-
公开(公告)号：WO2022087117A2
公开(公告)日：2022-04-28
申请号：PCT/US2021/055826
申请日：2021-10-20
Applicant: GOOGLE LLC
Inventor： PELECANOS, Jason , CHAO, Pu-Sen , HUANG, Yiling , WANG, Quan
Abstract: A method (300) for evaluating a verification model (146) includes receiving first and second sets of verification results (148) where each verification result indicates whether a primary model or an alternative model verifies an identity of a user (10) as a registered user. The method further includes identifying each verification result in the first and second sets that includes a performance metric (212), determining a first score (222) of the primary model based on a number of the verification results identified in the first set that includes the performance metric, and determining a second score of the alternative model based on a number of the verification results identified in the second set that includes the performance metric. The method further includes determining whether a verification capability of the alternative model is better than a verification capability of the primary model based on the first score and the second score.
-
公开(公告)号：WO2020117639A2
公开(公告)日：2020-06-11
申请号：PCT/US2019/063927
申请日：2019-12-02
Applicant: GOOGLE LLC
Inventor： CHAO, Pu-sen , CASADO, Diego Melendo , MORENO, Ignacio Lopez , WANG, Quan
IPC: G10L17/22
Abstract: Text independent speaker recognition models can be utilized by an automated assistant to verify a particular user spoke a spoken utterance and/or to identify the user who spoke a spoken utterance. Implementations can include automatically updating a speaker embedding for a particular user based on previous utterances by the particular user. Additionally or alternatively, implementations can include verifying a particular user spoke a spoken utterance using output generated by both a text independent speaker recognition model as well as a text dependent speaker recognition model. Furthermore, implementations can additionally or alternatively include prefetching content for several users associated with a spoken utterance prior to determining which user spoke the spoken utterance.
-
公开(公告)号：WO2018013401A1
公开(公告)日：2018-01-18
申请号：PCT/US2017/040906
申请日：2017-07-06
Applicant: GOOGLE LLC
Inventor： MORENO, Ignacio Lopez , WAN, Li , WANG, Quan
Abstract: Methods, systems, apparatus, including computer programs encoded on computer storage medium, to facilitate language independent-speaker verification. In one aspect, a method includes actions of receiving, by a user device, audio data representing an utterance of a user. Other actions may include providing, to a neural network stored on the user device, input data derived from the audio data and a language identifier. The neural network may be trained using speech data representing speech in different languages or dialects. The method may include additional actions of generating, based on output of the neural network, a speaker representation and determining, based on the speaker representation and a second representation, that the utterance is an utterance of the user. The method may provide the user with access to the user device based on determining that the utterance is an utterance of the user.
Abstract translation: 包括在计算机存储介质上编码的计算机程序的方法，系统和装置，以便于语言无关说话者验证。 在一个方面，一种方法包括通过用户设备接收表示用户的话语的音频数据的动作。 其他动作可以包括向存储在用户设备上的神经网络提供从音频数据导出的输入数据和语言标识符。 可以使用代表不同语言或方言的语音的语音数据来训练神经网络。 该方法可以包括基于神经网络的输出产生说话者表示并且基于说话者表示和第二表示来确定话语是用户的话语的附加动作。 该方法可以基于确定话语是用户话语来向用户提供对用户装置的访问。
-
公开(公告)号：WO2022246365A1
公开(公告)日：2022-11-24
申请号：PCT/US2022/072139
申请日：2022-05-05
Applicant: GOOGLE LLC
Inventor： MORENO, Ignacio Lopez , WANG, Quan , PELECANOS, Jason , HUANG, Yiling , SAGLAM, Mert
IPC: G10L17/18
Abstract: A speaker verification method (400) includes receiving audio data (120) corresponding to an utterance (119), processing the audio data to generate an evaluation attentive d-vector (200E) representing voice characteristics of the utterance, the evaluation ad-vector includes ne style classes (202) each including a respective value vector (220) concatenated with a corresponding routing vector (210). The method also includes generating using a self-attention mechanism (160), at least one multi-condition attention score (165) that indicates a likelihood that the evaluation ad-vector matches a respective reference ad-vector (200R) associated with a respective user (10). The method also includes identifying the speaker of the utterance as the respective user associated with the respective reference ad-vector based on the multi-condition attention score.
-
公开(公告)号：WO2021112840A1
公开(公告)日：2021-06-10
申请号：PCT/US2019/064501
申请日：2019-12-04
Applicant: GOOGLE LLC
Inventor： MORENO, Ignacio Lopez , WANG, Quan , PELECANOS, Jason , WAN, Li , GRUENSTEIN, Alexander , ERDOGAN, Hakan
Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.
-
Patent Agency Ranking
公开(公告)号：WO2020146042A1
公开(公告)日：2020-07-16
申请号：PCT/US2019/061030
申请日：2019-11-12
Applicant: GOOGLE LLC
Inventor： WANG, Chong , ZHANG, Aonan , WANG, Quan , ZHU, Zhenyao
Abstract: A method (500) includes receiving an utterance (120) of speech and segmenting the utterance of speech into a plurality of segments (220). For each segment of the utterance of speech, the method also includes extracting a speaker-discriminative embedding (240) from the segment and predicting a probability distribution over possible speakers (262) for the segment using a probabilistic generative model (300) configured to receive the extracted speaker-discriminative embedding as a feature input. The probabilistic generative model trained on a corpus of training speech utterances each segmented into a plurality of training segments (220T). Each training segment including a corresponding speaker-discriminative embedding and a corresponding speaker label (250). The method also includes assigning a speaker label to each segment of the utterance of speech based on the probability distribution over possible speakers for the corresponding segment.
-
公开(公告)号：WO2019222591A1
公开(公告)日：2019-11-21
申请号：PCT/US2019/032815
申请日：2019-05-17
Applicant: GOOGLE LLC
Inventor： JIA, Ye , CHEN, Zhifeng , WU, Yonghui , SHEN, Jonathan , PANG, Ruoming , WEISS, Ron J. , MORENO, Ignacio Lopez , REN, Fei , ZHANG, Yu , WANG, Quan , NGUYEN, Patrick An Phu
IPC: G10L13/033 , G10L13/04 , G10L25/30
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech synthesis. The methods, systems, and apparatus include actions of obtaining an audio representation of speech of a target speaker, obtaining input text for which speech is to be synthesized in a voice of the target speaker, generating a speaker vector by providing the audio representation to a speaker encoder engine that is trained to distinguish speakers from one another, generating an audio representation of the input text spoken in the voice of the target speaker by providing the input text and the speaker vector to a spectrogram generation engine that is trained using voices of reference speakers to generate audio representations, and providing the audio representation of the input text spoken in the voice of the target speaker for output.
-
公开(公告)号：WO2023048746A1
公开(公告)日：2023-03-30
申请号：PCT/US2021/063343
申请日：2021-12-14
Applicant: GOOGLE LLC
Inventor： WANG, Quan , LU, Han , CLARK, Evan , MORENNO, Ignacio, Lopez , SAK, Hasim , XU, Wei , JOGLEKAR, Taral , TRIPATHI, Anshuman
IPC: G10L21/0272 , G10L15/16 , G10L25/30
Abstract: A method (400) includes receiving an input audio signal (122) that corresponds to utterances (120) spoken by multiple speakers (10). The method also includes processing the input audio to generate a transcription (120) of the utterances and a sequence of speaker turn tokens (224) each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments (225) based on the sequence of speaker turn tokens. The method also includes extracting a speaker-discriminative embedding (240) from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes (262). The method also includes assigning a respective speaker label (250) to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to speaker segments clustered into each other class of the k classes.
-
公开(公告)号：WO2022081688A1
公开(公告)日：2022-04-21
申请号：PCT/US2021/054755
申请日：2021-10-13
Applicant: GOOGLE LLC
Inventor： FANG, Yeming , WANG, Quan , MENGIBAR, Pedro J. Moreno , LOPEZ MORENO, Ignacio , FENG, Gang , CHU, Fang , SHI, Jin , PELECANOS, Jason
Abstract: A method (300) of generating an accurate speaker representation for an audio sample (202) includes receiving a first audio sample from a first speaker (10) and a second audio sample from a second speaker. The method includes dividing a respective audio sample into a plurality of audio slices (214). The method also includes, based on the plurality of slices, generating a set of candidate acoustic embeddings (232) where each candidate acoustic embedding includes a vector representation of acoustic features. The method further includes removing a subset of the candidate acoustic embeddings from the set of candidate acoustic embeddings. The method additionally includes generating an aggregate acoustic embedding (234) from the remaining candidate acoustic embeddings in the set of candidate acoustic embeddings after removing the subset of the candidate acoustic embeddings.
-
公开(公告)号：WO2021252039A1
公开(公告)日：2021-12-16
申请号：PCT/US2021/022008
申请日：2021-03-11
Applicant: GOOGLE LLC
Inventor： WANG, Quan
IPC: G10L21/0208 , G10L25/30 , G10L13/02 , G10L21/0216 , G10L21/0264 , G10L13/00 , G10L15/063 , G10L2021/02082 , G10L25/93
Abstract: A method (400) includes receiving an overlapped audio signal (202) that includes audio spoken by a speaker (10) that overlaps a segment (156) of synthesized playback audio (154). The method also includes encoding a sequence of characters that correspond to the synthesized playback audio into a text embedding representation (212). For each character in the sequence of characters, the method also includes generating a respective cancelation probability (222) using the text embedding representation. The cancelation probability indicates a likelihood that the corresponding character is associated with the segment of the synthesized playback audio overlapped by the audio spoken by the speaker in the overlapped audio signal.
-
-
-
-
-
-
-
-
-
Search Results
15
records
(took 0.013 seconds)
