Patents by Inventor Md Akmal Haidar
Md Akmal Haidar has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11715461Abstract: Computer implemented method and system for automatic speech recognition. A first speech sequence is processed, using a time reduction operation of an encoder NN, into a second speech sequence comprising a second set of speech frame feature vectors that each concatenate information from a respective plurality of speech frame feature vectors included in the first set and includes fewer speech frame feature vectors than the first speech sequence. The second speech sequence is transformed, using a self-attention operation of the encoder NN, into a third speech sequence comprising a third set of speech frame feature vectors. The third speech sequence is processed using a probability operation of the encoder NN, to predict a sequence of first labels corresponding to the third set of speech frame feature vectors, and using a decoder NN to predict a sequence of second labels corresponding to the third set of speech frame feature vectors.Type: GrantFiled: October 21, 2020Date of Patent: August 1, 2023Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Md Akmal Haidar, Chao Xing
-
Patent number: 11663483Abstract: According to embodiments, an encoder neural network receives a one-hot representation of a real text. The encoder neural network outputs a latent representation of the real text. A decoder neural network receives random noise data or artificial code generated by a generator neural network from random noise data. The decoder neural network outputs softmax representation of artificial text. The decoder neural network receives the latent representation of the real text. The decoder neural network outputs a reconstructed softmax representation of the real text. A hybrid discriminator neural network receives a first combination of the soft-text and the latent representation of the real text and a second combination of the softmax representation of artificial text and the artificial code. The hybrid discriminator neural network outputs a probability indicating whether the second combination is similar to the first combination. Additional embodiments for utilizing latent representation are also disclosed.Type: GrantFiled: October 30, 2018Date of Patent: May 30, 2023Assignee: Huawei Technologies Co., Ltd.Inventors: Md Akmal Haidar, Mehdi Rezagholizadeh
-
Patent number: 11586833Abstract: A method and machine translation system for bi-directional translation of textual sequences between a first language and a second language are described. The machine translation system includes a first autoencoder configured to receive a vector representation of a first textual sequence in the first language and encode the vector representation of the first textual sequence into a first sentence embedding. The machine translation system also includes a sum-product network (SPN) configured to receive the first sentence embedding and generate a second sentence embedding by maximizing a first conditional probability of the second sentence embedding given the first sentence embedding and a second autoencoder receiving the second sentence embedding, the second autoencoder being trained to decode the second sentence embedding into a vector representation of a second textual sequence in the second language.Type: GrantFiled: June 12, 2020Date of Patent: February 21, 2023Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Mehdi Rezagholizadeh, Vahid Partovi Nia, Md Akmal Haidar, Pascal Poupart
-
Publication number: 20220335303Abstract: Methods, devices and processor-readable media for knowledge distillation using intermediate representations are described. A student model is trained using a Dropout-KD approach in which intermediate layer selection is performed efficiently such that the skip, search, and overfitting problems in intermediate layer KD may be solved. Teacher intermediate layers are selected randomly at each training epoch, with the layer order preserved to avoid breaking information flow. Over the course of multiple training epochs, all of the teacher intermediate layers are used for knowledge distillation. A min-max data augmentation method is also described based on the intermediate layer selection of the Dropout-KD training method.Type: ApplicationFiled: April 16, 2021Publication date: October 20, 2022Inventors: Md Akmal HAIDAR, Mehdi REZAGHOLIZADEH
-
Patent number: 11423282Abstract: In accordance to embodiments, an encoder neural network is configured to receive a one-hot representation of a real text and output a latent representation of the real text generated from the one-hot representation of the real text. A decoder neural network is configured to receive the latent representation of the real text, and output a reconstructed softmax representation of the real text from the latent representation of the real text, the reconstructed softmax representation of the real text is a soft-text. A generator neural network is configured to generate artificial text based on random noise data. A discriminator neural network is configured to receive the soft-text and receive a softmax representation of the artificial text, and output a probability indicating whether the softmax representation of the artificial text received by the discriminator neural network is not from the generator neural network.Type: GrantFiled: October 30, 2018Date of Patent: August 23, 2022Assignee: Huawei Technologies Co., Ltd.Inventors: Md Akmal Haidar, Mehdi Rezagholizadeh
-
Publication number: 20220122590Abstract: Computer implemented method and system for automatic speech recognition. A first speech sequence is processed, using a time reduction operation of an encoder NN, into a second speech sequence that comprises a second set of speech frame feature vectors that each concatenate information from a respective plurality of speech frame feature vectors included in the first set, wherein the second speech sequence includes fewer speech frame feature vectors than the first speech sequence. The second speech sequence is transformed, using a self-attention operation of the encoder NN, into a third speech sequence that comprises a third set of speech frame feature vectors. The third speech sequence is processed, using a probability operation of the encoder NN, to predict a sequence of first labels corresponding to the third set of speech frame feature vectors. The third speech sequence is also processed using a decoder NN to predict a sequence of second labels corresponding to the third set of speech frame feature vectors.Type: ApplicationFiled: October 21, 2020Publication date: April 21, 2022Inventors: Md Akmal HAIDAR, Chao XING
-
Publication number: 20210390269Abstract: A method and machine translation system for bi-directional translation of textual sequences between a first language and a second language are described. The machine translation system includes a first autoencoder configured to receive a vector representation of a first textual sequence in the first language and encode the vector representation of the first textual sequence into a first sentence embedding. The machine translation system also includes a sum-product network (SPN) configured to receive the first sentence embedding and generate a second sentence embedding by maximizing a first conditional probability of the second sentence embedding given the first sentence embedding and a second autoencoder receiving the second sentence embedding, the second autoencoder being trained to decode the second sentence embedding into a vector representation of a second textual sequence in the second language.Type: ApplicationFiled: June 12, 2020Publication date: December 16, 2021Inventors: Mehdi REZAGHOLIZADEH, Vahid PARTOVI NIA, Md Akmal HAIDAR, Pascal POUPART
-
Patent number: 11151334Abstract: In at least one broad aspect, described herein are systems and methods in which a latent representation shared between two languages is built and/or accessed, and then leveraged for the purpose of text generation in both languages. Neural text generation techniques are applied to facilitate text generation, and in particular the generation of sentences (i.e., sequences of words or subwords) in both languages, in at least some embodiments.Type: GrantFiled: September 26, 2018Date of Patent: October 19, 2021Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Mehdi Rezagholizadeh, Md Akmal Haidar, Alan Do-Omri, Ahmad Rashid
-
Patent number: 11120337Abstract: A method and system for augmenting a training dataset for a generative adversarial network (GAN). The training dataset includes labelled data samples and unlabelled data samples. The method includes: receiving generated samples generated using a first neural network of the GAN and the unlabelled samples of training dataset; determining a decision value for a sample from a decision function, wherein the sample is a generated sample of the generated samples or an unlabelled sample of the unlabelled samples of the training dataset; comparing the decision value to a threshold; in response to determining that the decision value exceeds the threshold: predicting a label for a sample; assigning the label to the sample; and augmenting the training dataset to include the sample with the assigned label as a labelled sample.Type: GrantFiled: October 20, 2017Date of Patent: September 14, 2021Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Dalei Wu, Md Akmal Haidar, Mehdi Rezagholizadeh, Alan Do-Omri
-
Patent number: 11003995Abstract: Method and system for performing semi-supervised regression with a generative adversarial network (GAN) that includes a generator comprising a first neural network and a discriminator comprising a second neural network, comprising: outputting, from the first neural network, generated samples derived from a random noise vector; inputting, to the second neural network, the generated samples, a plurality of labelled training samples, and a plurality of unlabelled training samples; and outputting, from the second neural network, a predicted continuous label for each of a plurality of the generated samples and unlabelled samples.Type: GrantFiled: October 20, 2017Date of Patent: May 11, 2021Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Mehdi Rezagholizadeh, Md Akmal Haidar, Dalei Wu
-
Publication number: 20200134415Abstract: In accordance to embodiments, an encoder neural network is configured to receive a one-hot representation of a real text and output a latent representation of the real text generated from the one-hot representation of the real text. A decoder neural network is configured to receive the latent representation of the real text, and output a reconstructed softmax representation of the real text from the latent representation of the real text, the reconstructed softmax representation of the real text is a soft-text. A generator neural network is configured to generate artificial text based on random noise data. A discriminator neural network is configured to receive the soft-text and receive a softmax representation of the artificial text, and output a probability indicating whether the softmax representation of the artificial text received by the discriminator neural network is not from the generator neural network.Type: ApplicationFiled: October 30, 2018Publication date: April 30, 2020Inventors: Md Akmal Haidar, Mehdi Rezagholizadeh
-
Publication number: 20200134463Abstract: According to embodiments, an encoder neural network receives a one-hot representation of a real text. The encoder neural network outputs a latent representation of the real text. A decoder neural network receives random noise data or artificial code generated by a generator neural network from random noise data. The decoder neural network outputs softmax representation of artificial text. The decoder neural network receives the latent representation of the real text. The decoder neural network outputs a reconstructed softmax representation of the real text. A hybrid discriminator neural network receives a first combination of the soft-text and the latent representation of the real text and a second combination of the softmax representation of artificial text and the artificial code. The hybrid discriminator neural network outputs a probability indicating whether the second combination is similar to the first combination. Additional embodiments for utilizing latent representation are also disclosed.Type: ApplicationFiled: October 30, 2018Publication date: April 30, 2020Inventors: Md Akmal Haidar, Mehdi Rezagholizadeh
-
Publication number: 20200097554Abstract: In at least one broad aspect, described herein are systems and methods in which a latent representation shared between two languages is built and/or accessed, and then leveraged for the purpose of text generation in both languages. Neural text generation techniques are applied to facilitate text generation, and in particular the generation of sentences (i.e., sequences of words or subwords) in both languages, in at least some embodiments.Type: ApplicationFiled: September 26, 2018Publication date: March 26, 2020Applicant: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Mehdi REZAGHOLIZADEH, Md Akmal HAIDAR, Alan DO-OMRI, Ahmad RASHID
-
Publication number: 20190122120Abstract: A method and system for augmenting a training dataset for a generative adversarial network (GAN). The training dataset includes labelled data samples and unlabelled data samples. The method includes: receiving generated samples generated using a first neural network of the GAN and the unlabelled samples of training dataset; determining a decision value for a sample from a decision function, wherein the sample is a generated sample of the generated samples or an unlabelled sample of the unlabelled samples of the training dataset; comparing the decision value to a threshold; in response to determining that the decision value exceeds the threshold: predicting a label for a sample; assigning the label to the sample; and augmenting the training dataset to include the sample with the assigned label as a labelled sample.Type: ApplicationFiled: October 20, 2017Publication date: April 25, 2019Inventors: Dalei Wu, Md Akmal Haidar, Mehdi Rezagholizadeh, Alan Do-Omri
-
Publication number: 20180336471Abstract: Method and system for performing semi-supervised regression with a generative adversarial network (GAN) that includes a generator comprising a first neural network and a discriminator comprising a second neural network, comprising: outputting, from the first neural network, generated samples derived from a random noise vector; inputting, to the second neural network, the generated samples, a plurality of labelled training samples, and a plurality of unlabelled training samples; and outputting, from the second neural network, a predicted continuous label for each of a plurality of the generated samples and unlabelled samples.Type: ApplicationFiled: October 20, 2017Publication date: November 22, 2018Inventors: Mehdi Rezagholizadeh, Md Akmal Haidar, Dalei Wu