Abstract: Embodiments included herein are directed towards a system and method for compressed domain language identification. Embodiments may include receiving a bitstream of a sequence of packets at one or more computing devices and classifying each packet into speech or non-speech based upon, at least in part, compressed domain voice activity detection (VAD). Embodiments may further include extracting a pseudo-cepstral representation from the speech detected packets and partially decoding without extracting a PCM format and generating a sequence of multi-frames, based upon, at least in part, the pseudo-cepstral representation. Embodiments may also include providing in real time the sequence of multi-frames to a deep neural network (DNN), wherein the DNN has been trained off-line for one or more desired target languages.

Abstract: The present disclosure is directed towards a method for discontinuous transmission (“DTX”) bandwidth reduction. The method may include receiving, at a processor, a frame identified as speech and determining that the frame was mistakenly identified as speech based upon, at least in part, a voice activity detection algorithm. The method may further include labeling the frame as a silence indicator frame.

Abstract: The present disclosure is directed towards a method for speech intelligibility. The method may include receiving, at one or more computing devices, a first speech input from a first user and performing voice activity detection upon the first speech input. The method may also include analyzing a spectral tilt associated with the first speech input, wherein analyzing includes computing an impulse response of a linear predictive coding (“LPC”) synthesis filter in a linear pulse code modulation (“PCM”) domain and wherein the one or more computing devices includes an adaptive high pass filter configured to recalculate one or more linear prediction coefficients.

Abstract: The present disclosure is directed towards a process for estimating the signal to noise ratio of a speech signal. The process may include receiving, at a computing device, a speech signal having a bitstream and a signal-to-noise ratio (“SNR”) associated therewith. The process may further include estimating the SNR directly from the bitstream or using a partial decoder that is configured to extract one or more parameters, the parameters including at least one of a fixed codebook gain, an adaptive codebook gain, a pitch lag, and a line spectral frequency (“LSF”) coefficient.

Abstract: Embodiments included herein are directed towards a system and method for compressed domain language identification. Embodiments may include receiving a bitstream of a sequence of packets at one or more computing devices and classifying each packet into speech or non-speech based upon, at least in part, compressed domain voice activity detection (VAD). Embodiments may further include extracting a pseudo-cepstral representation from the speech detected packets and partially decoding without extracting a PCM format and generating a sequence of multi-frames, based upon, at least in part, the pseudo-cepstral representation. Embodiments may also include providing in real time the sequence of multi-frames to a deep neural network (DNN), wherein the DNN has been trained off-line for one or more desired target languages.

Abstract: The present disclosure is directed towards a method for discontinuous transmission (“DTX”) bandwidth reduction. The method may include receiving, at a processor, a frame identified as speech and determining that the frame was mistakenly identified as speech based upon, at least in part, a voice activity detection algorithm. The method may further include labeling the frame as a silence indicator frame.

Abstract: The present disclosure is directed towards a process for estimating the signal to noise ratio of a speech signal. The process may include receiving, at a computing device, a speech signal having a bitstream and a signal-to-noise ratio (“SNR”) associated therewith. The process may further include estimating the SNR directly from the bitstream or using a partial decoder that is configured to extract one or more parameters, the parameters including at least one of a fixed codebook gain, an adaptive codebook gain, a pitch lag, and a line spectral frequency (“LSF”) coefficient.

Abstract: The present disclosure is directed towards a method for speech intelligibility. The method may include receiving, at one or more computing devices, a first speech input from a first user and performing voice activity detection upon the first speech input. The method may also include analyzing a spectral tilt associated with the first speech input, wherein analyzing includes computing an impulse response of a linear predictive coding (“LPC”) synthesis filter in a linear pulse code modulation (“PCM”) domain and wherein the one or more computing devices includes an adaptive high pass filter configured to recalculate one or more linear prediction coefficients.