Patents by Inventor Chung-Cheng Chiu
Chung-Cheng Chiu 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: 11935935Abstract: A thin film transistor includes a gate electrode embedded in an insulating layer that overlies a substrate, a gate dielectric overlying the gate electrode, an active layer comprising a compound semiconductor material and overlying the gate dielectric, and a source electrode and drain electrode contacting end portions of the active layer. The gate dielectric may have thicker portions over interfaces with the insulating layer to suppress hydrogen diffusion therethrough. Additionally or alternatively, a passivation capping dielectric including a dielectric metal oxide material may be interposed between the active layer and a dielectric layer overlying the active layer to suppress hydrogen diffusion therethrough.Type: GrantFiled: November 11, 2021Date of Patent: March 19, 2024Assignee: Taiwan Semiconductor Manufacturing Company LimitedInventors: Min-Kun Dai, Wei-Gang Chiu, I-Cheng Chang, Cheng-Yi Wu, Han-Ting Tsai, Tsann Lin, Chung-Te Lin
-
Patent number: 11922932Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses a set of speech recognition hypothesis samples, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.Type: GrantFiled: March 31, 2023Date of Patent: March 5, 2024Assignee: Google LLCInventors: Rohit Prakash Prabhavalkar, Tara N. Sainath, Yonghui Wu, Patrick An Phu Nguyen, Zhifeng Chen, Chung-Cheng Chiu, Anjuli Patricia Kannan
-
Publication number: 20240029716Abstract: A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.Type: ApplicationFiled: October 4, 2023Publication date: January 25, 2024Applicant: Google LLCInventors: Thibault Doutre, Wei Han, Min Ma, Zhiyun Lu, Chung-Cheng Chiu, Ruoming Pang, Arun Narayanan, Ananya Misra, Yu Zhang, Liangliang Cao
-
Patent number: 11816577Abstract: Generally, the present disclosure is directed to systems and methods that generate augmented training data for machine-learned models via application of one or more augmentation techniques to audiographic images that visually represent audio signals. In particular, the present disclosure provides a number of novel augmentation operations which can be performed directly upon the audiographic image (e.g., as opposed to the raw audio data) to generate augmented training data that results in improved model performance. As an example, the audiographic images can be or include one or more spectrograms or filter bank sequences.Type: GrantFiled: September 28, 2021Date of Patent: November 14, 2023Assignee: GOOGLE LLCInventors: Daniel Sung-Joon Park, Quoc Le, William Chan, Ekin Dogus Cubuk, Barret Zoph, Yu Zhang, Chung-Cheng Chiu
-
Publication number: 20230359898Abstract: Generally, the present disclosure is directed to systems and methods that generate augmented training data for machine-learned models via application of one or more augmentation techniques to audiographic images that visually represent audio signals. In particular, the present disclosure provides a number of novel augmentation operations which can be performed directly upon the audiographic image (e.g., as opposed to the raw audio data) to generate augmented training data that results in improved model performance. As an example, the audiographic images can be or include one or more spectrograms or filter bank sequences.Type: ApplicationFiled: July 11, 2023Publication date: November 9, 2023Inventors: Daniel Sung-Joon Park, Quoc Le, William Chan, Ekin Dogus Cubuk, Barret Zoph, Yu Zhang, Chung-Cheng Chiu
-
Patent number: 11804212Abstract: A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.Type: GrantFiled: June 15, 2021Date of Patent: October 31, 2023Assignee: Google LLCInventors: Thibault Doutre, Wei Han, Min Ma, Zhiyun Lu, Chung-Cheng Chiu, Ruoming Pang, Arun Narayanan, Ananya Misra, Yu Zhang, Liangliang Cao
-
Publication number: 20230237995Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses a set of speech recognition hypothesis samples, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.Type: ApplicationFiled: March 31, 2023Publication date: July 27, 2023Applicant: Google LLCInventors: Rohit Prakash Prabhavalkar, Tara N. Sainath, Younghui Wu, Patrick An Phu Nguyen, Zhifeng Chen, Chung-Cheng Chiu, Anjuli Kannan
-
Publication number: 20230237993Abstract: Systems and methods of the present disclosure are directed to a computing system, including one or more processors and a machine-learned multi-mode speech recognition model configured to operate in a streaming recognition mode or a contextual recognition mode. The computing system can perform operations including obtaining speech data and a ground truth label and processing the speech data using the contextual recognition mode to obtain contextual prediction data. The operations can include evaluating a difference between the contextual prediction data and the ground truth label and processing the speech data using the streaming recognition mode to obtain streaming prediction data. The operations can include evaluating a difference between the streaming prediction data and the ground truth label and the contextual and streaming prediction data. The operations can include adjusting parameters of the speech recognition model.Type: ApplicationFiled: October 1, 2021Publication date: July 27, 2023Inventors: Jiahui Yu, Ruoming Pang, Wei Han, Anmol Gulati, Chung-Cheng Chiu, Bo Li, Tara N. Sainath, Yonghui Hu
-
Publication number: 20230186901Abstract: A method includes receiving a training example for a listen-attend-spell (LAS) decoder of a two-pass streaming neural network model and determining whether the training example corresponds to a supervised audio-text pair or an unpaired text sequence. When the training example corresponds to an unpaired text sequence, the method also includes determining a cross entropy loss based on a log probability associated with a context vector of the training example. The method also includes updating the LAS decoder and the context vector based on the determined cross entropy loss.Type: ApplicationFiled: February 10, 2023Publication date: June 15, 2023Applicant: Google LLCInventors: Tara N. Sainath, Ruoming Pang, Ron Weiss, Yanzhang He, Chung-Cheng Chiu, Trevor Strohman
-
Patent number: 11646019Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses N-best lists of decoded hypotheses, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.Type: GrantFiled: July 27, 2021Date of Patent: May 9, 2023Assignee: Google LLCInventors: Rohit Prakash Prabhavalkar, Tara N. Sainath, Yonghui Wu, Patrick An Phu Nguyen, Zhifeng Chen, Chung-Cheng Chiu, Anjuli Patricia Kannan
-
Patent number: 11625572Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a target sequence from a source sequence. In one aspect, the system includes a recurrent neural network configured to, at each time step, receive an input for the time step and process the input to generate a progress score and a set of output scores; and a subsystem configured to, at each time step, generate the recurrent neural network input and provide the input to the recurrent neural network; determine, from the progress score, whether or not to emit a new output at the time step; and, in response to determining to emit a new output, select an output using the output scores and emit the selected output as the output at a next position in the output order.Type: GrantFiled: May 3, 2018Date of Patent: April 11, 2023Assignee: Google LLCInventors: Chung-Cheng Chiu, Navdeep Jaitly, John Dieterich Lawson, George Jay Tucker
-
Patent number: 11594212Abstract: A method includes receiving a training example for a listen-attend-spell (LAS) decoder of a two-pass streaming neural network model and determining whether the training example corresponds to a supervised audio-text pair or an unpaired text sequence. When the training example corresponds to an unpaired text sequence, the method also includes determining a cross entropy loss based on a log probability associated with a context vector of the training example. The method also includes updating the LAS decoder and the context vector based on the determined cross entropy loss.Type: GrantFiled: January 21, 2021Date of Patent: February 28, 2023Assignee: Google LLCInventors: Tara N. Sainath, Ruoming Pang, Ron Weiss, Yanzhang He, Chung-Cheng Chiu, Trevor Strohman
-
Publication number: 20230038982Abstract: A method for automatic speech recognition using joint acoustic echo cancellation, speech enhancement, and voice separation includes receiving, at a contextual frontend processing model, input speech features corresponding to a target utterance. The method also includes receiving, at the contextual frontend processing model, at least one of a reference audio signal, a contextual noise signal including noise prior to the target utterance, or a speaker embedding including voice characteristics of a target speaker that spoke the target utterance. The method further includes processing, using the contextual frontend processing model, the input speech features and the at least one of the reference audio signal, the contextual noise signal, or the speaker embedding vector to generate enhanced speech features.Type: ApplicationFiled: December 14, 2021Publication date: February 9, 2023Applicant: Google LLCInventors: Arun Narayanan, Tom O'malley, Quan Wang, Alex Park, James Walker, Nathan David Howard, Yanzhang He, Chung-Cheng Chiu
-
Publication number: 20220343894Abstract: A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.Type: ApplicationFiled: June 15, 2021Publication date: October 27, 2022Applicant: Google LLCInventors: Thibault Doutre, Wei Han, Min Ma, Zhiyun Lu, Chung-Cheng Chiu, Ruoming Pang, Arun Narayanan, Ananya Misra, Yu Zhang, Liangliang Cao
-
Publication number: 20220310072Abstract: Two-pass automatic speech recognition (ASR) models can be used to perform streaming on-device ASR to generate a text representation of an utterance captured in audio data. Various implementations include a first-pass portion of the ASR model used to generate streaming candidate recognition(s) of an utterance captured in audio data. For example, the first-pass portion can include a recurrent neural network transformer (RNN-T) decoder. Various implementations include a second-pass portion of the ASR model used to revise the streaming candidate recognition(s) of the utterance and generate a text representation of the utterance. For example, the second-pass portion can include a listen attend spell (LAS) decoder. Various implementations include a shared encoder shared between the RNN-T decoder and the LAS decoder.Type: ApplicationFiled: June 3, 2020Publication date: September 29, 2022Inventors: Tara N. Sainath, Ruoming Pang, David Rybach, Yanzhang He, Rohit Prabhavalkar, Wei Li, Mirkó Visontai, Qiao Liang, Trevor Strohman, Yonghui Wu, Ian C. McGraw, Chung-Cheng Chiu
-
Publication number: 20220207321Abstract: Systems and methods can utilize a conformer model to process a data set for various data processing tasks, including, but not limited to, speech recognition, sound separation, protein synthesis determination, video or other image set analysis, and natural language processing. The conformer model can use feed-forward blocks, a self-attention block, and a convolution block to process data to learn global interactions and relative-offset-based local correlations of the input data.Type: ApplicationFiled: December 31, 2020Publication date: June 30, 2022Inventors: Anmol Gulati, Ruoming Pang, Niki Parmar, Jiahui Yu, Wei Han, Chung-Cheng Chiu, Yu Zhang, Yonghui Wu, Shibo Wang, Weikeng Qin, Zhengdong Zhang
-
Patent number: 11335333Abstract: A method includes obtaining audio data for a long-form utterance and segmenting the audio data for the long-form utterance into a plurality of overlapping segments. The method also includes, for each overlapping segment of the plurality of overlapping segments: providing features indicative of acoustic characteristics of the long-form utterance represented by the corresponding overlapping segment as input to an encoder neural network; processing an output of the encoder neural network using an attender neural network to generate a context vector; and generating word elements using the context vector and a decoder neural network. The method also includes generating a transcription for the long-form utterance by merging the word elements from the plurality of overlapping segments and providing the transcription as an output of the automated speech recognition system.Type: GrantFiled: December 17, 2019Date of Patent: May 17, 2022Assignee: Google LLCInventors: Wei Han, Chung-Cheng Chiu, Yu Zhang, Yonghui Wu, Patrick Nguyen, Sergey Kishchenko
-
Publication number: 20220122586Abstract: A computer-implemented method of training a streaming speech recognition model that includes receiving, as input to the streaming speech recognition model, a sequence of acoustic frames. The streaming speech recognition model is configured to learn an alignment probability between the sequence of acoustic frames and an output sequence of vocabulary tokens. The vocabulary tokens include a plurality of label tokens and a blank token. At each output step, the method includes determining a first probability of emitting one of the label tokens and determining a second probability of emitting the blank token. The method also includes generating the alignment probability at a sequence level based on the first probability and the second probability. The method also includes applying a tuning parameter to the alignment probability at the sequence level to maximize the first probability of emitting one of the label tokens.Type: ApplicationFiled: September 9, 2021Publication date: April 21, 2022Applicant: Google LLCInventors: Jiahui Yu, Chung-cheng Chiu, Bo Li, Shuo-yiin Chang, Tara Sainath, Wei Han, Anmol Gulati, Yanzhang He, Arun Narayanan, Yonghui Wu, Ruoming Pang
-
Publication number: 20220122622Abstract: An automated speech recognition (ASR) model includes a first encoder, a second encoder, and a decoder. The first encoder receives, as input, a sequence of acoustic frames, and generates, at each of a plurality of output steps, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The second encoder receives, as input, the first higher order feature representation generated by the first encoder at each of the plurality of output steps, and generates, at each of the plurality of output steps, a second higher order feature representation for a corresponding first higher order feature frame. The decoder receives, as input, the second higher order feature representation generated by the second encoder at each of the plurality of output steps, and generates, at each of the plurality of time steps, a first probability distribution over possible speech recognition hypotheses.Type: ApplicationFiled: April 21, 2021Publication date: April 21, 2022Applicant: Google LLCInventors: Arun Narayanan, Tara Sainath, Chung-Cheng Chiu, Ruoming Pang, Rohit Prabhavalkar, Jiahui Yu, Ehsan Variani, Trevor Strohman
-
Publication number: 20220083743Abstract: A method includes receiving a sequence of audio features characterizing an utterance and processing, using an encoder neural network, the sequence of audio features to generate a sequence of encodings. At each of a plurality of output steps, the method also includes determining a corresponding hard monotonic attention output to select an encoding from the sequence of encodings, identifying a proper subset of the sequence of encodings based on a position of the selected encoding in the sequence of encodings, and performing soft attention over the proper subset of the sequence of encodings to generate a context vector at the corresponding output step. The method also includes processing, using a decoder neural network, the context vector generated at the corresponding output step to predict a probability distribution over possible output labels at the corresponding output step.Type: ApplicationFiled: November 30, 2021Publication date: March 17, 2022Applicant: Google LLCInventors: Chung-Cheng Chiu, Colin Abraham Raffel