Abstract: Techniques are disclosed relating to selecting and/or ranking from among multiple recordings based on determining facial attributes associated with detected words. For example, each recording may be transcribed and analyzed to determine whether the recordings include words in one or more sets of words. Facial analysis may be performed during intervals in the recordings corresponding to recognized words. Counts of the recognized words may be weighted based on detected facial attributes. In various embodiments, disclosed techniques may facilitate accurate selection of relevant media from large data sets.

Abstract: A method includes converting a user's utterance to text; encapsulating the converted text in a rheme object; searching, for each of a plurality of topics, for keywords in the converted text; determining a relevancy metric for each of the plurality of topics based on such searching; selecting one or more topics based on determined relevancy metrics; comparing some or all of the converted text to names in one or more patient lists or databases; identifying a unique patient whose name is contained in the converted; attaching an indication of the identified patient to the rheme object; effecting an action based on the selected one or more topics and the attached patient indication; and saving the topic in a conversation history with a reference to the identified patient.

Abstract: A method includes determining a first filtered signal based on an audio signal; determining a second filtered signal based on the audio signal; determining, based on the first filtered signal and the second filtered signal, a portion of the audio signal corresponding to a sharp noise; determining, based on the first filtered signal and the second filtered signal, a gain signal that, for the portion of the audio signal corresponding to the sharp noise, has a value that is smaller than a value of the gain signal for the remaining portion of the audio signal; and suppressing, based on the gain signal, the sharp noise from an amplifier input signal determined based on the audio signal.

Abstract: Systems and methods are disclosed for predicting words using a structured stem and suffix n-gram language model. The systems and methods include determining, using a first n-gram word language model, a first probability of a stem based on a first portion of a previously-input word in the received input. Using a second n-gram language model, a second probability of a first suffix may be determined based at least on a second portion the previously-input word in the received input. Further, a third probability of a second suffix different from the first suffix may be determined using a third n-gram language model based at least on a third portion of the previously-input word in the received input. A fourth probability of a predicted word may be determined based on the first, second and third probabilities. One or more predicted words may be determined and provided as an output to the user.

Abstract: In this invention, the design of the Huffman table can be done offline with a large input sequence database. The range of the quantization indices (or differential indices) for Huffman coding is identified. For each value of range, all the input signal which have the same range will be gathered and the probability distribution of each value of the quantization indices (or differential indices) within the range is calculated. For each value of range, one Huffman table is designed according to the probability. And in order to improve the bits efficiency of the Huffman coding, apparatus and methods to reduce the range of the quantization indices (or differential indices) are also introduced.

Abstract: A voice processing apparatus calculates a phase difference between first and second frequency signals obtained by transforming first and second voice signals generated by two voice input units for each frequency, calculates, for each extension range set outside or inside a reference range, a presence ratio based on the number of frequencies with the phase difference between the first and second frequency signals falling within the extension range, the reference range representing a range of the phase difference between the first and second voice signals for each frequency and corresponding to a direction in which a target sound source is assumed to be located, and sets, as a non-suppression range, a first extension range having the presence ratio higher than a predetermined value and a second extension range closer to the phase difference at the center of the reference range than the first extension range is within the reference range.

Abstract: A method for mitigating potential frame instability by an electronic device is described. The method includes obtaining a frame subsequent in time to an erased frame. The method also includes determining whether the frame is potentially unstable. The method further includes applying a substitute weighting value to generate a stable frame parameter if the frame is potentially unstable.

Abstract: An voice command processing method provides a unified voice control interface to access and control Internet of things (IoT) devices and configure value of attributes of graphical user interface (GUI) elements, attributes of applications, and attributes of the IoT devices. As a voice command comprises an expression of a percentage or a fraction of a baseline value of an attribute, or an exact value of the attribute of an IoT device, the unified voice control interface sets the attribute of the IoT device in response to the percentage, the fraction, or the exact value in the voice command.

Abstract: A method, apparatus, and tangible computer readable medium for processing a Hidden Markov Model (HMM) structure are disclosed herein. For example, the method includes receiving Hidden Markov Model (HMM) information from an external system. The method also includes processing back pointer data and first HMM states scores for one or more NULL states in the HMM information. Second HMM state scores are processed for one or more non-NULL states in the HMM information based on at least one predecessor state. Further, the method includes transferring the second HMM state scores to the external system.

Abstract: A method for improving decomposition of digital signals using training sequences is presented. A method for improving decomposition of digital signals using initialization is also provided. A method for sorting digital signals using frames based upon energy content in the frame is further presented. A method for utilizing user input for combining parts of a decomposed signal is also presented.

Abstract: A computer-implemented method for presenting statistical analysis in a natural language textual output comprising: receiving data to be analyzed by the processor; processing the data according to at least one of a plurality of pre-established statistical analysis types, thereby providing processed data; interpreting the processed data by analyzing the processed data to provide a pre-determined natural language text, thereby providing interpreted data; and generating a natural language textual output for the interpreted data according to at least one pre-established rule for converting the interpreted data to a natural language textual output.

Abstract: A speech-enabled management system is described herein. One system includes a grammar building tool configured to create a set of grammar keys based on ontology analytics corresponding to data received from a digital video manager (DVM) server, a speech recognition engine configured to recognize a speech command from a set of grammar files, a command translator configured to translate the recognized speech command to an executable command, and a processor configured to execute the speech command based on a particular grammar key from the set of grammar keys.

Abstract: A method of identifying a contact in a communication system using voice input, the method comprising: receiving an input string of characters, the input string representing a contact and being normally unpronounceable by a human voice when spoken literally; performing at least one transforming step to transform at least one character of the input string to thereby generate a pronounceable name for the contact; and outputting the pronounceable name for use in establishing a communication event with the contact using voice input.

Abstract: Various exemplary embodiments relate to a command interpreter for use in a vehicle control system in a vehicle for interpreting user commands, a vehicle interaction system including such a command interpreter, a vehicle including such a vehicle interaction system, and related method and non-transitory machine-readable storage medium, including: a memory and a processor, the processor being configured to: receive, from at least one human via a first input device, a first input having a first type; receive a second input having a second type via a second input device, wherein the second type comprises at least one of sensed information describing a surrounding environment of the vehicle and input received from at least one human; interpret both the first input and the second input to generate a system instruction; and transmit the system instruction to a different system of the vehicle.

Abstract: A method and system are disclosed for recognizing speech errors, such as in a spoken short messages, using an audio input device to receive an utterance of a short message, using an automated speech recognition module to generate a text sentence corresponding to the utterance, generating an N-best list of predicted error sequences for the text sentence using a linear-chain conditional random field (CRF) module, where each word of the text sentence is assigned a label in each of the predicted error sequences, and each label is assigned a probability score. The predicted error sequence labels are rescored using a metacost matrix module, the best rescored error sequence from the N-best list of predicted error sequences is selected using a Recognition Output Voting Error Reduction (ROVER) module, and a dialog action is executed by a dialog action module based on the best rescored error sequence and the dialog action policy.

Abstract: Provided is a speech/audio encoding apparatus with which it is possible to code a significant frequency domain region with high precision, and to enable high audio quality. A speech/audio encoding apparatus codes a linear prediction coefficient. A significant frequency domain region detection unit identifies a frequency domain region which is aurally significant from the linear prediction coefficient. A frequency domain region repositioning unit repositions the significant frequency domain region which is identified by the significant frequency domain region detection unit. A bit allocation computation unit determines a coding bit allocation on the basis of the significant frequency domain region which is repositioned by the frequency domain region repositioning unit.

Abstract: A personalized news service provides personalized news programs for its users by generating personalized combinations of audible versions of news stories derived from text-based based versions of the news stories. The audible versions may be generated from the text-based version by a text-to-speech system, or may by recording a person reading aloud the text-based version. To acquire recordings, the personalized news service can make a determination that a particular news story has a threshold extent of popularity. The news service can then transmit a request to a remote recording station for a recording of a verbal reading of the particular news story. The news service can then receive the requested recording from the remote recording station.

Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with training adaptive speech recognition systems (“ASR”) using audio and text obtained from captioned video. In various embodiments, the audio and caption may be aligned for identification, such as according to a start and end time associated with a caption, and the alignment may be adjusted to better fit audio to a given caption. In various embodiments, the aligned audio and caption may then be used for training if an error value associated with the audio and caption demonstrates that the audio and caption will aid in training the ASR. In various embodiments, filters may be used on audio and text prior to training. Such filters may be used to exclude potential training audio and text based on filter criteria. Other embodiments may be described and claimed.

Abstract: A semiconductor integrated circuit device for voice recognition includes: a signal processing unit which generates a feature pattern representing a state of distribution of frequency components of an input voice signal; a voice recognition database storage unit which stores a voice recognition database including a standard pattern representing a state of distribution of frequency components of plural phonemes; a conversion list storage unit which stores a conversion list including plural words or sentences to be conversion candidates; a standard pattern extraction unit which extracts a standard pattern corresponding to character data representing the first syllable of each word or sentence included in the conversion list, from the voice recognition database; and a matching detection unit which compares the feature pattern generated from the first syllable of the voice signal with the extracted standard pattern and thus detects the matching of the syllable.

Abstract: In an automatic speech recognition (ASR) processing system, ASR processing may be configured to process speech based on multiple channels of audio received from a beamformer. The ASR processing system may include a microphone array and the beamformer to output multiple channels of audio such that each channel isolates audio in a particular direction. The multichannel audio signals may include spoken utterances/speech from one or more speakers as well as undesired audio, such as noise from a household appliance. The ASR device may simultaneously perform speech recognition on the multi-channel audio to provide more accurate speech recognition results.