Abstract: 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.

Abstract: 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.

Abstract: A method for performing speech recognition using sequence-to-sequence models includes receiving audio data for an utterance and providing features indicative of acoustic characteristics of the utterance as input to an encoder. The method also includes processing an output of the encoder using an attender to generate a context vector, generating speech recognition scores using the context vector and a decoder trained using a training process, and generating a transcription for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for enhanced attention mechanisms. In some implementations, data indicating an input sequence is received. The data is processed using an encoder neural network to generate a sequence of encodings. A series of attention outputs is determined using one or more attender modules. Determining each attention output can include (i) selecting an encoding from the sequence of encodings and (ii) determining attention over a proper subset of the sequence of encodings, where the proper subset of encodings is determined based on a position of the selected encoding in the sequence of encodings. The selections of encodings are also monotonic through the sequence of encodings. An output sequence is generated by processing the attention outputs using a decoder neural network. An output is provided that indicates a language sequence determined from the output sequence.

Abstract: 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.

Abstract: Methods, systems, and apparatus, including computer-readable media, for performing speech recognition using sequence-to-sequence models. An automated speech recognition (ASR) system receives audio data for an utterance and provides features indicative of acoustic characteristics of the utterance as input to an encoder. The system processes an output of the encoder using an attender to generate a context vector and generates speech recognition scores using the context vector and a decoder trained using a training process that selects at least one input to the decoder with a predetermined probability. An input to the decoder during training is selected between input data based on a known value for an element in a training example, and input data based on an output of the decoder for the element in the training example. A transcription is generated for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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 am 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Methods, systems, and apparatus, including computer-readable media, for performing speech recognition using sequence-to-sequence models. An automated speech recognition (ASR) system receives audio data for an utterance and provides features indicative of acoustic characteristics of the utterance as input to an encoder. The system processes an output of the encoder using an attender to generate a context vector and generates speech recognition scores using the context vector and a decoder trained using a training process that selects at least one input to the decoder with a predetermined probability. An input to the decoder during training is selected between input data based on a known value for an element in a training example, and input data based on an output of the decoder for the element in the training example. A transcription is generated for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for enhanced attention mechanisms. In some implementations, data indicating an input sequence is received. The data is processed using an encoder neural network to generate a sequence of encodings. A series of attention outputs is determined using one or more attender modules. Determining each attention output can include (i) selecting an encoding from the sequence of encodings and (ii) determining attention over a proper subset of the sequence of encodings, where the proper subset of encodings is determined based on a position of the selected encoding in the sequence of encodings. The selections of encodings are also monotonic through the sequence of encodings. An output sequence is generated by processing the attention outputs using a decoder neural network. An output is provided that indicates a language sequence determined from the output sequence.

Abstract: 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.

Abstract: 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 am 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.

Abstract: The invention relates to a method for image processing, which can be used to calibrate the background quickly. When the external environment is changed due to the switch of light, the color of background is calibrated quickly, and the background can be updated together. The method not only is used to update the background, but also can be used to eliminate the convergence of background again.

Abstract: The invention discloses the asynchronous photography for dual camera apparatus and processing the method for real-time forward vehicle detection. Image is captured by a pair of monochrome camera and stored into a computer. After the video pre-process, the edge information is used to locate the forward vehicle position, and then obtained the disparity from a fast comparison search algorithm by the stereo vision methodology. Proposed algorithm calculation of the invention can conquer the asynchronous exposure problem from dual camera and lower the hardware cost.

Abstract: The invention relates to a method for image processing. First, establish the initial image background information. And retrieve the instant image information. Then calculate the initial image background information and color intensity information of the instant image. Furthermore, adjust the instant image information. Then calculate the moving-object information. Finally, track the moving-object information. It can improve the accuracy rate of detection without the influence of erected height.