Data processing: speech signal processing – linguistics – language – Speech signal processing
Reexamination Certificate
1999-09-30
2002-06-25
Dorvil, Richemond (Department: 2741)
Data processing: speech signal processing, linguistics, language
Speech signal processing
C704S201000, C704S230000, C704S243000, C704S236000
Reexamination Certificate
active
06411925
ABSTRACT:
The present invention relates to a speech processing apparatus and method. The invention has particular, although not exclusive relevance to the checking of training examples to ensure that they are consistent.
Speech recognition and speech verification systems both require stored models which are representative of the speech or the speaker to be recognised. These models are generated by the user inputting one or more training utterances. In order to reduce recognition or verification errors, the training utterances should be consistent.
One aim of the present invention is to provide a system for checking that training examples are consistent, in order to reduce mismatches during use.
According to one aspect, the present invention provides a consistency checking apparatus, for checking the consistency between a first sequence of frames representative of a first signal and a second sequence of frames representative of a second signal using a matching score and the results of a matching process performed on
One aim of the present invention is to provide an alternative technique for performing such a noise masking operation on the input speech signals.
According to one aspect, the present invention provides a speech processing apparatus comprising means for receiving a sequence of time frames representative of a speech signal; means for determining the distribution of energy with frequency within each of said time frames; and means for processing each frame energy distribution by: (i) determining the maximum energy level within the current frame; (ii) determining a maximum level for the current frame by subtracting a predetermined energy level from the maximum energy level; and (iii) making any energy components which are less than said masking level equal to said masking level.
REFERENCES:
patent: 4087630 (1978-05-01), Browning et al.
patent: 4805193 (1989-02-01), McLaughlin et al.
patent: 4827516 (1989-05-01), Tsukahara et al.
patent: 4918732 (1990-04-01), Gerson et al.
patent: 5621854 (1997-04-01), Hollier
patent: 5832424 (1998-11-01), Tsutsui
patent: 5960395 (1999-09-01), Tzirkel-Hancock
patent: 0 789 349 (1997-08-01), None
McEachern, Robert (“How the Ear Really Works,” IEEE-SP International Symposium, Time-Frequency and Time-Scale Analysis, Oct. 1992).
Dorvil Richemond
Nolan Daniel A.
LandOfFree
Speech processing apparatus and method for noise masking does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Speech processing apparatus and method for noise masking, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech processing apparatus and method for noise masking will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2976579