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. 发明申请

WO2021206804A1 SEQUENCE-TO-SEQUENCE SPEECH RECOGNITION WITH LATENCY THRESHOLD 审中-公开
公开(公告)号：WO2021206804A1
公开(公告)日：2021-10-14
申请号：PCT/US2021/018079
申请日：2021-02-15
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： GAUR, Yashesh , LI, Jinyu , LU, Liang , INAGUMA, Hirofumi , GONG, Yifan
IPC分类号： G10L15/16 , G10L15/32 , G10L15/06
摘要： A computing system including one or more processors configured to receive an audio input. The one or more processors may generate a text transcription of the audio input at a sequence-to-sequence speech recognition model, which may assign a respective plurality of external-model text tokens to a plurality of frames included in the audio input. Each external-model text token may have an external-model alignment within the audio input. Based on the audio input, the one or more processors may generate a plurality of hidden states. Based on the plurality of hidden states, the one or more processors may generate a plurality of output text tokens. Each output text token may have a corresponding output alignment within the audio input. For each output text token, a latency between the output alignment and the external-model alignment may be below a predetermined latency threshold. The one or more processors may output the text transcription.

2. 发明申请

WO2021201970A1 GENERATING AND USING TEXT-TO-SPEECH DATA FOR SPEECH RECOGNITION MODELS 审中-公开
公开(公告)号：WO2021201970A1
公开(公告)日：2021-10-07
申请号：PCT/US2021/016492
申请日：2021-02-04
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： YE, Guoli , HUANG, Yan , WEI, Wenning , HE, Lei , SHARMA, Eva , WU, Jian , TIAN, Yao , LIN, Edward C. , GONG, Yifan , ZHAO, Rui , LI, Jinyu , GALE, William Maxwell
IPC分类号： G10L15/065 , G10L15/16 , G10L13/02 , G10L13/08 , G10L25/30 , G10L15/08 , G10L15/063 , G10L15/26 , G10L2015/088
摘要： Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

3. 发明申请

WO2020214260A1 UNIVERSAL ACOUSTIC MODELING USING NEURAL MIXTURE MODELS 审中-公开
公开(公告)号：WO2020214260A1
公开(公告)日：2020-10-22
申请号：PCT/US2020/020718
申请日：2020-03-03
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： DAS, Amit , LI, Jinyu , LIU, Changliang , GONG, Yifan
IPC分类号： G10L15/16 , G10L15/32 , G06N3/02 , G06N20/20
摘要： According to some embodiments, a universal modeling system may include a plurality of domain expert models to each receive raw input data (e.g., a stream of audio frames containing speech utterances) and provide a domain expert output based on the raw input data. A neural mixture component may then generate a weight corresponding to each domain expert model based on information created by the plurality of domain expert models (e.g., hidden features and/or row convolution). The weights might be associated with, for example, constrained scalar numbers, unconstrained scaler numbers, vectors, matrices, etc. An output layer may provide a universal modeling system output (e.g., an automatic speech recognition result) based on each domain expert output after being multiplied by the corresponding weight for that domain expert model.

4. 发明申请

WO2019217101A1 MULTI-MODAL SPEECH ATTRIBUTION AMONG N SPEAKERS 审中-公开
公开(公告)号：WO2019217101A1
公开(公告)日：2019-11-14
申请号：PCT/US2019/029519
申请日：2019-04-27
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： ZHANG, Shixiong , WU, Lingfeng , KRUPKA, Eyal , XIAO, Xiong , GONG, Yifan
IPC分类号： G10L21/0272 , G10L21/0216 , G10L21/02 , G10L17/00
摘要： A computerized conference assistant includes a camera and a microphone. A face location machine of the computerized conference assistant finds a physical location of a human, based on a position of a candidate face in digital video captured by the camera. A beamforming machine of the computerized conference assistant outputs a beamformed signal isolating sounds originating from the physical location of the human. A diarization machine of the computerized conference assistant attributes information encoded in the beamformed signal to the human.

5. 发明申请

WO2022103430A1 CAPTION ASSISTED CALLING TO MAINTAIN CONNECTION IN CHALLENGING NETWORK CONDITIONS 审中-公开
公开(公告)号：WO2022103430A1
公开(公告)日：2022-05-19
申请号：PCT/US2021/029262
申请日：2021-04-27
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MAHAJAN, Akash Alok , GONG, Yifan
IPC分类号： H04L29/06
摘要： Systems are provided for managing and coordinating STT/TTS systems and the communications between these systems when they are connected in online meetings and for mitigating connectivity issues that may arise during the online meetings to provide a seamless and reliable meeting experience with either live captions and/or rendered audio. Initially, online meeting communications are transmitted over a lossy connectionless type protocol/channel. Then, in response to detected connectivity problems with one or more systems involved in the online meeting, which can cause jitter or packet loss, for example, an instruction is dynamically generated and processed for causing one or more of the connected systems to transmit and/or process the online meeting content with a more reliable connection/protocol, such as a connection-oriented protocol. Codecs at the systems are used, when needed to convert speech to text with related speech attribute information and to convert text to speech.

6. 发明申请

WO2021015879A1 STREAMING CONTEXTUAL UNIDIRECTIONAL MODELS 审中-公开
公开(公告)号：WO2021015879A1
公开(公告)日：2021-01-28
申请号：PCT/US2020/036820
申请日：2020-06-09
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： LI, Jinyu , AGARWAL, Amit, Kumar , GONG, Yifan , KESAVAMOORTHY, Harini
IPC分类号： G06N3/04 , G10L15/16 , G06N3/08 , G10L15/02
摘要： Streaming machine learning unidirectional models is facilitated by the use of embedding vectors. Processing blocks in the models apply embedding vectors as input. The embedding vectors utilize context of future data (e.g., data that is temporally offset into the future within a data stream) to improve the accuracy of the outputs generated by the processing blocks. The embedding vectors cause a temporal shift between the outputs of the processing blocks and the inputs to which the outputs correspond. This temporal shift enables the processing blocks to apply the embedding vector inputs from processing blocks that are associated with future data.

7. 发明申请

WO2020214281A1 CODE-SWITCHING SPEECH RECOGNITION WITH END-TO-END CONNECTIONIST TEMPORAL CLASSIFICATION MODEL 审中-公开
公开(公告)号：WO2020214281A1
公开(公告)日：2020-10-22
申请号：PCT/US2020/021931
申请日：2020-03-11
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： LI, Jinyu , YE, Guoli , ZHAO, Rui , GONG, Yifan , LI, Ke
IPC分类号： G10L15/16 , G10L15/00 , G06N3/04
摘要： A CS CTC model may be initialed from a major language CTC model by keeping network hidden weights and replacing output tokens with a union of major and secondary language output tokens. The initialized model may be trained by updating parameters with training data from both languages, and a LID model may also be trained with the data. During a decoding process for each of a series of audio frames, if silence dominates a current frame then a silence output token may be emitted. If silence does not dominate the frame, then a major language output token posterior vector from the CS CTC model may be multiplied with the LID major language probability to create a probability vector from the major language. A similar step is performed for the secondary language, and the system may emit an output token associated with the highest probability across all tokens from both languages.

8. 发明申请

WO2020197627A1 DYNAMIC COMBINATION OF ACOUSTIC MODEL STATES 审中-公开
公开(公告)号：WO2020197627A1
公开(公告)日：2020-10-01
申请号：PCT/US2020/015760
申请日：2020-01-30
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： KUMAR, Kshitiz , GONG, Yifan
IPC分类号： G10L15/16 , G10L15/065 , G06N3/04 , G10L15/20
摘要： A computer implemented method classifies an input corresponding to multiple different kinds of input. The method includes obtaining a set of features from the input, providing the set of features to multiple different models to generate state predictions, generating a set of state-dependent predicted weights, and combining the state predictions from the multiple models, based on the state-dependent predicted weights for classification of the set of features.

9. 发明申请

WO2015134294A1 LOW-FOOTPRINT ADAPTATION AND PERSONALIZATION FOR A DEEP NEURAL NETWORK 审中-公开
标题翻译：用于深层神经网络的低自适应和个性化
公开(公告)号：WO2015134294A1
公开(公告)日：2015-09-11
申请号：PCT/US2015/017872
申请日：2015-02-27
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： XUE, Jian , LI, Jinyu , YU, Dong , SELTZER, Michael L. , GONG, Yifan
IPC分类号： G10L15/07 , G10L15/16
CPC分类号： G10L15/16 , G06N3/082 , G10L15/075
摘要： The adaptation and personalization of a deep neural network (DNN) model for automatic speech recognition is provided. An utterance which includes speech features for one or more speakers may be received in ASR tasks such as voice search or short message dictation. A decomposition approach may then be applied to an original matrix in the DNN model. In response to applying the decomposition approach, the original matrix may be converted into multiple new matrices which are smaller than the original matrix. A square matrix may then be added to the new matrices. Speaker-specific parameters may then be stored in the square matrix. The DNN model may then be adapted by updating the square matrix. This process may be applied to all of a number of original matrices in the DNN model. The adapted DNN model may include a reduced number of parameters than those received in the original DNN model.
摘要翻译：提供了一种用于自动语音识别的深层神经网络（DNN）模型的适应和个性化。可以在诸如语音搜索或短消息听写的ASR任务中接收包括用于一个或多个扬声器的语音特征的话语。然后可以将分解方法应用于DNN模型中的原始矩阵。响应于应用分解方法，原始矩阵可以被转换成小于原始矩阵的多个新矩阵。然后可以将正方形矩阵添加到新矩阵。然后可以将扬声器特定参数存储在方阵中。然后可以通过更新方阵来适应DNN模型。该过程可以应用于DNN模型中的所有原始矩阵。适应的DNN模型可以包括与原始DNN模型中接收的参数相比减少的参数数量。

10. 发明申请

WO2020214298A1 ADVERSARIAL SPEAKER ADAPTATION 审中-公开
公开(公告)号：WO2020214298A1
公开(公告)日：2020-10-22
申请号：PCT/US2020/022875
申请日：2020-03-16
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MENG, Zhong , LI, Jinyu , GONG, Yifan
IPC分类号： G10L15/07 , G10L15/16 , G10L25/30
摘要： Embodiments are associated with a speaker-independent acoustic model capable of classifying senones based on input speech frames and on first parameters of the speaker-independent acoustic model, a speaker-dependent acoustic model capable of classifying senones based on input speech frames and on second parameters of the speaker-dependent acoustic model, and a discriminator capable of receiving data from the speaker-dependent acoustic model and data from the speaker-independent acoustic model and outputting a prediction of whether received data was generated by the speaker-dependent acoustic model based on third parameters. The second parameters are initialized based on the first parameters, the second parameters are trained based on input frames of a target speaker to minimize a senone classification loss associated with the second parameters, a portion of the second parameters are trained based on the input frames of the target speaker to maximize a discrimination loss associated with the discriminator, and the third parameters are trained based on the input frames of the target speaker to minimize the discrimination loss.

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