EP0047589A1
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method and apparatus for detecting speech in a voice channel signal
Assignee: Nortel Networks Ltd
•
Filing: 1981-08-13
•
Granted: —
•
Expires: 2001-08-13
Abstract
Abstract in a digital speech detector, a first detector (601) produces an output signal if any sample of a voice channel signal has a magnitude (T) exceeding a fixed threshold (TF) above noise levels. A second detector (602) produces a second threshold (TL) which is adaptively adjusted to noise levels on the channel by being set to a level above the current sample magnitude (T) each time that this does not exceed the preceding sample's magnitude (TP). When the sample magnitude (T) rises above the second threshold (TL), and for each subsequent sample of successively increasing magnitude, the second detector (602) produces an output signal. A speech decision for the voice channel is reached if either detector (601, 602) produces its output signal. The output signals of the first and second detectors (601, 602) are maintained for fixed and variable, respectively, hangover periods to maintain the speech decision during intersyllabic pauses in speech. The samples are supplied to the speech detector by an offset remover and averaging circuit.
Inventors
- 👤 Fouad Daaboul
- 👤 Tiu Le Van
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-02 20:22
CPC Classifications
G; G10; G10L; G10L25/00; G10L25/78
Claims Analysis
Total Claims: 13
Claim 1
Independent Claim
169 words
A method of detecting the presence of speech signals in a sampled voice channel signal, comprising producing a first signal whenever the magnitude (T) of a signal sample exceeds a first threshold level (TF), characterized by the steps of: comparing the magnitude (T) of each sample with that (TP) of the preceding sample; whenever the magnitude (T) of a sample is not greater than that (TP) of the preceding sample, setting a second threshold (TL) to a level which is greater than and is dependent upon the magnitude (T) of the current sample; whenever the magnitude (T) of a sample is greater than that (TP) of the preceding sample, producing a second signal if this second signal was produced in respect of the preceding sample or if the magnitude (T) of the current sample exceeds the second threshold level (TL); and in response to either the first signal or the second signal, producing a third signal, representing the presence of speech, at least in respect of the current sample.
Claim 2
Independent Claim
169 words
A method of detecting the presence of speech signals in a sampled voice channel signal, comprising producing a first signal whenever the magnitude (T) of a signal sample exceeds a first threshold level (TF), characterized by the steps of: comparing the magnitude (T) of each sample with that (TP) of the preceding sample; whenever the magnitude (T) of a sample is not greater than that (TP) of the preceding sample, setting a second threshold (TL) to a level which is greater than and is dependent upon the magnitude (T) of the current sample; whenever the magnitude (T) of a sample is greater than that (TP) of the preceding sample, producing a second signal if this second signal was produced in respect of the preceding sample or if the magnitude (T) of the current sample exceeds the second threshold level (TL); and in response to either the first signal or the second signal, producing a third signal, representing the presence of speech, at least in respect of the current sample.
Claim 3
Dependent Claim
79 words
A method as claimed in claim 1, characterized by the steps of:- in response to the first signal, producing a fourth signal in respect of a first predetermined number of consecutive samples commencing with the current sample; and in response to a second signal, producing a fifth signal in respect of a second,number of consecutive samples commencing with the current sample; wherein the third signal is produced in the presence of either the fourth signal or the fifth signal.
Claim 4
Dependent Claim
74 words
A method as claimed in claim 2, characterized by the step of determining said second number in dependence upon previous sample magnitudes, said second number being increased by a predetermined amount, up to a maximum number, for each sample in respect of which the second signal is produced, and being decreased by a predetermined amount at least for each sample whose magnitude (T) is not greater than the magnitude (TP) of the preceding sample.
Claim 5
Dependent Claim
123 words
A method as claimed in claim 2 or 3, characterized by the steps of:- whenever the magnitude (T) of a sample exceeds that (TP) of the preceding sample, and in respect of the preceding sample the fifth signal was produced but the second signal was not produced, producing the second signal in respect of the current sample if its magnitude (T) does not exceed the second threshold level (TL) but exceeds a third threshold level (TH); and setting the third threshold level (TH) equal to the magnitude (TP) of the preceding sample whenever the second signal was produced in respect of the preceding sample and the magnitude (T) of the current sample is not greater than the magnitude (TP) of the preceding sample.
Claim 6
Independent Claim
42 words
A method as claimed in any of claims 1 to 4 characterized in that each time that the second threshold level (TL) is set, it is set to be greater than the magnitude (T) of the current sample by a predetermined amount.
Claim 7
Independent Claim
60 words
A method as claimed in any of claims 1 to 5 characterized in that each signal sample is constituted by an average of a plurality of individual samples of the voice channel signal, the method comprising the step of producing each signal sample by removing d.c. offsets from and averaging a plurality of individual samples of the voice channel signal.
Claim 8
Dependent Claim
26 words
A speech detector characterized by comprising one or more read-only memories programmed and arranged to carry out the method of any of claims 1 to 6.
Claim 9
Dependent Claim
224 words
A speech detector for detecting the presence of speech signals in a sampled voice channel signal, comprising means (605) for producing a first signal whenever the magnitude (T) of a signal sample exceeds a first threshold level (TF), characterized in that the speech detector comprises:- means (611) for generating a second threshold (TL); means (609) for delaying each sample until the next sample; means (610) for comparing the magnitude (T) of each sample with that (TP) of the preceding sampled delayed by said delaying means (609); means (611), responsive to said comparing means (610) determining that the magnitude (T) of a sample is not greater than that (TP) of the preceding sample, for setting the second threshold (TL) to a level which is greater than and is dependent upon the magnitude (T) of the current sample; means (611), responsive to said comparing means (610) determining that the magnitude (T) of a sample is greater than that (TP) of the preceding sample, for producing a second signal if this second signal was produced in respect of the preceding sample or if the magnitude (T) of the current sample exceeds the second threshold level (TL); and means (603) responsive to either the first signal or the second signal for producing a third signal, representing the presence of speech, at least in respect of the current sample.
Claim 10
Dependent Claim
224 words
A speech detector for detecting the presence of speech signals in a sampled voice channel signal, comprising means (605) for producing a first signal whenever the magnitude (T) of a signal sample exceeds a first threshold level (TF), characterized in that the speech detector comprises:- means (611) for generating a second threshold (TL); means (609) for delaying each sample until the next sample; means (610) for comparing the magnitude (T) of each sample with that (TP) of the preceding sampled delayed by said delaying means (609); means (611), responsive to said comparing means (610) determining that the magnitude (T) of a sample is not greater than that (TP) of the preceding sample, for setting the second threshold (TL) to a level which is greater than and is dependent upon the magnitude (T) of the current sample; means (611), responsive to said comparing means (610) determining that the magnitude (T) of a sample is greater than that (TP) of the preceding sample, for producing a second signal if this second signal was produced in respect of the preceding sample or if the magnitude (T) of the current sample exceeds the second threshold level (TL); and means (603) responsive to either the first signal or the second signal for producing a third signal, representing the presence of speech, at least in respect of the current sample.
Claim 11
Dependent Claim
89 words
A speech detector as claimed in claim 8 characterized by:- means (606) responsive to the first signal to produce a fourth signal in respect of a first predetermined number of consecutive samples commencing with the current sample; and means (611) responsive to the second signal to produce a fifth signal in respect of a second number of consecutive samples commencing with the current sample; wherein the means (603) for producing the third signal is responsive to either the fourth signal or the fifth signal to produce the third signal.
Claim 12
Dependent Claim
88 words
A speech detector as claimed in claim 9 characterized by means (611) for determining said second number in dependence upon previous sample magnitudes, said determining means being responsive to the second signal being produced in respect of a sample to increase the second number, up to a maximum number, by a predetermined amount, and being responsive to the comparing means (610) determining that the magnitude (T) of a sample is not greater than that (TP) of the preceding sample to decrease the second number by a predetermined amount.
Claim 13
Dependent Claim
39 words
A speech detector as claimed in claim 8, 9 or 10 characterized by means (401 to 406) for producing each signal sample by removing d.c. offsets from and averaging a plurality of individual samples of the voice channel signal.
References Cited (Backward Citations)
US3712959A
Cited
US4052568A
Cited
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.