GB2257282A - Speech recognizer, processor and responder - Google Patents

Speech recognizer, processor and responder Download PDF

Info

Publication number
GB2257282A
GB2257282A GB9110335A GB9110335A GB2257282A GB 2257282 A GB2257282 A GB 2257282A GB 9110335 A GB9110335 A GB 9110335A GB 9110335 A GB9110335 A GB 9110335A GB 2257282 A GB2257282 A GB 2257282A
Authority
GB
United Kingdom
Prior art keywords
machine
natural language
instructions
languages
recognize
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
GB9110335A
Other versions
GB9110335D0 (en
Inventor
H A Fatmi
H Sherief
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
H Sherief
Original Assignee
H Sherief
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by H Sherief filed Critical H Sherief
Priority to GB9110335A priority Critical patent/GB2257282A/en
Publication of GB9110335D0 publication Critical patent/GB9110335D0/en
Publication of GB2257282A publication Critical patent/GB2257282A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/285—Memory allocation or algorithm optimisation to reduce hardware requirements

Abstract

A speech recognizer, processor, and responder based on orthogonal logic, memory and filters. The orthogonality factor greatly simplifies the input data structure by making it vector data and correspondingly enables the invention of orthogonal gates, memories, shift registers, decoders and filters.

Description

SPEECH RECOGNIZER, PROCESSOR AND RESPONDER This invention relates to speech recognizer, processor and responder.
Speech recognizers, processors and responders are modern machines which are capable of responding to human speech in many languages of the world. They consist of elements : decoders, registers, controllers, arithmetic units, logic units, clocks, transducers, memories, quantizers, adaptive filters, coders, channels, input-output facilities, etc..
The current machines on the market have limited facilities. They are highly expensive, remain mostly idle do not respond to shades of meaning of speech, and therefore cannot be adapted to English, Europian, and other languages.
According to the present invention there is provided a chasis, 86 specially designed units, means for mounting the units on the chasis, the chasis connected with each other, and input-output facilities.
Referring to Figures 1 and 2, a speech recognizer 60 recognizes speech input 55 and 56 , which is processed in the speech processor 63 with its data input 51 and 52, control output 49 and 50, memory 61 and adress outputs 53 and 54 and adress decoder 59. A speech responder 62 with outputs 57 and 58. The speech processor consists of special accumulator 9, 10 and 11, special registers 12, 13 and 14; 27, 28 and 29; 30, 31 and 32; 33, 34 and 35; 36, 37 and 38; special arithmetic and logic units 15, 16 and 17; special controllers 18, 19 and 20; special buffers 40, 39 and 41; 43, 42 and 44 with external input-output 5,6,7,and 8; control output 3 and 4; and internal input-output 1,2, 45,46,47 and 48.
Referring to Figure 3, a transducer 64 is used to convert human speech to electrical signals, a controller 65 controls the performance of the recognizer through special memories 66 and 67, another transducer 68, special quantizers 69 and 70, special adaptive filters 71 and 72, special coders 73, 74, 75 and 76, special decoders 77, 78, 79 and 80, inverse adaptive filters 81 and 82, input facility 83, output facility 84, clock 85, and channel 86.
In order to respond to speech, varies levels of meaning of words must be identified. The speech recognizer, processor and responder according to the invention identifies the varies meanings of words and responds to them accordinly. In order to recognize human speech in any language, the synthesizer according to the invention characterises human speech in various different classes such as vowel, semi-vowel, dipthong, nasal, fricative, affricate, plosive, aspirate, etc. The machine also analyses the input speech as regards time, frequency, and other parameters.

Claims (11)

Claims
1. The machine recognizes English, French, German, Spanish and other Europian Languages as well as other languages of the world.
2 The machine can compute by instruction, recognize and understand showing expert knowledge, producing an output in the aforesaid and other natural languages.
3. The machine will be able to recognize life preservation signals, communicating it to the relevent life preservation authorities, recognizing their instructions and relaying them to the person whose life is in danger in natural language.
4. The machine will be able to take orders from their costumers in natural language for various consumer products and envoice their accounts update their statements of account in natural language.
5. The machine will be able to forcast in natural language the activities of shiping, marketing and banking, weather details, stock exchange prices etc in natural language.
6. The machine will be able to recognize instructions of accountants, carrying out book keeping and various activities and report to them on the financial activities of their costumers in natural language.
7. The machine will be able to carry out the reconstruction of visual patterns stored in its memory by the recognition of instructions by natural language.
8. The machine will be able to produce necessary aids to carry out various industrial processes etc in natural language.
9. The machine will advance high quality natural language communication all over the world.
10. The machine will be indispensable in defence where commanders on the battle field, in the air, or in the navy men issue instructions to their troops with maximum efficiency and utmost urgency in natural language.
11. The machine will raise the quality of office automation by introducing natural language recognition by phonetic type writters and other devices.
GB9110335A 1991-05-13 1991-05-13 Speech recognizer, processor and responder Withdrawn GB2257282A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
GB9110335A GB2257282A (en) 1991-05-13 1991-05-13 Speech recognizer, processor and responder

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
GB9110335A GB2257282A (en) 1991-05-13 1991-05-13 Speech recognizer, processor and responder

Publications (2)

Publication Number Publication Date
GB9110335D0 GB9110335D0 (en) 1991-07-03
GB2257282A true GB2257282A (en) 1993-01-06

Family

ID=10694914

Family Applications (1)

Application Number Title Priority Date Filing Date
GB9110335A Withdrawn GB2257282A (en) 1991-05-13 1991-05-13 Speech recognizer, processor and responder

Country Status (1)

Country Link
GB (1) GB2257282A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2126393A (en) * 1982-08-20 1984-03-21 Asulab Sa Speech-controlled apparatus
GB2145551A (en) * 1983-08-23 1985-03-27 David Thurston Griggs Speech-controlled phonetic typewriter or display device
EP0184032A1 (en) * 1984-11-30 1986-06-11 International Business Machines Corporation Speech recognition system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2126393A (en) * 1982-08-20 1984-03-21 Asulab Sa Speech-controlled apparatus
GB2145551A (en) * 1983-08-23 1985-03-27 David Thurston Griggs Speech-controlled phonetic typewriter or display device
EP0184032A1 (en) * 1984-11-30 1986-06-11 International Business Machines Corporation Speech recognition system

Also Published As

Publication number Publication date
GB9110335D0 (en) 1991-07-03

Similar Documents

Publication Publication Date Title
ATE203119T1 (en) LANGUAGE RECOGNITION SYSTEM FOR COMPOUND WORD LANGUAGES
DE3275779D1 (en) Recognition of speech or speech-like sounds
Howson Upper sorbian
Ghannay et al. Where are we in semantic concept extraction for Spoken Language Understanding?
GB2257282A (en) Speech recognizer, processor and responder
Morgan et al. Stochastic perceptual auditory-event-based models for speech recognition.
JPS57111658A (en) Schedule controller
Wang et al. An experimental analysis on integrating multi-stream spectro-temporal, cepstral and pitch information for mandarin speech recognition
Lyberg Some consequences of a model for segment duration based on F0-dependence
O'Shaughnessy Design of a real-time French text-to-speech system
DE3279549D1 (en) Apparatus and method for articulatory speech recognition
Olabe et al. Real time text-to-speech conversion system for spanish
Chung et al. The interaction of polar question and declarative intonation with lexical tone in Moro
Fushikida et al. A text to speech synthesizer for the personal computer
Fujimura Comment: Beyond the segment
Zdaranok Linguistic and Acoustic Resources of the Computer-Based System for Analysis and Interpretation of Speech Intonation
Dixon et al. Strategic compromise and modeling in automatic recognition of continuous speech: A hierarchical approach
Koushtuev et al. Voice announcement for vehicle operators
Fox The IPA alphabet: remarks on some proposals for reform
KR20000051760A (en) method for selecting unit of similar morpheme in continue voice cognition system
Martin Study of Sounds: Articles Contributed in Commemoration of the 30th Anniversary of the Founding of the Phonetic Society of Japan
Harris et al. Effect of Learning on Perception: Discrimination of Relative Onset Time of the Formants in Certain Speech and Non‐Speech Patterns
Ditang Parallel neural networks for speaker-independent all-Chinese-syllable speech recognition
Ifukube et al. Speech Recognition Systems for the Hearing Impaired and the Elderly
Carterette et al. Repetition and Confirmation of Messages Received by Ear and by Eye

Legal Events

Date Code Title Description
WAP Application withdrawn, taken to be withdrawn or refused ** after publication under section 16(1)