Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating domain-specific speech recognition models for a domain of interest by combining and tuning existing speech recognition models when a speech recognizer does not have access to a speech recognition model for that domain of interest and when available domain-specific data is below a minimum desired threshold to create a new domain-specific speech recognition model. A system configured to practice the method identifies a speech recognition domain and combines a set of speech recognition models, each speech recognition model of the set of speech recognition models being from a respective speech recognition domain. The system receives an amount of data specific to the speech recognition domain, wherein the amount of data is less than a minimum threshold to create a new domain-specific model, and tunes the combined speech recognition model for the speech recognition domain based on the data.

Abstract: Some embodiments described herein relate to a multimodal user interface for use in an automobile. The multimodal user interface may display information on a windshield of the automobile, such as by projecting information on the windshield, and may accept input from a user via multiple modalities, which may include a speech interface as well as other interfaces. The other interfaces may include interfaces allowing a user to provide geometric input by indicating an angle. In some embodiments, a user may define a task to be performed using multiple different input modalities. For example, the user may provide via the speech interface speech input describing a task that the user is requesting be performed, and may provide via one or more other interfaces geometric parameters regarding the task. The multimodal user interface may determine the task and the geometric parameters from the inputs.

Abstract: In an automatic speech recognition (ASR) dictation application, a user interface may be provided for informing a user how to dictate desired text. Input may be received from the user of the dictation application, specifying a desired text sequence. In response to the received input, output may automatically be provided to the user via the user interface, indicating one or more speech sequences that, when spoken by a user and recognized by the dictation application using ASR, would cause the dictation application to output the desired text sequence as a recognition result.

Abstract: Techniques for performing multi-style speech synthesis. The techniques include using at least one computer hardware processor to perform: obtaining input comprising text and an identification of a desired speaking style to use in rendering the text as speech; identifying a plurality of speech segments for use in rendering the text as speech, the identifying comprising identifying a first speech segment recorded and/or synthesized in a first speaking style that is different from the desired speaking style based at least in part on a measure of similarity between the desired speaking style and the first speaking style; synthesizing speech from the text in the desired speaking style at least in part by using the first speech segment; and outputting the synthesized speech.

Abstract: Disclosed herein are methods, systems, and computer-readable storage media for automatic speech recognition. The method includes selecting a speaker independent model, and selecting a quantity of speaker dependent models, the quantity of speaker dependent models being based on available computing resources, the selected models including the speaker independent model and the quantity of speaker dependent models. The method also includes recognizing an utterance using each of the selected models in parallel, and selecting a dominant speech model from the selected models based on recognition accuracy using the group of selected models. The system includes a processor and modules configured to control the processor to perform the method. The computer-readable storage medium includes instructions for causing a computing device to perform the steps of the method.

Abstract: In accordance with aspects of the disclosure, a computing device may provide a user interface for developing an interactive natural-language response system, which may include a virtual assistant. A user may interact with a system using spoken, written (e.g., text), or other input methods. The user interface may allow a user to associate sentences with intents, tag words within the sentences with concepts, and construct a grammar using the associated intents and tagged concepts. The system may use the grammar for automatically predictively associating sentences with intents and words with concepts. The system may display in the foam of a chat transcript a single branch of a tree of a discussion between the virtual assistant and a user. The user interface may graphically display variable values to assist a user to test system responses under different simulated conditions.

Abstract: An assignment device (1) assigns word class information (WKI) to one or more words of text information (ETI). Based on word-class sequence information (WK-AI) formed from this assigned word class information (WKI), actions (A) are executed in order to notify the user of conflicts or to provide the user with background information (HI) relating to words in the text information (TT).

Abstract: Disclosed herein are systems, methods, and computer-readable media to connecting to addresses received in spoken communications. The method for connecting to addresses received in spoken communications comprises receiving at least one spoken communication containing a spoken address, extracting each address automatically from the at least one spoken communication, displaying to a user at least one extracted address, and receiving from the user a selection of at least one extracted address to initiate communication.

Abstract: Methods and apparatus for a communication system having microphones and loudspeakers to determine a noise and speech level estimate for a transformed signal, determine a SNR from the noise and speech level estimates, and determine a gain for the transformed signal to achieve a selected SNR range at a given position. In one embodiment, the gain is determined by adapting an actual gain to follow a target gain, wherein the target gain is adjusted to achieve the selected SNR range.

Abstract: The method comprises receive first audio comprising speech from a user of a computing device, detecting an end of speech in the first audio, generating an ASR result based, at least in part, on a portion of the first audio prior to the detected end of speech, determining whether a valid action can be performed by a speech-enabled application installed on the computing device using the ASR result, and processing second audio when it is determined that a valid action cannot be performed by the speech-enabled application using the ASR result.

Abstract: Methods and systems are provided for improving speech recognition of multilingual named entities. In some embodiments, a list comprising a plurality of named entities may be accessed by a computing device. A first named entity represented in the native language may be compared with the first named entity represented in the foreign language. One or more words that appear in both the first named entity represented in the native language and the first named entity represented in the foreign language may be identified as one or more foreign words. A grapheme-to-phoneme (G2P) conversion may be applied to the one or more foreign words, wherein graphemes of the one or more foreign words are mapped to phonemes in the native language. The G2P conversion may result in a native pronunciation for each of the one or more foreign words, which are added to a recognition dictionary along with the native pronunciations.

Abstract: Devices and systems supporting more than one Virtual Assistant (VA) are able to initiate and collaborate with multiple virtual assistants within the same session and at the same time. This system allows application specific virtual assistants to register and listen for intents from a general purpose virtual assistant. When the general purpose virtual assistant raises an intent, control can be passed to an interested application specific virtual assistant for handling. The system of registering new intents increases the knowledge of the general purpose virtual assistant, or overloads the handling of an existing intent.

Abstract: Systems and methods are described herein for performing actions based on a determined intent within messages received by a mobile device. In some embodiments, the systems and methods may access a message received by a mobile application (e.g., text messaging application, chat application, and so on) of the mobile device, analyze the message to determine an intent of the message (e.g., whether the message includes a request or a task for a recipient of the message), and perform an action based on the determined intent (e.g., set a reminder when the message includes a task for the recipient). Further details are described herein.

Abstract: A system and method for speech recognition is provided. Embodiments may include receiving an audio signal at a first deep neural network (“DNN”) associated with a computing device. Embodiments may further include receiving the audio signal at a second deep neural network (“DNN”) associated with a computing device, wherein the second deep neural network includes fewer parameters than the first deep neural network. Embodiments may also include determining whether to select an output from the first deep neural network or the second deep neural network and providing the selected output to a decoder with an overall objective of speeding up ASR.

Abstract: Methods and apparatus for performing speech recognition using a garbage model. The method comprises receiving audio comprising speech and processing at least some of the speech using a garbage model to produce a garbage speech recognition result. The garbage model includes a plurality of sub-words, each of which corresponds to a possible combination of phonemes in a particular language.

Abstract: A system and an associated method for responding to a user's voice inquiry are disclosed. The system accepts the voice inquiry and obtains personal data regarding the user. The system then identifies potential subjects of interest in the voice inquiry from media content currently provided to the user through a device which has captured the voice inquiry, media content present in or capturing the user's surroundings, or media content previously provided to the user as responses to previous voice inquiries by the user. Next, the system determines at least one subject of interest based on at least one of the personal data and the user's previous voice inquiries. The system then presents a response related to the determined subject of interest to the user's voice inquiry.

Abstract: Techniques for use in medical coding include applying a natural language understanding engine to a free-form text documenting at least one clinical patient encounter to generate a set of one or more medical billing codes for the patient encounter. A user interface may be provided, configured to allow one or more human users to review and correct the generated set of medical billing codes. Within the user interface, in response to user selection of a first medical billing code of the generated set of medical billing codes, at least a portion of a government-authorized codebook for the first medical billing code may be displayed, and a position of the first medical billing code may be indicated in the displayed portion of the codebook.

Abstract: Techniques are provided whereby a clarification request may be generated with a clinical documentation improvement (CDI) system for resolution by a clinician, and notification of the clarification request may be transmitted to a medical coding system. At a medical coding system, notification may be received of a clarification request generated at a CDI system for resolution by a clinician. In some embodiments, the medical coding system may be a computer-assisted coding (CAC) system.

Abstract: A computer program product, for automatically editing a medical record transcription, resides on a computer-readable medium and includes computer-readable instructions for causing a computer to obtain a first medical transcription of a dictation, the dictation being from medical personnel and concerning a patient, analyze the first medical transcription for presence of a first trigger phrase associated with a first standard text block, determine that the first trigger phrase is present in the first medical transcription if an actual phrase in the first medical transcription corresponds with the first trigger phrase, and insert the first standard text block into the first medical transcription.

Abstract: Presenting natural-language-understanding (NLU) results can include redundancies and awkward sentence structures. In an embodiment of the present invention, a method includes, responsive to receiving a result to a NLU query, loading a matching template of a plurality of templates stored in a memory. Each template has mask fields associated with at least one property. The method compares the properties of the mask fields of each of the templates to properties of the query and properties of the result, and selects the matching template. The method further completes the matching template by inserting fields of the result into corresponding mask fields of the matching template. The method may further suppress certain mask fields of the matching template to increase brevity and improve the naturalness of the response when appropriate based on the results of the NLU query. The method further presents the completed matching template to a user via a display.