Abstract: A computing device may receive or otherwise access a base audio layer and one or more enhancement audio layers. The computing device can reconstruct the retrieved base layer and/or enhancement layers into a single data stream or audio file. The local computing device may process audio frames in a highest enhancement layer retrieved in which the data can be validated (or a lower layer if the data in audio frames in the enhancement layer(s) cannot be validated) and build a stream or audio file based on the audio frames in that layer.

Abstract: A method for generating a high-band target signal includes receiving, at an encoder, an input signal having a low-band portion and a high-band portion. The method also includes comparing a first autocorrelation value of the input signal to a second autocorrelation value of the input signal. The method further includes scaling the input signal by a scaling factor to generate a scaled input signal. The scaling factor is determined based on a result of the comparison. The method also includes generating a low-band signal based on the input signal and generating the high-band target signal based on the scaled input signal.

Abstract: A condition determining section (24) determines whether or not two consecutive lines in an image meet a joining condition that is based on a characteristic of a language of a character string, the two consecutive lines being extracted from the character string composed of a plurality of lines. In a case where the joining condition is met, an extracted line joining section (25) and a translation section (26) join and then translate the two consecutive lines.

Abstract: An echo cancellation system that generates multiple output paths, enabling Automatic Speech Recognition (ASR) processing in parallel with voice communication. For single direction AEC (e.g., ASR processing), the system prioritizes speech from a single user and ignores other speech by selecting a single directional output from a plurality of directional outputs as a first output path. For multi-directional AEC (e.g., voice communication), the system includes all speech by combining the plurality of directional outputs as a second output path. The system may use a weighted sum technique, such that each directional output is represented in the combined output based on a corresponding signal metric, or an equal weighting technique, such that a first group of directional outputs having a higher signal metric may be equally weighted using a first weight while a second group of directional outputs having a lower signal metric may be equally weighted using a second weight.

Abstract: Technical solutions are described for generating structured conversational data. An example method includes receiving an utterance that is part of a conversation and identifying the utterance as part of an adjacency pair. The adjacency pair includes two utterances, each produced by different speakers. The method also includes associating the utterance with a label from a predetermined set of labels based on the identifying of the adjacency pair.

Abstract: Textual data is organized into statement clusters. Sentences are extracted from textual data and parsed. A verb usage pattern is identified and an SVO triplet is determined. The SVO triplet is compared to a taxonomy associated with the domain of the data and a sentiment is derived. A statement cluster is constructed comprising a higher level SVO triplet sensitive to the taxonomy and verb usage pattern, as well as the derived sentiment. Accordingly, the statement clusters may be organized by grouping.

Abstract: A singing voice synthesis data editing method includes adding, to singing voice synthesis data, a piece of virtual note data placed immediately before a piece of note data having no contiguous preceding piece of note data, the singing voice synthesis data including: multiple pieces of note data for specifying a duration and a pitch at which each note that is in a time series, representative of a melody to be sung, is voiced; multiple pieces of lyric data associated with at least one of the multiple pieces of note data; and a sequence of sound control data that directs sound control over a singing voice synthesized from the multiple pieces of lyric data, and obtaining the sound control data that directs sound control over the singing voice synthesized from the multiple pieces of lyric data, and that is associated with the piece of virtual note data.

Abstract: A method at a first electronic device of multiple electronic devices, each electronic device of the plurality of electronic devices including one or more microphones and a speaker, includes detecting a voice input; determining a quality score for the detected voice input; communicating the quality score to the other devices of the plurality of electronic devices; receiving quality scores generated by the other devices for detection of the voice input by the other devices; if the quality score generated by the first electronic device is the highest amongst the quality scores, outputting an audible and/or visual response to the detected voice input, where the other devices of the plurality of electronic devices forgo outputting an audible response to the detected voice input; and if the quality score generated by the first electronic device is not the highest amongst the quality scores, forgoing outputting a response to the detected voice input.

Abstract: In some implementations, a language proficiency of a user of a client device is determined by one or more computers. The one or more computers then determines a text segment for output by a text-to-speech module based on the determined language proficiency of the user. After determining the text segment for output, the one or more computers generates audio data including a synthesized utterance of the text segment. The audio data including the synthesized utterance of the text segment is then provided to the client device for output.

Abstract: An apparatus and method for verifying an utterance based on multi-event detection information in a natural language speech recognition system. The apparatus includes a noise processor configured to process noise of an input speech signal, a feature extractor configured to extract features of speech data obtained through the noise processing, an event detector configured to detect events of the plurality of speech features occurring in the speech data using the noise-processed data and data of the extracted features, a decoder configured to perform speech recognition using a plurality of preset speech recognition models for the extracted feature data, and an utterance verifier configured to calculate confidence measurement values in units of words and sentences using information on the plurality of events detected by the event detector and a preset utterance verification model and perform utterance verification according to the calculated confidence measurement values.

Abstract: Embodiments are directed towards providing a smart sign that dynamically translates content that is displayed on the sign based on a preferred language of mobile devices that are in close proximity to the sign. The smart sign determines when one or more mobile devices are in proximity to the smart sign. The smart sign communicates with each of these mobile devices to determine a preferred language of a respective user of each mobile device. The smart sign translates and displays the content in each of the preferred languages on the sign. In various embodiments, the smart sign can relocate or resize the translated content so that it can fit on a display screen of the smart sign relative to a location of the mobile devices relative to the smart sign.

Abstract: In order to solve a conventional problem that an accurate translation cannot be realized, a learning apparatus includes: a parser unit parsing a target language sentence, thereby acquiring a binary tree of the target language sentence; a source language element acquiring unit acquiring one or more source language elements; a source language partial structure acquiring unit acquiring one or more source language partial structures each containing a parent node having a phrase label and two child nodes each having a phrase label or a source language element; a labeling unit providing a reordering label to the one or more source language partial structures; a model building unit that builds one or more parsing models each having appearance probability information regarding a labeled source language partial structure; and an accumulating unit accumulating a binary tree of a source language sentence having the one or more parsing models.

Abstract: Received data representing speech is stored, and a trigger detection block detects a presence of data representing a trigger phrase in the received data. In response, a first part of the stored data representing at least a part of the trigger phrase is supplied to an adaptive speech enhancement block, which is trained on the first part of the stored data to derive adapted parameters for the speech enhancement block. A second part of the stored data, overlapping with the first part of the stored data, is supplied to the adaptive speech enhancement block operating with said adapted parameters, to form enhanced stored data. A second trigger phrase detection block detects the presence of data representing the trigger phrase in the enhanced stored data. In response, enhanced speech data are output from the speech enhancement block for further processing, such as speech recognition.

Abstract: The present disclosure relates to an audio signal coding method and apparatus. The method includes categorizing audio signals into high-frequency audio signals and low-frequency audio signals, coding the low-frequency audio signals using a corresponding low-frequency coding manner according to characteristics of low-frequency audio signals, and selecting a bandwidth extension mode to code the high-frequency audio signals according to the low-frequency coding manner and/or characteristics of the audio signals.

Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.

Abstract: In general, techniques are described for indicating reusability of an index that determines a Huffman codebook used to code data associated with a vector in a spherical harmonics domain. The bitstream may comprise an indicator for whether to reuse, from a previous frame, at least one syntax element indicative of the index. The memory may be configured to store the bitstream.

Abstract: An audio recording apparatus comprises: a recording process for recording audio; a receiving process for receiving an indicated go-back time; and a processor that executes an information appending process that appends information associated with a time going back by the go-back time from a base time, linked to audio in the recording, in accordance with a user's instructions.

Abstract: In general, techniques are described for indicating reuse of a syntax element that indicates a quantization mode used when compressing a vector. A device comprising a processor and a memory may perform the techniques. The processor may be configured to obtain a bitstream comprising a vector in a spherical harmonics domain. The bitstream may further comprise an indicator for whether to reuse, from a previous frame, at least one syntax element indicative of a quantization mode used when compressing the vector. The memory may be configured to store the bitstream.

Abstract: A method for recommending the pronunciation of a name includes providing a plurality of audio records wherein the audio records include a set of audio records identifying the pronunciation of a common name. The method also includes analyzing the set of audio records identifying the pronunciation to determine the most frequent common pronunciation of the common name in the set of audio records. Once determined, the most frequent common pronunciation of the common name is presented to an end user.

Abstract: In general, techniques are described for indicating reuse of a syntax element indicating a vector quantization codebook used in compressing a vector. A device comprising a processor and a memory may perform the techniques. The processor may be configured to obtain a bitstream comprising a vector in a spherical harmonics domain. The bitstream may further comprise an indicator for whether to reuse, from a previous frame, a syntax element indicative of a vector quantization codebook used when compressing the vector. The memory may be configured to store the bitstream.