Nuance Communications, Inc.

Jose Lainez

Sridhar Pilli

Daniel Almendro Barreda

Dushyant Sharma

Patrick A Naylor

Mahesh Godavarti

Qian-Yu Tang

Jagadeesh Balam

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.

System and method for compressed domain language identification

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.

System and method to reduce transmission bandwidth via improved discontinuous transmission

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.

System and method for speech enhancement on compressed speech

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.

Growing community of inventors

London, United Kingdom

Jose Lainez