WO2021127990A1 - Procédé de reconnaissance d'empreinte vocale basé sur la réduction du bruit vocal et appareil associé - Google Patents

Procédé de reconnaissance d'empreinte vocale basé sur la réduction du bruit vocal et appareil associé Download PDF

Info

Publication number
WO2021127990A1
WO2021127990A1 PCT/CN2019/127961 CN2019127961W WO2021127990A1 WO 2021127990 A1 WO2021127990 A1 WO 2021127990A1 CN 2019127961 W CN2019127961 W CN 2019127961W WO 2021127990 A1 WO2021127990 A1 WO 2021127990A1
Authority
WO
WIPO (PCT)
Prior art keywords
speech
recognized
neural network
network model
convolutional neural
Prior art date
Application number
PCT/CN2019/127961
Other languages
English (en)
Chinese (zh)
Inventor
陈昊亮
罗伟航
Original Assignee
广州国音智能科技有限公司
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 广州国音智能科技有限公司 filed Critical 广州国音智能科技有限公司
Priority to CN201980003326.0A priority Critical patent/CN111108554A/zh
Priority to PCT/CN2019/127961 priority patent/WO2021127990A1/fr
Publication of WO2021127990A1 publication Critical patent/WO2021127990A1/fr

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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/20—Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/04—Training, enrolment or model building
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/18—Artificial neural networks; Connectionist approaches

Definitions

  • This application relates to the technical field of voiceprint recognition, and in particular to a voiceprint recognition method and related devices based on speech noise reduction.
  • Voiceprint recognition refers to the process of comprehensively analyzing and comparing the voice acoustic characteristics of an unknown speaker or an uncertain speaker with the voice acoustic characteristics of a known speaker, and making a conclusion whether the two are the same.
  • the voiceprint recognition effect is not good.
  • the present application provides a voiceprint recognition method and related devices based on speech noise reduction, which are used to solve the technical problem that the existing voiceprint recognition method has poor recognition effect for noisy speech to be recognized.
  • the first aspect of the present application provides a voiceprint recognition method based on speech noise reduction, including:
  • the first spectrogram is input into a preset convolutional neural network model to obtain a voiceprint recognition result of the voice to be recognized.
  • the step of inputting the first spectrogram into a preset convolutional neural network model to obtain the voiceprint recognition result of the speech to be recognized includes:
  • the performing denoising processing on the to-be-recognized speech includes:
  • Denoising processing is performed on the speech to be recognized based on a method combining empirical mode decomposition and wavelet threshold.
  • the method based on the combination of empirical mode decomposition and wavelet threshold to denoise the speech to be recognized includes:
  • the denoised high-frequency eigenmode function component and the non-high-frequency eigenmode function component are added and reconstructed to obtain the denoised speech to be recognized.
  • a second aspect of the present application provides a voiceprint recognition device based on speech noise reduction, including:
  • the first acquisition module is used to acquire the voice to be recognized
  • the first denoising module is configured to perform denoising processing on the speech to be recognized
  • the first extraction module is configured to extract the first spectrogram of the speech to be recognized after denoising
  • the recognition module is used to input the first spectrogram into a preset convolutional neural network model to obtain the voiceprint recognition result of the voice to be recognized.
  • it also includes:
  • the second acquisition module is used to acquire training sample speech
  • the second denoising module is used to perform denoising processing on the training sample speech
  • the second extraction module is used to extract the second spectrogram of the training sample speech after denoising
  • a training module configured to input the second spectrogram into a convolutional neural network model for training
  • the calculation module is used to calculate the recognition rate of the training sample speech by the convolutional neural network model.
  • the recognition rate reaches a threshold
  • the trained convolutional neural network model is obtained, and the trained convolutional neural network model is obtained.
  • the convolutional neural network model is used as the preset convolutional neural network model.
  • the first denoising module includes:
  • the decomposition sub-module is used to adaptively decompose the speech to be recognized based on empirical mode decomposition to obtain several eigenmode function components;
  • the denoising sub-module is configured to perform denoising processing on the high frequency eigenmode function component in the eigenmode function component based on the wavelet threshold;
  • the reconstruction sub-module is used to add and reconstruct the denoised high-frequency eigenmode function components and non-high-frequency eigenmode function components to obtain the denoised speech to be recognized.
  • a third aspect of the present application provides a voiceprint recognition device based on speech noise reduction, the device including a processor and a memory;
  • the memory is used to store program code and transmit the program code to the processor
  • the processor is configured to execute any of the voiceprint recognition methods based on speech noise reduction in the first aspect according to instructions in the program code.
  • the fourth aspect of the present application provides a computer-readable storage medium, the computer-readable storage medium is used to store program code, and the program code is used to execute any one of the voice-based speech noise reduction described in the first aspect Voiceprint recognition method.
  • the fifth aspect of the present application provides a computer program product including instructions, which is characterized in that when it runs on a computer, the computer executes any of the voiceprint recognition based on speech noise reduction described in the first aspect method.
  • This application provides a voiceprint recognition method based on speech noise reduction, including: acquiring the speech to be recognized; performing denoising processing on the speech to be recognized; extracting the first spectrogram of the speech to be recognized after denoising; The spectrogram is input to the preset convolutional neural network model, and the voiceprint recognition result of the voice to be recognized is obtained.
  • the voiceprint recognition method based on speech noise reduction in this application performs denoising processing on the acquired speech to be recognized to obtain the denoised speech to be recognized, and performs voiceprint recognition based on the denoised speech to be recognized, which is helpful In order to improve the result of voiceprint recognition, it solves the technical problem that the existing voiceprint recognition method has poor identification effect for the voice to be recognized with noise.
  • Fig. 1 is a schematic flowchart of an embodiment of a voiceprint recognition method based on speech noise reduction provided by this application;
  • FIG. 2 is a schematic flowchart of another embodiment of a voiceprint recognition method based on speech noise reduction provided by this application;
  • FIG. 3 is a schematic structural diagram of an embodiment of a voiceprint recognition device based on speech noise reduction provided by this application.
  • An embodiment of a voiceprint recognition method based on speech noise reduction includes:
  • Step 101 Obtain a voice to be recognized.
  • the voice to be recognized can be obtained through a voice recording device.
  • Step 102 Perform denoising processing on the speech to be recognized.
  • wavelet transform wavelet threshold
  • auditory model can be used to denoise the speech to be recognized, which is not specifically limited here.
  • Step 103 Extract the first spectrogram of the speech to be recognized after denoising.
  • the first spectrogram of the speech to be recognized can be obtained through a spectrograph.
  • Step 104 Input the first spectrogram into a preset convolutional neural network model to obtain a voiceprint recognition result of the voice to be recognized.
  • the first spectrogram is input into the preset convolutional neural network model for feature extraction and classification recognition, and the voiceprint recognition result of the voice to be recognized is obtained.
  • the voiceprint recognition method based on speech noise reduction in the embodiments of the present application performs denoising processing on the acquired speech to be recognized to obtain the denoised speech to be recognized, and performs voiceprint recognition based on the denoised speech to be recognized. It is helpful to improve the result of voiceprint recognition, thereby solving the technical problem that the existing voiceprint recognition method has poor identification effect for the voice to be recognized with noise.
  • FIG. 2 Another embodiment of a voiceprint recognition method based on speech noise reduction provided by this application includes:
  • Step 201 Obtain training sample speech.
  • training sample speech can be obtained in the voiceprint recognition database.
  • Step 202 Perform denoising processing on the training sample speech.
  • the empirical mode decomposition method is used to self-process the training sample speech. After adaptive decomposition, several eigenmode function components are obtained.
  • eigenmode function components include training sample speech signal and noise; secondly, the eigenmode function components are analyzed to determine the high-frequency eigenmodes containing noise Function component, using wavelet threshold method to denoise the high-frequency eigenmode function component; finally, add the denoised high-frequency eigenmode function component and the remaining non-high-frequency eigenmode function components to reconstruct The initial training sample speech, so as to obtain the denoised training sample speech.
  • Step 203 Extract a second spectrogram of the training sample speech after denoising.
  • the first spectrogram of the training sample speech can be obtained through a spectrograph.
  • Step 204 Input the second spectrogram into the convolutional neural network model for training.
  • voiceprint features in the second spectrogram are extracted through the convolutional neural network model, and classification training is performed according to the extracted voiceprint features.
  • Step 205 Calculate the recognition rate of the training sample speech by the convolutional neural network model. When the recognition rate reaches the threshold, obtain the trained convolutional neural network model, and use the trained convolutional neural network model as the preset convolutional neural network model.
  • the recognition rate is obtained according to the ratio of the number of correctly recognized second spectrograms to the total number of second spectrograms.
  • the training is stopped and the trained convolutional neural network model is obtained.
  • the trained convolutional neural network model is used as a preset convolutional neural network model, where the convolutional neural network model can be a residual network, a deep full-sequence convolutional neural network, etc.
  • Step 206 Acquire the voice to be recognized.
  • the voice to be recognized can be obtained through a voice recording device.
  • Step 207 Perform denoising processing on the speech to be recognized.
  • the method based on the combination of empirical mode decomposition and wavelet threshold is preferred to denoise the speech to be recognized.
  • the specific process is as follows: First, the speech to be recognized is adaptively decomposed by the empirical mode decomposition method to obtain several originals.
  • Eigenmode function components among which several eigenmode function components include the speech signal to be recognized and noise; secondly, the eigenmode function components are analyzed to determine the high-frequency eigenmode function components containing noise, and the wavelet threshold method is used Denoise the high-frequency eigenmode function components; finally, add the denoised high-frequency eigenmode function components and the remaining non-high-frequency eigenmode function components to reconstruct the initial speech to be recognized, thereby Obtain the to-be-recognized voice after denoising.
  • Step 208 Extract the first spectrogram of the speech to be recognized after denoising.
  • the first spectrogram of the speech to be recognized can be obtained through a spectrograph.
  • Step 209 Input the first spectrogram into the preset convolutional neural network model to obtain the voiceprint recognition result of the voice to be recognized.
  • the first spectrogram is input into the preset convolutional neural network model for feature extraction and classification recognition, and the voiceprint recognition result of the voice to be recognized is obtained.
  • the voiceprint recognition method based on speech noise reduction in the embodiment of this application uses the convolutional neural network model to perform feature extraction and classification recognition, and the end-to-end learning ability of the convolutional neural network model can improve the accuracy and recognition of voiceprint recognition.
  • Speed By denoising the acquired speech to be recognized, the denoised speech to be recognized is obtained, and the speech recognition is performed based on the denoised speech to be recognized, which helps to further improve the result of voiceprint recognition, thereby solving the problem.
  • Some voiceprint recognition methods have a technical problem that the recognition effect of the voice to be recognized containing noise is not good.
  • An embodiment of a voiceprint recognition device based on voice noise reduction provided by the present application includes:
  • the first acquiring module 301 is used to acquire the voice to be recognized.
  • the first denoising module 302 is configured to perform denoising processing on the speech to be recognized.
  • the first extraction module 303 is configured to extract the first spectrogram of the speech to be recognized after denoising.
  • the recognition module 304 is configured to input the first spectrogram into the preset convolutional neural network model to obtain the voiceprint recognition result of the voice to be recognized.
  • the second acquisition module 305 is used to acquire training sample speech.
  • the second denoising module 306 is used to denoise the training sample speech.
  • the second extraction module 307 is used to extract the second spectrogram of the training sample speech after denoising.
  • the training module 308 is used to input the second spectrogram into the convolutional neural network model for training.
  • the calculation module 309 is used to calculate the recognition rate of the training sample speech by the convolutional neural network model.
  • the recognition rate reaches the threshold
  • the trained convolutional neural network model is obtained, and the trained convolutional neural network model is used as the preset volume Product neural network model.
  • the first denoising module 302 includes:
  • the decomposition sub-module 3021 is used for adaptively decomposing the speech to be recognized based on empirical mode decomposition to obtain several eigenmode function components.
  • the denoising sub-module 3022 is configured to perform denoising processing on the high frequency eigenmode function components in the eigenmode function components based on the wavelet threshold.
  • the reconstruction sub-module 3023 is used to add and reconstruct the denoised high-frequency eigenmode function components and non-high-frequency eigenmode function components to obtain the denoised speech to be recognized.
  • This application provides an embodiment of a voiceprint recognition device based on speech noise reduction, the device includes a processor and a memory;
  • the memory is used to store the program code and transmit the program code to the processor
  • the processor is configured to execute the voiceprint recognition method based on voice noise reduction in the foregoing embodiment of the voiceprint recognition method based on voice noise reduction according to the instructions in the program code.
  • This application provides an embodiment of a computer-readable storage medium.
  • the computer-readable storage medium is used to store program code, and the program code is used to execute the voice-based voice reduction in the foregoing embodiment of the voiceprint recognition method based on voice noise reduction. noisy voiceprint recognition method.
  • This application also provides an embodiment of a computer program product including instructions, which when run on a computer, causes the computer to execute the voiceprint based on voice noise reduction in the aforementioned embodiment of the voiceprint recognition method based on voice noise reduction recognition methods.
  • the disclosed device and method may be implemented in other ways.
  • the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of this application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium. , Including several instructions to execute all or part of the steps of the methods described in the various embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device, etc.).
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (English full name: Read-Only Memory, English abbreviation: ROM), random access memory (English full name: Random Access Memory, English abbreviation: RAM), magnetic Various media that can store program codes, such as discs or optical discs.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Circuit For Audible Band Transducer (AREA)

Abstract

L'invention concerne un procédé de reconnaissance d'empreinte vocale basé sur la réduction du bruit vocal et un appareil associé. Le procédé comprend les étapes consistant à : acquérir une voix devant être soumise à une reconnaissance (101) ; réaliser un traitement de débruitage sur la voix devant être soumise à une reconnaissance (102) ; extraire un premier spectrogramme de la voix débruitée devant être soumise à une reconnaissance (103) ; et entrer le premier spectrogramme dans un modèle de réseau neuronal convolutionnel prédéfini pour obtenir un résultat de reconnaissance d'empreinte vocale de la voix devant être soumise à une reconnaissance (104). La réalisation d'un traitement de débruitage sur la voix acquise devant être soumise à une reconnaissance pour obtenir une voix débruitée devant être soumise à une reconnaissance et la réalisation d'une reconnaissance d'empreinte vocale sur la base de la voix débruitée devant être soumise à une reconnaissance pour faciliter l'amélioration d'un résultat de reconnaissance d'empreinte vocale résolvent le problème technique dans les procédés de reconnaissance d'empreinte vocale existants qui présentent un effet d'identification médiocre en ce qui concerne la voix devant être soumise à une reconnaissance contenant du bruit.
PCT/CN2019/127961 2019-12-24 2019-12-24 Procédé de reconnaissance d'empreinte vocale basé sur la réduction du bruit vocal et appareil associé WO2021127990A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980003326.0A CN111108554A (zh) 2019-12-24 2019-12-24 一种基于语音降噪的声纹识别方法和相关装置
PCT/CN2019/127961 WO2021127990A1 (fr) 2019-12-24 2019-12-24 Procédé de reconnaissance d'empreinte vocale basé sur la réduction du bruit vocal et appareil associé

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/127961 WO2021127990A1 (fr) 2019-12-24 2019-12-24 Procédé de reconnaissance d'empreinte vocale basé sur la réduction du bruit vocal et appareil associé

Publications (1)

Publication Number Publication Date
WO2021127990A1 true WO2021127990A1 (fr) 2021-07-01

Family

ID=70427299

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/127961 WO2021127990A1 (fr) 2019-12-24 2019-12-24 Procédé de reconnaissance d'empreinte vocale basé sur la réduction du bruit vocal et appareil associé

Country Status (2)

Country Link
CN (1) CN111108554A (fr)
WO (1) WO2021127990A1 (fr)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112562695B (zh) * 2020-11-26 2023-09-29 珠海格力电器股份有限公司 声纹识别方法、装置、计算机设备和存储介质
CN113823291A (zh) * 2021-09-07 2021-12-21 广西电网有限责任公司贺州供电局 一种应用于电力作业中的声纹识别的方法及系统
CN114265373A (zh) * 2021-11-22 2022-04-01 煤炭科学研究总院 综采面一体式操控台控制系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090326942A1 (en) * 2008-06-26 2009-12-31 Sean Fulop Methods of identification using voice sound analysis
CN107146624A (zh) * 2017-04-01 2017-09-08 清华大学 一种说话人确认方法及装置
CN109378002A (zh) * 2018-10-11 2019-02-22 平安科技（深圳）有限公司 声纹验证的方法、装置、计算机设备和存储介质
CN109524014A (zh) * 2018-11-29 2019-03-26 辽宁工业大学 一种基于深度卷积神经网络的声纹识别分析方法
CN110299142A (zh) * 2018-05-14 2019-10-01 桂林远望智能通信科技有限公司 一种基于网络融合的声纹识别方法及装置
WO2019199554A1 (fr) * 2018-04-11 2019-10-17 Microsoft Technology Licensing, Llc Séparation vocale en multiples microphones
CN110459225A (zh) * 2019-08-14 2019-11-15 南京邮电大学 一种基于cnn融合特征的说话人辨认系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105895078A (zh) * 2015-11-26 2016-08-24 乐视致新电子科技（天津）有限公司 动态选择语音模型的语音识别方法及装置
CN107093430A (zh) * 2017-05-10 2017-08-25 哈尔滨理工大学 一种基于小波包变换的声纹特征提取算法
CN109410977B (zh) * 2018-12-19 2022-09-23 东南大学 一种基于EMD-Wavelet的MFCC相似度的语音段检测方法
CN110349593A (zh) * 2019-07-25 2019-10-18 江门市华恩电子研究院有限公司 基于波形时频域分析的语义和声纹双重识别的方法及系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090326942A1 (en) * 2008-06-26 2009-12-31 Sean Fulop Methods of identification using voice sound analysis
CN107146624A (zh) * 2017-04-01 2017-09-08 清华大学 一种说话人确认方法及装置
WO2019199554A1 (fr) * 2018-04-11 2019-10-17 Microsoft Technology Licensing, Llc Séparation vocale en multiples microphones
CN110299142A (zh) * 2018-05-14 2019-10-01 桂林远望智能通信科技有限公司 一种基于网络融合的声纹识别方法及装置
CN109378002A (zh) * 2018-10-11 2019-02-22 平安科技（深圳）有限公司 声纹验证的方法、装置、计算机设备和存储介质
CN109524014A (zh) * 2018-11-29 2019-03-26 辽宁工业大学 一种基于深度卷积神经网络的声纹识别分析方法
CN110459225A (zh) * 2019-08-14 2019-11-15 南京邮电大学 一种基于cnn融合特征的说话人辨认系统

Also Published As

Publication number Publication date
CN111108554A (zh) 2020-05-05

Similar Documents

Publication Publication Date Title
Macartney et al. Improved speech enhancement with the wave-u-net
CN106486130B (zh) 噪声消除、语音识别方法及装置
US9640186B2 (en) Deep scattering spectrum in acoustic modeling for speech recognition
US10614827B1 (en) System and method for speech enhancement using dynamic noise profile estimation
WO2021127990A1 (fr) Procédé de reconnaissance d'empreinte vocale basé sur la réduction du bruit vocal et appareil associé
CN111696568B (zh) 一种半监督瞬态噪声抑制方法
CN108564956B (zh) 一种声纹识别方法和装置、服务器、存储介质
Ghaemmaghami et al. Noise robust voice activity detection using features extracted from the time-domain autocorrelation function
WO2023092955A1 (fr) Procédé et appareil de traitement de signaux audio
Wiem et al. Unsupervised single channel speech separation based on optimized subspace separation
Hou et al. Domain adversarial training for speech enhancement
Andrianakis et al. Speech spectral amplitude estimators using optimally shaped Gamma and Chi priors
CN108172214A (zh) 一种基于Mel域的小波语音识别特征参数提取方法
Huang et al. Dccrgan: Deep complex convolution recurrent generator adversarial network for speech enhancement
Mira et al. LA-VocE: Low-SNR audio-visual speech enhancement using neural vocoders
WO2021152566A1 (fr) Système et procédé de protection d'empreinte vocale de locuteur dans des signaux audio
CN113744715A (zh) 声码器语音合成方法、装置、计算机设备及存储介质
KR102033469B1 (ko) 적응형 잡음제거기, 잡음제거 방법
Lin et al. Focus on the sound around you: Monaural target speaker extraction via distance and speaker information
Al-Ali et al. Enhanced forensic speaker verification using multi-run ICA in the presence of environmental noise and reverberation conditions
Joy et al. Deep Scattering Power Spectrum Features for Robust Speech Recognition.
CN107993666B (zh) 语音识别方法、装置、计算机设备及可读存储介质
Nisa et al. The speech signal enhancement approach with multiple sub-frames analysis for complex magnitude and phase spectrum recompense
CN115457973A (zh) 说话人分割方法、系统、终端及存储介质
Hussain et al. A Novel Speech Intelligibility Enhancement Model based on Canonical Correlation and Deep Learning

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: 19957550

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 01.12.2022)