Abstract: Systems and methods are provided for smart audio segmentation using look-ahead based acousto-linguistic features. For example, systems and methods are provided for obtaining audio, processing the audio, identifying a potential segmentation boundary within the audio, and determining whether to generate a segment break at the potential segmentation boundary. One or more look-ahead words occurring after the potential segmentation boundary are identified, wherein an acoustic segmentation score and a language segmentation score associated with the potential segmentation boundary and the one or more look-ahead words are generated. Systems then either refrain from generating a segment break at the potential segmentation boundary or generate the segment break at the potential segmentation boundary based on the acoustic and/or language segmentation score at least meeting or exceeding a segmentation score threshold.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless inter-networking between a wireless wide area network (WWAN) and a local area network (WLAN) employing one or more extended range wireless inter-networking devices. Aspects of the present disclosure more specifically are directed toward a high powered wireless interconnect device that includes high efficiency circuitry to make it possible to implement in a portable or in-vehicle form factor, which may provide reasonable battery life, size, weight, and thermal dissipation. an extended range wireless inter-networking device, according to another embodiment of the disclosure. Aspects of the present disclosure further include a portable wireless access point configured for extended range communications, which may include a high power user equipment (“HPUE”) as disclosed herein.

Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Abstract: Systems and methods are provided for identifying targeted datasets that are configured to facilitate an improvement in the accuracy of an acoustic model included in the automatic speech recognition system. Systems obtain a obtain a test dataset comprising (i) audio data having natural speech utterances and (ii) a transcription of the natural speech utterances. Systems generate a text-to-speech dataset comprising audio data having synthesized speech utterances based on the transcription of the natural speech utterances. Systems apply the test dataset and the text-to-speech dataset to the acoustic model to obtain a first acoustic model output and a second acoustic model output, respectively. Systems identify a first set of errors in the first acoustic model output and a second set of errors in the second acoustic model output. Finally, based on comparing the first set of errors and the second set of errors, an acoustic model error ratio is generated.

Abstract: Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.

Abstract: A wireless wide area network (WWAN) radio includes a first WWAN transceiver/MODEM configured to communicate over one or more WWANs, and a standard power port communicably coupled to the first WWAN transceiver/MODEM. The standard power port is configured as the donor path for a coupled port including a standard power port antenna and configured to transmit at a first maximum power level. The WWAN radio further includes a high-power port communicably coupled to the standard power port and configured to have a fixed gain value high power amplifier and a high power antenna, the high power port configured to transmit at a second maximum power level being greater than the first maximum power level.

Abstract: Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless inter-networking between a wireless wide area network (WWAN) and a local area network (WLAN) employing one or more extended range wireless inter-networking devices. Aspects of the present disclosure more specifically are directed toward a high powered wireless interconnect device that includes high efficiency circuitry to make it possible to implement in a portable or in-vehicle form factor, which may provide reasonable battery life, size, weight, and thermal dissipation. An extended range wireless inter-networking device, according to another embodiment of the disclosure. Aspects of the present disclosure further include a portable wireless access point configured for extended range communications, which may include a high power user equipment (“HPUE”) as disclosed herein.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless inter-networking between a wireless wide area network (WWAN) and a local area network (WLAN) employing one or more extended range wireless inter-networking devices. Aspects of the present disclosure more specifically are directed toward a high powered wireless interconnect device that includes high efficiency circuitry to make it possible to implement in a portable or in-vehicle form factor, which may provide reasonable battery life, size, weight, and thermal dissipation. an extended range wireless inter-networking device, according to another embodiment of the disclosure. Aspects of the present disclosure further include a portable wireless access point configured for extended range communications, which may include a high power user equipment (“HPUE”) as disclosed herein.

Abstract: A data processing system is implemented for receiving speech data for a plurality of languages, and determining letters from the speech data. The data processing system also implements normalizing the speech data by applying linguistic based rules for Latin-based languages on the determined letters, building a computer model using the normalized speech data, fine-tuning the computer model using additional speech data, and recognizing words in a target language using the fine-tuned computer model.

Abstract: Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless communications, for example, within a wireless wide area network (WWAN), employing a wireless communication devices capable of operations in a plurality of enumerated categories of authorized use. Aspects of the present disclosure pertain to devices, systems and methods for dynamically provisioning a wireless communication device. Aspects of the present disclosure also pertain to systems and methods for devices, wireless operators, and/or private networks to implement different policies based on transmit power levels, device capabilities, locations, environmental and subscription services.

Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless inter-networking between a wireless wide area network (WWAN) and a local area network (WLAN) employing one or more extended range wireless inter-networking devices. Aspects of the present disclosure more specifically are directed toward a high powered wireless interconnect device that includes high efficiency circuitry to make it possible to implement in a portable or in-vehicle form factor, which may provide reasonable battery life, size, weight, and thermal dissipation. An extended range wireless inter-networking device, according to another embodiment of the disclosure. Aspects of the present disclosure further include a portable wireless access point configured for extended range communications, which may include a high power user equipment (“HPUE”) as disclosed herein.

Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless inter-networking between a wireless wide area network (WWAN) and a local area network (WLAN) employing one or more extended range wireless inter-networking devices. Aspects of the present disclosure more specifically are directed toward a high powered wireless interconnect device that includes high efficiency circuitry to make it possible to implement in a portable or in-vehicle form factor, which may provide reasonable battery life, size, weight, and thermal dissipation. an extended range wireless inter-networking device, according to another embodiment of the disclosure. Aspects of the present disclosure further include a portable wireless access point configured for extended range communications, which may include a high power user equipment (“HPUE”) as disclosed herein.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless inter-networking between a wireless wide area network (WWAN) and a local area network (WLAN) employing one or more extended range wireless inter-networking devices. Aspects of the present disclosure more specifically are directed toward a high powered wireless interconnect device that includes high efficiency circuitry to make it possible to implement in a portable or in-vehicle form factor, which may provide reasonable battery life, size, weight, and thermal dissipation. an extended range wireless inter-networking device, according to another embodiment of the disclosure. Aspects of the present disclosure further include a portable wireless access point configured for extended range communications, which may include a high power user equipment (“HPUE”) as disclosed herein.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless inter-networking between a wireless wide area network (WWAN) and a wireless local area network (WLAN) employing one or more extended range wireless inter-networking devices. Aspects of the present disclosure more specifically are directed toward a high powered wireless interconnect device that includes high efficiency circuitry to make it possible to implement in a portable or in-vehicle form factor, which may provide reasonable battery life, size, weight, and thermal dissipation.

Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Abstract: Aspects of the present disclosure generally pertains a system and method for wireless inter-networking between a wireless wide area network (WWAN) and a wireless local area network (WLAN) employing one or more extended range wireless inter-networking devices. Aspects of the present disclosure more specifically are directed toward a high powered wireless interconnect device that includes high efficiency circuitry to make it possible to implement in a portable or in-vehicle form factor, which may provide reasonable battery life, size, weight, and thermal dissipation.