Abstract: A communication system is described. The communication system including an automatic speech recognizer configured to receive a speech signal and to convert the speech signal into a text sequence. The communication also including a speech analyzer configured to receive the speech signal. The speech analyzer configured to extract paralinguistic characteristics from the speech signal. The communication system further includes a translator coupled with the automatic speech recognizer. The translator configured to convert the text sequence from a first language to a second language. In addition, the communication system includes a speech output device coupled with the automatic speech recognizer and the speech analyzer. The speech output device configured to convert the text sequence into an output speech signal based on the extracted paralinguistic characteristics.

Abstract: The present disclosure provides a robot and speech interaction recognition rate improvement circuit and method thereof. In the circuit, the main controller transmits a pre-recorded servo sound file to the first decoder in response to detecting the robot being in a motion state; the first decoder decodes the servo sound file to obtain a first sound analog signal of a servo sound; the analog-to-digital converter converts the first sound analog signal of the servo sound into a first sound digital signal, and converts a second sound analog signal collected by the microphone into a second sound digital signal; and the main controller further performs a suppression process on the servo sound in the second sound digital signal based on the first sound digital signal and the second sound digital signal. As a result, the influence of the sound of the servo of the robot is effectively reduced.

Abstract: One embodiment provides a method, including: receiving, at an information handling device, voice data from a user; generating a transcription record comprising the voice data; transmitting the voice data to at least one other device; receiving, from the at least one other device, another transcription record, generated by the at least one other device, associated with the transmitted voice data; identifying, by comparing the transcription record and the another transcription record, at least one difference between the transcription record and the another transcription record; and providing, responsive to identifying a difference, a notification. Other aspects are described and claimed.

Abstract: A codec allowing for switching between different coding modes is improved by, responsive to a switching instance, performing temporal smoothing and/or blending at a respective transition.

Abstract: Natural speech dialog system and methods are disclosed. In one example, a method includes identifying a dialog system intent associated with the speech input based on at least one predetermined intent keyword, the dialog system intent having required intent parameters, determining whether data for all required intent parameters of the dialog system are available, based on the determination, selectively initiating a parameter collection dialog associated with the dialog system intent, the parameter collection dialog being operable to collect data for the required parameters not otherwise available to the dialog system intent, and based on the dialog system intent and one or more required parameters, generating an action instruction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing a natural language based program interface to software applications. One of the methods includes, obtaining, via a natural language front end, a natural language query or a natural language update statement issued by a software application; converting the natural language query or natural language update statement into structured operations to be performed on APIs of a knowledge base; performing the structured operations on the APIs to produce a natural language output statement; and providing, via a natural language output interface, the natural language output statement to the software application. The knowledge base stores entity information according to a data schema and has structured APIs for use by software applications to query the knowledge base; the software applications are limited to communicating with the knowledge base through the interfaces provided by the natural language front end.

Abstract: A sound processing method includes: executing a time frequency conversion process; executing a noise level evaluation process; executing a bandwidth controlling process; executing a sound source direction decision process; executing a gain setting process; executing a correction process; and executing a frequency time conversion process.

Abstract: Provided are a speech recognition training processing method and an apparatus including the same. The speech recognition training processing method includes acquiring a multi-talker mixed speech signal from a plurality of speakers, performing permutation invariant training (PIT) model training on the multi-talker mixed speech signal based on knowledge from a single-talker speech recognition model and updating a multi-talker speech recognition model based on a result of the PIT model training.

Abstract: Provided are a speech recognition training processing method and an apparatus including the same. The speech recognition training processing method includes acquiring a stream of speech data from one or more speakers, extracting an auxiliary feature corresponding to a speech characteristic of the one or more speaker and updating an acoustic model by performing permutation invariant training (PIT) model training based on the auxiliary feature.

Abstract: Techniques for identifying a wake word by a device that is also playing audio content at the same time are described herein. For example, a device may execute playback of an audio file with a corresponding first variable wave form. The device may receive a second variable wave form that includes the first variable wave form and additional audio. In embodiments, a latency value may be identified based on comparing amplitudes and frequencies of portions of the first variable wave form and the second variable wave form. The second variable wave form may be modified by applying the latency value and inverting the second variable wave form with respect to the first variable wave form. The modified variable wave form may be merged with the first variable wave form to generate a merged variable wave form. A particular audio signal may be identified in the merged variable wave form.

Abstract: Disclosed are a method, a terminal, and an apparatus for extracting a headword and a computer-readable storage medium, wherein the method comprises: acquiring a text information input by a user; determining an out-edge weight of each search term of the text information; calculating a linkage-matrix for the each search term; calculating a priori score of the each search term according to a preset document library; determining a random jumping vector for the each search term according to the priori score; calculating a first preliminary score of the each search term according to the linkage-matrix and the random jumping vector; determining a second preliminary score of the each search term according to a preset part-of-speech configuration rule; determining a final degree score of the each search term according to the first preliminary score and the second preliminary score; extracting the headword of the text information according to the final degree score.

Abstract: Natural speech dialog system and methods are disclosed. In one example, a method includes identifying a dialog system intent associated with the speech input based on at least one predetermined intent keyword, the dialog system intent having required intent parameters, determining whether data for all required intent parameters of the dialog system are available, based on the determination, selectively initiating a parameter collection dialog associated with the dialog system intent, the parameter collection dialog being operable to collect data for the required parameters not otherwise available to the dialog system intent, and based on the dialog system intent and one or more required parameters, generating an action instruction.

Abstract: Methods, non-transitory computer readable media, and devices that convert into a common electronic format a plurality electronic medical records retrieved in response to a request with identification data. A natural language processing algorithm is applied to obtain a subset of summarization data from each of the converted medical electronic record based on medical information data in the received request. The algorithm screens the initial subset of summarization data based on one or more factors to generate a reduced subset of summarization data for each of the converted medical electronic records. At least a portion of the reduced subset of summarization data is populated into data fields within one of a plurality of templates identified for each of the converted electronic medical records from the reduced subset of summarization data. A clinical summarization record is generated based on at least the populated summarization data in each of the identified ones of the plurality of templates.

Abstract: The present disclosure provides a semantic understanding based emoji input method and device, and relates to the input method technology field. The method includes: obtaining a text content according to an input sequence; performing word segmentation on the text content, and extracting text features based on the word segmentation result; constructing an input vector using the text features, performing classification using an emotion classification model to determine an emotion label of the text content; based on a correspondence relationship between the emotion label and emojis of various themes, respectively obtaining an emoji corresponding to the emotion label from each of the various themes; sorting the obtained emojis of the various themes, and displaying the sorted emojis as candidate options in a client. The disclosed invention facilitates users to input an emoji, enhances emoji input efficiency, and provides users with rich and wide scope of emoji resources.

Abstract: The present invention proposes a new method for improving the performance of a real-valued filterbank based spectral envelope adjuster. By adaptively locking the gain values for adjacent channels dependent on the sign of the channels, as defined in the application, reduced aliasing is achieved. Furthermore, the grouping of the channels during gain-calculation, gives an improved energy estimate of the real valued subband signals in the filterbank.

Abstract: Various embodiments described herein facilitate multi-lingual communications. The systems and methods of some embodiments may enable multi-lingual communications through different modes of communications including, for example, Internet-based chat, e-mail, text-based mobile phone communications, postings to online forums, postings to online social media services, and the like. Certain embodiments may implement communications systems and methods that translate text between two or more languages (e.g., spoken), while handling/accommodating for one or more of the following in the text: specialized/domain-related jargon, abbreviations, acronyms, proper nouns, common nouns, diminutives, colloquial words or phrases, and profane words or phrases.

Abstract: An approach is provided to detect pronouns that are included in textual posts that are found in an online discussion. The textual posts are analyzed using a natural language processing speech classification technique, that results in an identification of a noun to which the detected pronoun refers. The system then displays, on a display device, the noun to which the pronoun refers.

Abstract: Techniques are provided for wake-on-voice (WOV) key-phrase enrollment. A methodology implementing the techniques according to an embodiment includes generating a WOV key-phrase model based on identification of the sequence of sub-phonetic units of a user-provided key-phrase. The WOV key-phrase model is employed by a WOV processor for detection of the user spoken key-phrase and triggering operation of an automatic speech recognition (ASR) processor in response to the detection. The method further includes updating an ASR language model based on the user-provided key-phrase. The update includes one of embedding the WOV key-phrase model into the ASR language model, converting sub-phonetic units of the WOV key-phrase model and embedding the converted WOV key-phrase model into the ASR language model, or generating an ASR key-phrase model by applying a phoneme-syllable based statistical language model to the user-provided key-phrase and embedding the generated ASR key-phrase model into the ASR language model.

Abstract: A speaker adaption method and a speaker adaption apparatus, a device and a storage medium are provided. The method includes: acquiring first speech data of a target speaker; inputting the first speech data to a pre-trained batch normalization (BN) network to be subjected to an adaptive training to acquire a speech recognition model including a speech parameter of the target speaker.

Abstract: This information processing method includes: acquiring a first speech signal including a first utterance; acquiring a second speech signal including a second utterance; recognizing whether the speaker of the second utterance is a first speaker by comparing a feature value for the second utterance and a first speaker model; when the first speaker is recognized, performing speech recognition in a first language on the second utterance, generating text in the first language corresponding to the second utterance subjected to speech recognition in the first language, and translating the text in the first language into a second language; and, in a case where the first speaker is not recognized, performing speech recognition in the second language on the second utterance, generating text in the second language corresponding to the second utterance subjected to speech recognition in the second language, and translating the text in the second language into the first language.