Patent US5787393A successfully refreshed from Google Patents.
US5787393A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Speech recognition apparatus using neural network, and learning method therefor
Assignee: Seiko Epson Corp
•
Filing: 1995-06-07
•
Granted: 1998-07-28
•
Expires: 2015-06-07
Abstract
Abstract A speech recognition apparatus using a neural network. A neuron-like element according to the present invention has a means for storing a value of the inner condition thereof, a means for updating a value of internal status on the basis of an output from the neuron-like element itself, outputs from other neuron-like elements and an external input, and an output value generating means for converting a value of internal status into an external output. Accordingly, the neuron-like element itself can retain the history of input data. This enables the time series data, such as speech to be processed without providing any special means in the neural network.
Inventors
- 👤 Mitsuhiro Inazumi
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-30 08:07
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/08; G10L15/16
Claims Analysis
Total Claims: 6
Claim 1
Independent Claim
200 words
A method for recognizing speech, comprising: extracting values of an input to be recognized; inputting the extracted values into a recurrent neural network; storing input learning data of a plurality of continuous data streams within a plurality of categories; selecting input learning data of a plurality of continuous data streams to be learned within a plurality of categories; storing positive output learning data of a plurality of continuous data streams within a plurality of categories corresponding to an input learning data category; storing negative output learning data of a plurality of continuous data streams within a plurality of categories corresponding to an input learning data category; selecting output learning data of a plurality of continuous data streams to be learned, each of which corresponds to an input learning data category; connecting the selected input learning data into a single continuous data stream; connecting the selected output learning data into a single continuous data stream in correlation with the connection of said input learning data; inputting said connected input learning data stream to the extraction step; and changing weightings at connections of neuron elements on the basis of outputs of said recurrent neural network and said connected output learning data streams.
Claim 2
Independent Claim
200 words
A method for recognizing speech, comprising: extracting values of an input to be recognized; inputting the extracted values into a recurrent neural network; storing input learning data of a plurality of continuous data streams within a plurality of categories; selecting input learning data of a plurality of continuous data streams to be learned within a plurality of categories; storing positive output learning data of a plurality of continuous data streams within a plurality of categories corresponding to an input learning data category; storing negative output learning data of a plurality of continuous data streams within a plurality of categories corresponding to an input learning data category; selecting output learning data of a plurality of continuous data streams to be learned, each of which corresponds to an input learning data category; connecting the selected input learning data into a single continuous data stream; connecting the selected output learning data into a single continuous data stream in correlation with the connection of said input learning data; inputting said connected input learning data stream to the extraction step; and changing weightings at connections of neuron elements on the basis of outputs of said recurrent neural network and said connected output learning data streams.
Claim 3
Dependent Claim
22 words
The method for recognizing speech as in claim 1, wherein the number of said input learning data categories is equal to two.
Claim 4
Dependent Claim
60 words
The method for recognizing speech as in claim 1, further comprising: storing noise data; overlaying said selected input learning data with noise data selected from the stored noise data, the selected input learning data overlaid with the noise data causing said recurrent neural network to learn so that said noise data contained in said input learning data can be differentiated.
Claim 5
Dependent Claim
28 words
The method for recognizing speech as in claim 3, further comprising shifting said noise data to different overlaying positions on said selected input learning data to repeat learning.
Claim 6
Dependent Claim
37 words
The method for recognizing speech as in claim 3, wherein selected input learning data not overlaid with the noise data and selected portions of the input learning data overlaid with the noise data are used for learning.
References Cited (Backward Citations)
EP0281160A1
Cited
US5175794A
Cited
EP0318858A2
Cited
JPH0272398A
Cited
US5040215A
Cited
JPH0281160A
Cited
US5093899A
Cited
US5185848A
Cited
US5297237A
Cited
US5119469A
Cited
US5150323A
Cited
JPH04295894A
Cited
JPH04295897A
Cited
EP0510632A2
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-07-27 | 2002-01-26 | 2002-07-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-07-27 | 2006-01-26 | 2006-07-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-07-27 | 2010-01-26 | 2010-07-28 | $7700.00 | Window Closed / Lapsed |