公开(公告)号：US20170148340A1

公开(公告)日：2017-05-25

申请号：US14948365

申请日：2015-11-22

Applicant: Victor Popa-Simil ,  Andrei Popa-Simil

Inventor： Victor Popa-Simil ,  Andrei Popa-Simil

IPC: G09B9/48 ,  A42B3/04 ,  A61B5/0488 ,  G09B9/08 ,  A61B5/0402 ,  A61B5/0476 ,  G06F17/50 ,  G09B9/12

CPC classification number: G09B9/48 ,  G06F17/5009 ,  G09B9/085 ,  G09B9/12 ,  G09B9/16

Abstract: A method and device used to improve flying education, and reduce pilot student hazard when passing from simulators to the real aircraft, by introducing an intermediary stage where a simulator and a model radio-controlled aircraft with similar features as original is used in a system with many participants, an instructor, flight monitors, command center, mission control, audience located remotely and taking part in the same action via internet telecommunication. The simulator is used to measure biometric parameters of the pilots, certify them, and also for gaming, having fail-safe procedures embedded. System contains a flight-monitoring network, using both goniometry and radar devices, placed on surface and airborne, using these devices as signal repeaters for extensions of communication. The system may be used in missions dangerous to human crews, and by the complexity of simulation it improves the flying, as well as to improve the piloting of RC aircrafts.

公开(公告)号：US08751239B2

公开(公告)日：2014-06-10

申请号：US11867196

申请日：2007-10-04

Applicant: Jilei Tian ,  Victor Popa ,  Jani K. Nurminen

Inventor： Jilei Tian ,  Victor Popa ,  Jani K. Nurminen

IPC: G10L13/00

CPC classification number: G10L15/063 ,  G10L15/26 ,  G10L21/00 ,  G10L2021/0135

Abstract: An apparatus for providing text independent voice conversion may include a first voice conversion model and a second voice conversion model. The first voice conversion model may be trained with respect to conversion of training source speech to synthetic speech corresponding to the training source speech. The second voice conversion model may be trained with respect to conversion to training target speech from synthetic speech corresponding to the training target speech. An output of the first voice conversion model may be communicated to the second voice conversion model to process source speech input into the first voice conversion model into target speech corresponding to the source speech as the output of the second voice conversion model.

Abstract translation: 用于提供文本独立语音转换的装置可以包括第一语音转换模型和第二语音转换模型。 关于将训练源语音转换成对应于训练源语音的合成语音，可以对第一语音转换模型进行训练。 关于从对应于训练目标语音的合成语音到训练目标语音的转换，可以对第二语音转换模型进行训练。 第一语音转换模型的输出可以被传送到第二语音转换模型，以将输入到第一语音转换模型的源语音转换为与源语音相对应的目标语音作为第二语音转换模型的输出。

公开(公告)号：US07725411B2

公开(公告)日：2010-05-25

申请号：US11396831

申请日：2006-04-03

Applicant: Jilei Tian ,  Jani K. Nurminen ,  Victor Popa

Inventor： Jilei Tian ,  Jani K. Nurminen ,  Victor Popa

IPC: G06E1/00 ,  G06E3/00 ,  G06G7/00

CPC classification number: G06K9/628 ,  G06N99/005 ,  G10L21/007

Abstract: An apparatus for providing data clustering and mode selection includes a training element and a transformation element. The training element is configured to receive a first training data set, a second training data set and auxiliary data extracted from the same material as the first training data set. The training element is also configured to train a classifier to group the first training data set into M clusters based on the auxiliary data and the first training data set and train M processing schemes corresponding to the M clusters for transforming the first training data set into the second training data set. The transformation element is in communication with the training element and is configured to cluster the second training data set into M clusters based on features associated with the second training data set.

Abstract translation: 一种用于提供数据聚类和模式选择的装置包括训练元素和变换元素。 训练元件被配置为接收从与第一训练数据集相同的材料提取的第一训练数据集，第二训练数据集和辅助数据。 训练元素还被配置为训练分类器，以基于辅助数据和第一训练数据集以及对应于M个簇的训练M个处理方案将第一训练数据集合分组成M个群集，以将第一训练数据集变换为 第二训练数据集。 转换元件与训练元素通信，并且被配置为基于与第二训练数据集相关联的特征将第二训练数据集聚集成M个群集。

公开(公告)号：US20090171657A1

公开(公告)日：2009-07-02

申请号：US11966255

申请日：2007-12-28

Applicant: Jilei Tian ,  Victor Popa ,  Jani Kristian Nurminen

Inventor： Jilei Tian ,  Victor Popa ,  Jani Kristian Nurminen

IPC: G10L19/04

CPC classification number: G10L21/00 ,  G10L2021/0135

Abstract: A hybrid approach is described for combining frequency warping and Gaussian Mixture Modeling (GMM) to achieve better speaker identity and speech quality. To train the voice conversion GMM model, line spectral frequency and other features are extracted from a set of source sounds to generate a source feature vector and from a set of target sounds to generate a target feature vector. The GMM model is estimated based on the aligned source feature vector and the target feature vector. A mixture specific warping function is generated each set of mixture mean pairs of the GMM model, and a warping function is generated based on a weighting of each of the mixture specific warping functions. The warping function can be used to convert sounds received from a source speaker to approximate speech of a target speaker.

Abstract translation: 描述了混合方法，用于组合频率扭曲和高斯混合建模（GMM），以实现更好的扬声器身份和语音质量。 为了训练语音转换GMM模型，从一组源声音中提取线谱频率和其他特征以产生源特征向量和从一组目标声音生成目标特征向量。 基于对齐的源特征向量和目标特征向量来估计GMM模型。 每个GMM模型的混合均值对都产生混合特定的翘曲函数，并且基于每个混合特定翘曲函数的加权产生翘曲函数。 翘曲功能可用于将从源扬声器接收的声音转换为目标扬声器的近似语音。

公开(公告)号：US07480641B2

公开(公告)日：2009-01-20

申请号：US11400629

申请日：2006-04-07

Applicant: Jilei Tian ,  Jani K. Nurminen ,  Victor Popa

Inventor： Jilei Tian ,  Jani K. Nurminen ,  Victor Popa

IPC: G06E1/00 ,  G06E3/00 ,  G06F15/18 ,  G06G7/00 ,  G06N3/02

CPC classification number: G10L21/00 ,  G10L13/033 ,  G10L2021/0135

Abstract: An apparatus for providing efficient evaluation of feature transformation includes a training module and a transformation module. The training module is configured to train a Gaussian mixture model (GMM) using training source data and training target data. The transformation module is in communication with the training module. The transformation module is configured to produce a conversion function in response to the training of the GMM. The training module is further configured to determine a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM.

Abstract translation: 用于提供特征变换的有效评估的装置包括训练模块和变换模块。 训练模块被配置为使用训练源数据和训练目标数据训练高斯混合模型（GMM）。 变换模块与训练模块通信。 转换模块被配置为响应于GMM的训练而产生转换功能。 训练模块还被配置为通过计算GMM的跟踪测量来确定在使用转换功能之前的转换功能的质量。

公开(公告)号：US20080262838A1

公开(公告)日：2008-10-23

申请号：US11788263

申请日：2007-04-17

Applicant: Jani K. Nurminen ,  Victor Popa ,  Jilei Tian

Inventor： Jani K. Nurminen ,  Victor Popa ,  Jilei Tian

IPC: G10L21/00

CPC classification number: G10L13/033

Abstract: An apparatus for providing voice conversion using temporal dynamic features includes a feature extractor and a transformation element. The feature extractor may be configured to extract dynamic feature vectors from source speech. The transformation element may be in communication with the feature extractor and configured to apply a first conversion function to a signal including the extracted dynamic feature vectors to produce converted dynamic feature vectors. The first conversion function may have been trained using at least dynamic feature data associated with training source speech and training target speech. The transformation element may be further configured to produce converted speech based on an output of applying the first conversion function.

Abstract translation: 用于使用时间动态特征提供语音转换的装置包括特征提取器和变换元件。 特征提取器可以被配置为从源语音提取动态特征向量。 变换元件可以与特征提取器通信并且被配置为将第一转换函数应用于包括所提取的动态特征向量的信号以产生转换的动态特征向量。 可以使用至少与训练源语音和训练目标语音相关联的动态特征数据来训练第一转换功能。 转换元件还可以被配置为基于应用第一转换函数的输出来产生转换的语音。

公开(公告)号：US20080255827A1

公开(公告)日：2008-10-16

申请号：US11733329

申请日：2007-04-10

Applicant: Jani K. Nurminen ,  Victor Popa ,  Elina Helander ,  Jilei Tian

Inventor： Jani K. Nurminen ,  Victor Popa ,  Elina Helander ,  Jilei Tian

IPC: G10L19/00

CPC classification number: G10L21/028 ,  G10L15/04 ,  G10L25/78 ,  G10L2021/0135

Abstract: It may be desirable to provide a way to collect high quality speech training data without undue burden to the user. Speech training data may be collected during normal usage of a device. In this way, the collection of speech training data may be effectively transparent to the user, without the need for a distinct collection mode from the user's point of view. For example, where the device is or includes a phone (such as a cellular phone), when the user makes or receives a phone call to/from another party, speech training data may be automatically collected from one or both of the parties during the phone call.

Abstract translation: 可能需要提供一种收集高质量语音训练数据的方式，而不会对用户造成不必要的负担。 在设备的正常使用期间可以收集语音训练数据。 以这种方式，语音训练数据的收集对于用户来说可能是有效的透明的，而不需要用户的观点的不同的收集模式。 例如，当设备是或包括电话（例如蜂窝电话）时，当用户向/从另一方进行或接收电话呼叫时，可以在一方或两方当中自动收集语音训练数据 电话。

公开(公告)号：US20210353794A1

公开(公告)日：2021-11-18

申请号：US16876337

申请日：2020-05-18

Applicant: Victor Popa-Simil ,  Ioana Livia Popa-Simil ,  Andrei Popa-Simil ,  Liviu Popa-Simil ,  Gabriel Vasilescu ,  Adrian Boboc ,  Arpad Harangozo

Inventor： Victor Popa-Simil ,  Ioana Livia Popa-Simil ,  Andrei Popa-Simil ,  Liviu Popa-Simil ,  Gabriel Vasilescu ,  Adrian Boboc ,  Arpad Harangozo

IPC: A61L2/10 ,  B25J9/16 ,  F24H3/00 ,  G06K9/00 ,  G05D1/00

Abstract: With respect to pandemics, restaurants, stadiums, cafeterias, and bars are among the most dangerous places to socialize due to the form of interaction. Exchange of bacteria and viruses are facilitated intensively from the mouth and nose via air transport in droplets of saliva and bodily fluids being deposited on surfaces, foods, and in the air. The present development creates a comfortable environment where the air-space of each customer is separated by invisible cold-hot air and vis-UV barriers, which take away bacteria and viruses, destroying them and preventing recirculation while offering pleasant, clean, and sanitized ambient conditions for a face to face meeting. An immersive experience can be provided with surrounding screens and gas therapy that may be customized according to the customer's preferences. Food distribution is performed with a robotic shuttle system and when the customer departs, an extensive cleanup is performed using chemicals and UV irradiation through robotic systems.

公开(公告)号：US20210016216A1

公开(公告)日：2021-01-21

申请号：US17018177

申请日：2020-09-11

Applicant: Victor Popa-Simil ,  Ioana Livia Popa-Simil ,  Andrei Popa-Simil ,  Liviu Popa-Simil

Inventor： Victor Popa-Simil ,  Ioana Livia Popa-Simil ,  Andrei Popa-Simil ,  Liviu Popa-Simil

IPC: B01D46/44 ,  B60H1/00 ,  C12M1/12

Abstract: COVID-19 is a large virus with remarkable resilience, propagation and multiplication features that require complex technologic systems and manners to assure a reasonable protection. A transparent, multiuse face mask with valves and for inhalation of air from a specialized filter placed in a cleaner air space, and an exhalation valve that drives the exhaled air via a tube to a filter bladder placed on wrist and from there to a tube that has the release end near ground, or can be connected to the aspiration tube of the infrastructure, that removes it, preventing recirculation. The general convention that defines the usage method is that the building, buss, and any other enclosure provide clean antiseptic air above and consumer s have to release their exhalations down near floor from where the structure to remove them by a controlled air flow similar to clean rooms.
The main condition is that people to place their exhalation exhaust sterilized and placed near ground in order to increase the probability to inhale clean sterile air at the head level. No filter is perfect, and no sterilization unit, therefore the enclosure has to deal with exhaust gas, and remove into the atmosphere safely. The work to keep people inside safe is done by both the enclosure that may provide vacuum lines to collect the exhaled air, and by the people who will use correctly the infrastructure. The system is designed for smart communities for everybody to wear for about 3 weeks when a covid-19 or other virus infection occurs to suppress its multiplication rate, without perturbation in their activity and then returning to normality.

公开(公告)号：US20200306476A1

公开(公告)日：2020-10-01

申请号：US16847926

申请日：2020-04-14

Applicant: Victor Popa-Simil ,  Andrei Popa-Simil

Inventor： Victor Popa-Simil ,  Andrei Popa-Simil

IPC: A61M16/04 ,  A61M16/20 ,  A61M16/10 ,  A61M16/00 ,  A61L2/08 ,  G16H20/40

Abstract: Many pneumonia diseases and lung malfunctions can be quickly repaired using an improved lung lavage technique where the patient is rotated in specific 3D orientations to increase the efficiency of the lavage procedure. The process involves filling and emptying the lungs with fluid and rotating the patient makes this process “natural” and effective. Supplementary, a hydro-pneumatic system facilitates the operations with the patient sustained in various positions such as being immersed in water and having various control mechanisms such as variable pressures, temperatures, and performing assisted breathing. Additionally, immersed devices are implanted that “shake-up of alveolar wall” and other devices perform ultrasound imaging with a 0.1 mm resolution, a resolution in competition with stereoscopic X-ray. The bio-medical data acquisition system allows physicians to completely assess patient status in real time and guide the treatment to ensure optimum patient care, under quality assurance procedures.