Abstract: A system for processing and presenting a conversation includes a sensor, a processor, and a presenter. The sensor is configured to capture an audio-form conversation. The processor is configured to automatically transform the audio-form conversation into a transformed conversation. The transformed conversation includes a synchronized text, wherein the synchronized text is synchronized with the audio-form conversation. The presenter is configured to present the transformed conversation including the synchronized text and the audio-form conversation. The presenter is further configured to present the transformed conversation to be navigable, searchable, assignable, editable, and shareable.

Abstract: Computer-implemented method and system for receiving and processing one or more moment-associating elements. For example, the computer-implemented method includes receiving the one or more moment-associating elements, transforming the one or more moment-associating elements into one or more pieces of moment-associating information, and transmitting at least one piece of the one or more pieces of moment-associating information.

Abstract: Techniques are described for training neural networks on variable length datasets. The numeric representation of the length of each training sample is randomly perturbed to yield a pseudo-length, and the samples sorted by pseudo-length to achieve lower zero padding rate (ZPR) than completely randomized batching (thus saving computation time) yet higher randomness than strictly sorted batching (thus achieving better model performance than strictly sorted batching).

Abstract: Computer-implemented method and system for receiving and processing one or more moment-associating elements. For example, the computer-implemented method includes receiving the one or more moment-associating elements, transforming the one or more moment-associating elements into one or more pieces of moment-associating information, and transmitting at least one piece of the one or more pieces of moment-associating information.

Abstract: A wake-up word for a digital assistant may be specified by a user to trigger the digital assistant to respond to the wake-up word, with the user providing one or more initial pronunciations of the wake-up word. The wake-up word may be unique, or at least not determined beforehand by a device manufacturer or developer of the digital assistant. The initial pronunciation(s) of the keyword may then be augmented with other potential pronunciations of the wake-up word that might be provided in the future, and those other potential pronunciations may then be pruned down to a threshold number of other potential pronunciations. One or more recordings of the initial pronunciation(s) of the wake-up may then be used to train a phoneme recognizer model to better recognize future instances of the wake-up word being spoken by the user or another person using the initial pronunciation or other potential pronunciations.

Abstract: Techniques are described for training neural networks on variable length datasets. The numeric representation of the length of each training sample is randomly perturbed to yield a pseudo-length, and the samples sorted by pseudo-length to achieve lower zero padding rate (ZPR) than completely randomized batching (thus saving computation time) yet higher randomness than strictly sorted batching (thus achieving better model performance than strictly sorted batching).

Abstract: Techniques are described for training neural networks on variable length datasets. The numeric representation of the length of each training sample is randomly perturbed to yield a pseudo-length, and the samples sorted by pseudo-length to achieve lower zero padding rate (ZPR) than completely randomized batching (thus saving computation time) yet higher randomness than strictly sorted batching (thus achieving better model performance than strictly sorted batching).

Abstract: Techniques are described for training neural networks on variable length datasets. The numeric representation of the length of each training sample is randomly perturbed to yield a pseudo-length, and the samples sorted by pseudo-length to achieve lower zero padding rate (ZPR) than completely randomized batching (thus saving computation time) yet higher randomness than strictly sorted batching (thus achieving better model performance than strictly sorted batching).

Abstract: A wake-up word for a digital assistant may be specified by a user to trigger the digital assistant to respond to the wake-up word, with the user providing one or more initial pronunciations of the wake-up word. The wake-up word may be unique, or at least not determined beforehand by a device manufacturer or developer of the digital assistant. The initial pronunciation(s) of the keyword may then be augmented with other potential pronunciations of the wake-up word that might be provided in the future, and those other potential pronunciations may then be pruned down to a threshold number of other potential pronunciations. One or more recordings of the initial pronunciation(s) of the wake-up may then be used to train a phoneme recognizer model to better recognize future instances of the wake-up word being spoken by the user or another person using the initial pronunciation or other potential pronunciations.

Abstract: A wake-up word for a digital assistant may be specified by a user to trigger the digital assistant to respond to the wake-up word, with the user providing one or more initial pronunciations of the wake-up word. The wake-up word may be unique, or at least not determined beforehand by a device manufacturer or developer of the digital assistant. The initial pronunciation(s) of the keyword may then be augmented with other potential pronunciations of the wake-up word that might be provided in the future, and those other potential pronunciations may then be pruned down to a threshold number of other potential pronunciations. One or more recordings of the initial pronunciation(s) of the wake-up may then be used to train a phoneme recognizer model to better recognize future instances of the wake-up word being spoken by the user or another person using the initial pronunciation or other potential pronunciations.

Abstract: A system for processing and presenting a conversation includes a sensor, a processor, and a presenter. The sensor is configured to capture an audio-form conversation. The processor is configured to automatically transform the audio-form conversation into a transformed conversation. The transformed conversation includes a synchronized text, wherein the synchronized text is synchronized with the audio-form conversation. The presenter is configured to present the transformed conversation including the synchronized text and the audio-form conversation. The presenter is further configured to present the transformed conversation to be navigable, searchable, assignable, editable, and shareable.

Abstract: Computer-implemented method and system for receiving and processing one or more moment-associating elements. For example, the computer-implemented method includes receiving the one or more moment-associating elements, transforming the one or more moment-associating elements into one or more pieces of moment-associating information, and transmitting at least one piece of the one or more pieces of moment-associating information.

Abstract: A system for processing and presenting a conversation includes a sensor, a processor, and a presenter. The sensor is configured to capture an audio-form conversation. The processor is configured to automatically transform the audio-form conversation into a transformed conversation. The transformed conversation includes a synchronized text, wherein the synchronized text is synchronized with the audio-form conversation. The presenter is configured to present the transformed conversation including the synchronized text and the audio-form conversation. The presenter is further configured to present the transformed conversation to be navigable, searchable, assignable, editable, and shareable.

Abstract: Computer-implemented method and system for receiving and processing one or more moment-associating elements. For example, the computer-implemented method includes receiving the one or more moment-associating elements, transforming the one or more moment-associating elements into one or more pieces of moment-associating information, and transmitting at least one piece of the one or more pieces of moment-associating information.

Abstract: The performance of a player of a computer game is noted and the player accorded a latency handicap based thereon. The latency handicap is used to slow down play of the computer game, preferably only during times of high player activity. The latency handicap can be reduced over time or owing to improvement in the player's performance.

Abstract: A wake-up word for a digital assistant may be specified by a user to trigger the digital assistant to respond to the wake-up word, with the user providing one or more initial pronunciations of the wake-up word. The wake-up word may be unique, or at least not determined beforehand by a device manufacturer or developer of the digital assistant. The initial pronunciation(s) of the keyword may then be augmented with other potential pronunciations of the wake-up word that might be provided in the future, and those other potential pronunciations may then be pruned down to a threshold number of other potential pronunciations. One or more recordings of the initial pronunciation(s) of the wake-up may then be used to train a phoneme recognizer model to better recognize future instances of the wake-up word being spoken by the user or another person using the initial pronunciation or other potential pronunciations.

Abstract: A method for classifying speakers includes: receiving, by a speaker recognition system including a processor and memory, input audio including speech from a speaker; extracting, by the speaker recognition system, a plurality of speech frames containing voiced speech from the input audio; computing, by the speaker recognition system, a plurality of features for each of the speech frames of the input audio; computing, by the speaker recognition system, a plurality of recognition scores for the plurality of features; computing, by the speaker recognition system, a speaker classification result in accordance with the recognition scores; and outputting, by the speaker recognition system, the speaker classification result.

Abstract: A method for training a neural network of a neural network based speaker classifier for use in speaker change detection. The method comprises: a) preprocessing input speech data; b) extracting a plurality of feature frames from the preprocessed input speech data; c) normalizing the extracted feature frames of each speaker within the preprocessed input speech data with each speaker's mean and variance; d) concatenating the normalized feature frames to form overlapped longer frames having a frame length and a hop size; e) inputting the overlapped longer frames to the neural network based speaker classifier; and f) training the neural network through forward-backward propagation.

Abstract: A method for classifying speakers includes: receiving, by a speaker recognition system including a processor and memory, input audio including speech from a speaker; extracting, by the speaker recognition system, a plurality of speech frames containing voiced speech from the input audio; computing, by the speaker recognition system, a plurality of features for each of the speech frames of the input audio; computing, by the speaker recognition system, a plurality of recognition scores for the plurality of features; computing, by the speaker recognition system, a speaker classification result in accordance with the recognition scores; and outputting, by the speaker recognition system, the speaker classification result.

Abstract: A method for training a neural network of a neural network based speaker classifier for use in speaker change detection. The method comprises: a) preprocessing input speech data; b) extracting a plurality of feature frames from the preprocessed input speech data; c) normalizing the extracted feature frames of each speaker within the preprocessed input speech data with each speaker's mean and variance; d) concatenating the normalized feature frames to form overlapped longer frames having a frame length and a hop size; e) inputting the overlapped longer frames to the neural network based speaker classifier; and f) training the neural network through forward-backward propagation.