: a crowdsourced corpus for Moroccan DARIJA speech-to-text translation
Kanadje et al. Assisted keyword indexing for lecture videos using unsupervised keyword spotting
CN107886938B (zh) 虚拟现实引导催眠语音处理方法及装置
Kepuska et al. Speech corpus generation from DVDs of movies and tv series
Răgman et al. Efficient training strategies for natural sounding speech synthesis and speaker adaptation based on FastPitch
JP2012073280A (ja) 音響モデル生成装置、音声翻訳装置、音響モデル生成方法
Long et al. Filled pause refinement based on the pronunciation probability for lecture speech

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16917179

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 31.07.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16917179

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19-02-2020)