专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

US20240274121A1 PERSONA AND AVATAR SYNTHESIS 审中-公开
公开(公告)号：US20240274121A1
公开(公告)日：2024-08-15
申请号：US18228500
申请日：2023-07-31
申请人： Perfecta Federal, LLC
发明人： Jawad KAKAR , George ZOULIAS
IPC分类号： G10L13/047 , G06N20/00 , G10L13/033
CPC分类号： G10L13/047 , G06N20/00 , G10L13/033
摘要： A set of attributes to be generated for a persona used to provide an online presence are identified, in which each attribute in the set includes a predetermined value that indicates a preference for a static mapping algorithm or a machine learning algorithm to generate the each attribute. One or more corresponding features for the each attribute are further specified. The one or more corresponding features are then assembled into a corresponding feature input for the each attribute in the set of attributes. At least one corresponding feature of the corresponding feature input is selected for the each attribute in the set of attributes via static mapping or machine learning provided by the machine learning algorithm based on a corresponding predetermined value. The each attribute of the set of attributes is then synthesized for the persona based on the at least one corresponding feature selected for the each attribute.

2. 发明公开

US20240242705A1 METHOD, ELECTRONIC DEVICE, AND COMPUTER PROGRAM PRODUCT FOR DATA PROCESSING 审中-公开
公开(公告)号：US20240242705A1
公开(公告)日：2024-07-18
申请号：US18110611
申请日：2023-02-16
申请人： Dell Products L.P.
发明人： Zijia Wang , Zhisong Liu , Zhen Jia
IPC分类号： G10L13/047 , G10L13/033 , G10L13/10 , G10L25/18
CPC分类号： G10L13/047 , G10L13/0335 , G10L13/10 , G10L25/18 , G10L2013/105
摘要： A method in an illustrative embodiment includes determining a first loss function for a first sub-model of a speech generation model based on a plurality of feature vectors associated with training image information, training audio information, and training text information used to train the speech generation model. The method may further include determining a second loss function for a second sub-model and a third loss function for a third sub-model of the speech generation model based on the plurality of feature vectors that have been processed. In addition, the method may further include determining a fourth loss function for a fourth sub-model of the speech generation model based on the processed plurality of feature vectors. The method may further include updating parameters of the speech generation model based on the first loss function, the second loss function, the third loss function, and the fourth loss function.

3. 发明公开

US20240233706A1 TEXT-BASED SPEECH GENERATION 审中-公开
公开(公告)号：US20240233706A1
公开(公告)日：2024-07-11
申请号：US18562962
申请日：2022-05-23
申请人： Microsoft Technology Licensing, LLC
发明人： Xu TAN , Tao Qin , Sheng Zhao , Tie-Yan Liu
IPC分类号： G10L13/10 , G10L13/047 , G10L13/06
CPC分类号： G10L13/10 , G10L13/047 , G10L13/06 , G10L2013/105
摘要： According to implementations of the subject matter described herein, a solution is proposed for text to speech. In this solution, an initial phoneme sequence corresponding to text is generated, the initial phoneme sequence comprising feature representations of a plurality of phonemes. A first phoneme sequence is generated by inserting a feature representation of an additional phoneme into the initial phoneme sequence, the additional phoneme being related to a characteristic of spontaneous speech. The duration of a phoneme among the plurality of phonemes and the additional phoneme is determined by using an expert model corresponding to the phoneme, and a second phoneme sequence is generated based on the first phoneme sequence. Spontaneous-style speech corresponding to the text is determined based on the second phoneme sequence. In this way, spontaneous-style speech with more varying rhythms can be generated based on spontaneous-style additional phonemes and multiple expert models.

4. 发明公开

US20240219907A1 APPARATUS AND METHOD FOR MONITORING AND CONTROLLING OF A NEURAL NETWORK USING ANOTHER NEURAL NETWORK IMPLEMENTED ON ONE OR MORE SOLID-STATE CHIPS 审中-公开
公开(公告)号：US20240219907A1
公开(公告)日：2024-07-04
申请号：US18485830
申请日：2023-10-12
申请人： Apex AI Industries, LLC
发明人： Kenneth A. Abeloe
IPC分类号： G05D1/00 , B60R11/02 , B60R11/04 , B60W30/095 , G06N3/045 , G06N3/08 , G06N5/046 , G06N20/00 , G10L13/00 , G10L13/047 , G10L15/16 , G10L15/22 , B60Q5/00
CPC分类号： G05D1/0088 , B60R11/0217 , B60R11/04 , B60W30/0956 , G06N3/045 , G06N3/08 , G06N5/046 , G06N20/00 , G10L13/00 , G10L13/047 , G10L15/16 , G10L15/22 , B60Q5/006 , B60R2300/102 , B60R2300/103 , G10L2015/223
摘要： A method of operating an apparatus using a control system that includes at least one neural network. The method includes receiving an input value captured by the apparatus, processing the input value using the at least one neural network of the control system implemented on first one or more solid-state chips, and obtaining an output from the at least one neural network resulting from processing the input value. The method may also include processing the output with another neural network implemented on solid-state chips to determine whether the output breaches a predetermined condition that is unchangeable after an initial installation onto the control system. The aforementioned another neural network is prevented from being retrained. The method may also include the step of using the output from the at least one neural network to control the apparatus unless the output breaches the predetermined condition. Similar corresponding apparatuses are described.

5. 发明授权

US12014723B2 Information processing method, information processing device, and program 有权
公开(公告)号：US12014723B2
公开(公告)日：2024-06-18
申请号：US17119426
申请日：2020-12-11
申请人： Yamaha Corporation
发明人： Makoto Tachibana , Motoki Ogasawara
IPC分类号： G10L13/047 , G06T11/20
CPC分类号： G10L13/047 , G06T11/203
摘要： An information processing method is realized by a computer and includes generating a first characteristic transition which is a transition of acoustic characteristics, in accordance with an instruction from a user, generating a second characteristic transition which is a transition of acoustic characteristics of voice that is pronounced in a specific pronunciation style selected from a plurality of pronunciation styles, and generating a combined characteristic transition which is a transition of the acoustic characteristics of synthesized voice by combining the first characteristic transition and the second characteristic transition.

6. 发明公开

US20240013768A1 IMAGE DESCRIPTION GENERATION FOR SCREEN READERS 审中-公开
公开(公告)号：US20240013768A1
公开(公告)日：2024-01-11
申请号：US17810765
申请日：2022-07-05
申请人： Capital One Services, LLC
发明人： Michael MOSSOBA , Abdelkader M'Hamed BENKREIRA , Noel LYLES , Joshua EDWARDS
IPC分类号： G10L13/047 , G06V10/764 , G06T7/194 , G06V10/86 , G10L13/08 , G09B21/00
CPC分类号： G10L13/047 , G06V10/764 , G06T7/194 , G06V10/86 , G10L13/08 , G09B21/006
摘要： In some implementations, a browser extension may receive a setting indicating a level of verbosity and may receive an image and a set of words associated with the image. The browser extension may identify a foreground of the image and a background of the image and may identify, within the foreground of the image, a set of objects. The browser extension may rank the set of objects based on one or more properties of the set of objects and the set of words and may select a subset of objects from the set of objects based on the setting and the ranking. Accordingly, the browser extension may generate descriptions of the selected subset of objects based on the setting and may input the generated descriptions to a text to speech algorithm.

7. 发明授权

US11869482B2 Speech waveform generation 有权
公开(公告)号：US11869482B2
公开(公告)日：2024-01-09
申请号：US17272325
申请日：2018-09-30
申请人： Microsoft Technology Licensing, LLC
发明人： Yang Cui , Xi Wang , Lei He , Kao-Ping Soong
IPC分类号： G10L13/047
CPC分类号： G10L13/047
摘要： A method and apparatus for generating a speech waveform. Fundamental frequency information, glottal features and vocal tract features associated with an input may be received, wherein the glottal features include a phase feature, a shape feature, and an energy feature (1310). A glottal waveform is generated based on the fundamental frequency information and the glottal features through a first neural network model (1320). A speech waveform is generated based on the glottal waveform and the vocal tract features through a second neural network model (1330).

8. 发明授权

US11854521B2 Electronic musical instruments, method and storage media 有权
公开(公告)号：US11854521B2
公开(公告)日：2023-12-26
申请号：US17129724
申请日：2020-12-21
申请人： CASIO COMPUTER CO., LTD.
发明人： Makoto Danjyo , Fumiaki Ota , Atsushi Nakamura
IPC分类号： G10H1/36 , G10H1/00 , G10L13/033 , G10L13/047
CPC分类号： G10H1/361 , G10H1/0008 , G10L13/0335 , G10L13/047 , G10H2210/005
摘要： In an electronic musical instrument that can output stored lyrics of a song in accordance with operations by a user, a processor determines whether a pedal is on or off, and if the pedal is off, the lyric is advanced in accordance with a user operation of a keyboard, and if the pedal is on, the lyric is not advanced in accordance with a user operation of a keyboard.

9. 发明授权

US11842722B2 Speech synthesis method and system 有权
公开(公告)号：US11842722B2
公开(公告)日：2023-12-12
申请号：US17908014
申请日：2021-06-09
申请人： AI SPEECH CO., LTD.
发明人： Kai Yu , Zhijun Liu , Kuan Chen
IPC分类号： G10L25/30 , G10L13/047
CPC分类号： G10L13/047 , G10L25/30
摘要： Disclosed is a speech synthesis method including: acquiring fundamental frequency information and acoustic feature information from original speech; generating an impulse train from the fundamental frequency information, and inputting it to a harmonic time-varying filter; inputting the acoustic feature information into a neural network filter estimator to obtain corresponding impulse response information; generating noise signal by a noise generator; determining, by the harmonic time-varying filter, harmonic component information through filtering processing on the impulse train and the impulse response information; determining, by a noise time-varying filter, noise component information based on the impulse response information and the noise; and generating a synthesized speech from the harmonic component information and the noise component information. Acoustic features are processed to obtain corresponding impulse response information, and harmonic component information and noise component information are modeled respectively, thereby reducing computation of speech synthesis and improving the quality of the synthesized speech.

10. 发明授权

US11823655B2 Synthetic speech processing 有权
公开(公告)号：US11823655B2
公开(公告)日：2023-11-21
申请号：US17836330
申请日：2022-06-09
申请人： Amazon Technologies, Inc.
发明人： Antonio Bonafonte , Panagiotis Agis Oikonomou Filandras , Bartosz Perz , Arent van Korlaar , Ioannis Douratsos , Jonas Felix Ananda Rohnke , Elena Sokolova , Andrew Paul Breen , Nikhil Sharma
IPC分类号： G10L13/10 , G10L13/047 , G10L15/16 , G10L15/18 , G10L15/22
CPC分类号： G10L13/10 , G10L13/047 , G10L15/16 , G10L15/1815 , G10L15/22 , G10L2015/223
摘要： A speech-processing system receives both text data and natural-understanding data (e.g., a domain, intent, and/or entity) related to a command represented in the text data. The system uses the natural-understanding data to vary vocal characteristics in determining spectrogram data corresponding to the text data based on the natural-understanding data.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式