US5867813A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for automatically and reproducibly rating the transmission quality of a speech transmission system
Assignee: Ascom Schweiz AG
•
Filing: 1995-05-01
•
Granted: 1999-02-02
•
Expires: 2015-05-01
Abstract
Abstract A recorded voice test signal is transmitted from a transmitting end of a mobile communication system, and in a test unit at the receiving end a frame generator is synchronized with the received signal. Each frame of the signal is evaluated in computing circuits on the outputs of the frame generator, which calculate characteristic values of each frame which are then subtracted from calculated characteristic reference values of the frames stored in a memory. The differences between these characteristic values are fed to a neural network which classifies the quality of the difference signals as Good, Medium and Bad, and a defuzzyfication logic circuit further refines the quality classification output, whereby the transmission quality throughout the mobile communication system can be reprodicbly rated for a system quality rating.
Inventors
- 👤 Gianni Di Pietro
- 👤 Ziemowit Zglinski
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-07 15:04
CPC Classifications
G; G10; G10L; G10L25/00; G10L25/48; G10L25/69; H; H04; H04B; H04B17/00; H04B17/0082; H04B17/0085; H04B17/30; H04B17/309
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
138 words
A method for automatically and reproducibly rating the transmission quality of a speech transmission system, comprising the steps of: a) Generating a test signal containing a predetermined recorded voice signal; b) transmitting the test signal by the speech transmission system from a transmitting end to a receiving end; c) extracting characteristic values from the received test signal; d) determining a differential pattern corresponding to the difference between the characteristic values and predetermined reference values; and e) feeding the differential pattern to a neural network that has been trained for classifying patterns according to a number of predetermined transmission quality classes, wherein the test signal comprises a synchronization signal consisting of at least one chirp signal, and further wherein the chirp signal is generated with different frequency slopes depending on the transmission direction in the bidirectional speech transmission system.
Claim 2
Independent Claim
138 words
A method for automatically and reproducibly rating the transmission quality of a speech transmission system, comprising the steps of: a) Generating a test signal containing a predetermined recorded voice signal; b) transmitting the test signal by the speech transmission system from a transmitting end to a receiving end; c) extracting characteristic values from the received test signal; d) determining a differential pattern corresponding to the difference between the characteristic values and predetermined reference values; and e) feeding the differential pattern to a neural network that has been trained for classifying patterns according to a number of predetermined transmission quality classes, wherein the test signal comprises a synchronization signal consisting of at least one chirp signal, and further wherein the chirp signal is generated with different frequency slopes depending on the transmission direction in the bidirectional speech transmission system.
Claim 3
Dependent Claim
23 words
Method according to claim 1, wherein the test signal contains several identical voice signals, having a duration of 2 to 15 seconds each.
Claim 4
Dependent Claim
24 words
Method according to claim 1, further comprising the step of refining the classification output of the neural network by means of a defuzzyfication logic.
Claim 5
Dependent Claim
14 words
Method according to claim 1, wherein the chirp is within the acoustic frequency range.
Claim 6
Dependent Claim
30 words
Method according to claim 1, comprising the step of preprocessing the test signal before extracting the characteristic values by decomposing the test signal into a predetermined number of time frames.
Claim 7
Dependent Claim
45 words
Method according to claim 5, wherein the preprocessing comprises the steps of: a) Generating digital samples; b) preemphasizing the digital samples by elevating the higher frequences; c) generating overlapping frames of the digital samples; and d) extracting a set of characteristic values of each frame.
Claim 8
Dependent Claim
18 words
Method according to claim 5, wherein the characteristic values are extracted by spectral analysis of the time frames.
Claim 9
Dependent Claim
40 words
Method according to claim 7, wherein the spectral analysis comprises the steps of: a) Determining the DFT coefficients for each frame; b) emphasizing the DFT coefficients; c) grouping the DFT coefficients into several frequency bands according to the Bark scale.
Claim 10
Dependent Claim
32 words
Method according to claim 7, wherein the spectral analysis comprises the steps of: a) Determining the autocorrelation function of each frame; b) calculating the prediction coefficients; and c) determining the cepstrum coefficients.
Claim 11
Dependent Claim
27 words
Method according to claim 1, further comprising the step of feeding the differential pattern to a data reduction circuit before having it classified by the neural network.
References Cited (Backward Citations)
GB1455712A
Cited
EP0114463B1
Cited
DE3513361A1
Cited
DE3708002A1
Cited
US4860360A
Cited
US5040215A
Cited
US5220640A
Cited
WO1994000922A1
Cited
EP0722164A1
Cited
US5715372A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2002-02-01 | 2002-08-03 | 2003-02-02 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2006-02-01 | 2006-08-03 | 2007-02-02 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2010-02-01 | 2010-08-03 | 2011-02-02 | $7700.00 | Window Closed / Lapsed |