Abstract: In some cases, a handheld device that includes a microphone and a scanner may be used for voice-assisted scanning. For example, a user may provide a voice input via the microphone and may activate the scanner to scan an item identifier (e.g., a barcode). The handheld device may communicate voice data and item identifier information to a remote system for voice-assisted scanning. The remote system may perform automatic speech recognition (ASR) operations on the voice data and may perform item identification operations based on the scanned identifier. Natural language understanding (NLU) processing may be improved by combining ASR information with item information obtained based on the scanned identifier. An action may be executed based on the likely user intent.

Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.

Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.

Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.

Abstract: Devices, systems and methods are disclosed for estimating a prior probability for speech recognition by taking into account a number of observations of a particular word and a prior probability for a group of words having a similar number of observations. For example, a prior probability may be determined by combining a number of correct results and a number of observations for a group of words and calculating a prior probability of the entire group. Further, a prior probability may be determined for a word that was not previously observed by determining a prior probability for a group of words that have been observed once. The prior probability for a particular word may be determined differently as the number of observations increases and may transition from the group prior probability to an individual prior probability when the number of observations exceeds a threshold.

Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.

Abstract: According to one or more embodiments of the disclosure, a method is provided. The method may include executing playback of a video. The method may also include receiving user input to rewind at least one portion of the video. Further, the method may include restarting playback of the video at a previous position before the at least one portion of the video. The method may also include activating subtitles associated with the video during playback of the video from the previous position, wherein the subtitles are displayed during playback of the at least one portion of the video. Additionally, the method may include deactivating subtitles during playback of the video after a predetermined amount of time.

Abstract: In some cases, a handheld device that includes a microphone and a scanner may be used for voice-assisted scanning. For example, a user may provide a voice input via the microphone and may activate the scanner to scan an item identifier (e.g., a barcode). The handheld device may communicate voice data and item identifier information to a remote system for voice-assisted scanning. The remote system may perform automatic speech recognition (ASR) operations on the voice data and may perform item identification operations based on the scanned identifier. Natural language understanding (NLU) processing may be improved by combining ASR information with item information obtained based on the scanned identifier. An action may be executed based on the likely user intent.

Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.

Abstract: A speech-based audio device may be configured to detect a user-uttered trigger expression and to respond by interpreting subsequent words or phrases as commands. In order to distinguish between utterance of the trigger expression by the user and generation of the trigger expression by the device itself, output signals used as speaker inputs are analyzed to detect whether the trigger expression has been generated by the speaker. If a detected trigger expression has been generated by the speaker, it is disqualified. Disqualified trigger expressions are not acted upon the by the audio device.

Abstract: An audio buffer is used to capture audio in anticipation of a user command to do so. Sensors and processor activity may be monitored, looking for indicia suggesting that the user command may be forthcoming. Upon detecting such indicia, a circular buffer is activated. Audio correction may be applied to the audio stored in the circular buffer. After receiving the user command instructing the device to process or record audio, at least a portion of the audio that was stored in the buffer before the command is combined with audio received after the command. The combined audio may then be processed, transmitted or stored.

Abstract: A computing device can utilize one or more sensors to capture data associated with a current environment, state, condition, property, etc. of the device. Based at least in part on the captured data, the current environment, state, condition, property, etc. of the computing device can be determined or identified. Based on the determined/identified current environment, state, condition, property, etc., the computing device can configure the notification intensity level for the device. The device can determine a suitable notification intensity level and set that notification intensity level for the device. An incoming communication received at the computing device while the device is still associated with the determined/identified current environment, state, condition, property, etc. can cause a notification to be outputted at the set notification intensity level.

Abstract: A system and method for using speech recognition, natural language understanding, image processing, and facial recognition to automatically analyze the audio and video data of video content and generate enhanced data relating to the video content and characterize the aspects or events of the video content. The results of the analysis and characterization of the aspects of the video content may be used to annotate and enhance the video content to enhance a user's viewing experience by allowing the user to interact with the video content and presenting the user with information related to the video content.

Abstract: Features are disclosed for applying maximum likelihood methods to channel normalization in automatic speech recognition (“ASR”). Feature vectors computed from an audio input of a user utterance can be compared to a Gaussian mixture model. The Gaussian that corresponds to each feature vector can be determined, and statistics (e.g., constrained maximum likelihood linear regression statistics) can then be accumulated for each feature vector. Using these statistics, or some subset thereof, offsets and/or a diagonal transform matrix can be computed for each feature vector. The offsets and/or diagonal transform matrix can be applied to the corresponding feature vector to generate a feature vector normalized based on maximum likelihood methods. The ASR process can then proceed using the transformed feature vectors.

Abstract: Features are disclosed for maintaining data that can be used to personalize spoken language processing, such as automatic speech recognition (“ASR”), natural language understanding (“NLU”), natural language processing (“NLP”), etc. The data may be obtained from various data sources, such as applications or services used by the user. User-specific data maintained by the data sources can be retrieved and stored for use in generating personal models. Updates to data at the data sources may be reflected by separate data sets in the personalization data, such that other processes can obtain the update data sets separate from other data.

Abstract: Features are disclosed for updating or generating natural language processing models based on information associated with items expected to be referenced in natural language processing input, such as audio of user utterances, user-entered text, etc. Natural language processing models may include, e.g., language models, acoustic models, named entity recognition models, intent classification models, and the like. The models may be updated or generated based on selected features of input data and a machine learning model trained to produce probabilities based on the selected features.

Abstract: A speech recognition system that also automatically recognizes and acts in response to significant audio interruptions. Received audio is compared with stored acoustic signatures of noises which may trigger a change in device operation, such as pausing, loudening or attenuating of content playback after hearing a certain audio interruption, such as a doorbell, etc. If the received audio matches a stored acoustic model, the system alters an operational state of one or more devices, which may or may not include itself.

Abstract: Natural language controlled devices may be configured to activate command recognition in response to one or more wake words. Techniques are provided to receive a candidate word for evaluation as a wake word that activates a natural language control functionality of a computing device. The candidate word may include one or more words or sounds. Values for multiple wake word metrics are then determined. The candidate word is evaluated based on the various wake word metrics.

Abstract: Features are disclosed for selecting and using multiple transforms associated with a particular remote device for use in automatic speech recognition (“ASR”). Each transform may be based on statistics that have been generated from processing utterances that share some characteristic (e.g., acoustic characteristics, time frame within which the utterances where processed, etc.). When an utterance is received from the remote device, a particular transform or set of transforms may be selected for use in speech processing based on data obtained from the remote device, speech processing of a portion of the utterance, speech processing of prior utterances, etc. The transform or transforms used in processing the utterances may then be updated based on the results of the speech processing.

Abstract: Neural networks may be used in certain automatic speech recognition systems. To improve performance of these neural networks, they may be updated/retrained during run time by training the neural network based on the output of a speech recognition system or based on the output of the neural networks themselves. The outputs may include weighted outputs, lattices, weighted N-best lists, or the like. The neural networks may be acoustic model neural networks or language model neural networks. The neural networks may be retrained after each pass through the network, after each utterance, or in varying time scales.