Patent ReferencesVoice-actuated switching system Active attenuation system with on-line modeling of speaker, error path and feedback pack Spectrally efficient TDM duplex communication system Audio processing system for teleconferencing with high and low transmission delays Variable rate vocoder Apparatus and method for adapting a digital radiotelephone system to increased subscriber traffic Analysis of audio quality using speech recognition and synthesis Transmitter-receiver having ear-piece type acoustic transducing part Hard handoff method using the dummy pilot Method and apparatus for performing speech frame encoding mode selection in a variable rate encoding system Patent #: 6484138 InventorsAssigneeApplicationNo. 10398263 filed on 10/11/2001US Classes:704/231, Recognition455/452.2, Based on service quality (e.g., bandwidth, etc.)455/67.13, Noise, distortion, or unwanted signal detection (e.g., quality control, etc.)455/135, By signal quality (e.g., signal to noise ratio)455/161.3, Using signal strength or quality381/110, VOICE CONTROLLED370/280, Time division379/202.01, Conferencing704/221, Pattern matching vocoders455/62, Optimum frequency selection381/151, Body contact wave transfer (e.g., bone conduction earphone, larynx microphone)455/437Mobile assisted or initiatedExaminersPrimary: Opsasnick, Michael N.Attorney, Agent or FirmForeign Patent References
International ClassG10L 15/00AbstractFor measuring the influence of noise on the talking quality of a telephone link in a telecommunications network, a talker speech signal (s(t)) and a degraded speech signal (s′(t)) are fed to an objective measurement device for obtaining an output signal (q) representing an estimated value of the talking quality. The degraded signal includes a returned signal (r(t)) originating from the network during transmission of the talker speech signal over the telephone link. The objective measurement provided by the device is a modified PSQM-like measurement, which is modified to include modelling of masking effects resulting from noise present in the returned signal. Preferably, the modelling includes noise suppression performed on a difference signal (D(t,f)) in a loudness density domain using noise estimation.Other References
Field of SearchBased on service quality (e.g., bandwidth, etc.)Noise, distortion, or unwanted signal detection (e.g., quality control, etc.) By signal quality (e.g., signal to noise ratio) Using signal strength or quality Signal quality (e.g., timing jitter, distortion, signal-to-noise ratio) Recognition Detect speech in noise | |