Abstract: Examples of the disclosure describe user environment aware single channel acoustic noise reduction. A noisy signal received by a computing device is transformed and feature vectors of the received noisy signal are determined. The computing device accesses classification data corresponding to a plurality of user environments. The classification data for each user environment has associated therewith a noise model. A comparison is performed between the determined feature vectors and the accessed classification data to identify a current user environment. A noise level, a speech level, and a speech presence probability from the transformed noisy signal are estimated and the noise signal is reduced based on the estimates. The resulting signal is outputted as an enhanced signal with a reduced or eliminated noise signal.

Abstract: Examples of the disclosure describe user environment aware single channel acoustic noise reduction. A noisy signal received by a computing device is transformed and feature vectors of the received noisy signal are determined. The computing device accesses classification data corresponding to a plurality of user environments. The classification data for each user environment has associated therewith a noise model. A comparison is performed between the determined feature vectors and the accessed classification data to identify a current user environment. A noise level, a speech level, and a speech presence probability from the transformed noisy signal are estimated and the noise signal is reduced based on the estimates. The resulting signal is outputted as an enhanced signal with a reduced or eliminated noise signal.

Abstract: There is provided a method of quantifying a voice quality in a telecommunication system including a first gateway in communication with a second gateway over a packet network. The method comprises deriving speech parameters from a first speech signal of a first talker received by the first gateway over a first communication line and a second speech signal of a second talker received by the first gateway from the second gateway over the packet network, determining a conversational impairment index using the speech parameters, deriving technology parameters based on voice technology and components in the telecommunication system, determining a technology impairment index using the technology parameters, and mapping the conversational impairment index and the technology impairment index into a conversational quality index to quantify the voice quality in the telecommunication system.