GB2209419B - Apparatus and methods for analysing transitions in finite state machines - Google Patents

Apparatus and methods for analysing transitions in finite state machines

Info

Publication number
GB2209419B
GB2209419B GB8824487A GB8824487A GB2209419B GB 2209419 B GB2209419 B GB 2209419B GB 8824487 A GB8824487 A GB 8824487A GB 8824487 A GB8824487 A GB 8824487A GB 2209419 B GB2209419 B GB 2209419B
Authority
GB
United Kingdom
Prior art keywords
state
transitions
cumulative distance
speech recognition
minimum
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.)
Expired
Application number
GB8824487A
Other versions
GB8824487D0 (en
GB2209419A (en
Inventor
Alexander Howard Lloyd
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.)
National Research Development Corp UK
Original Assignee
National Research Development Corp UK
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
Priority claimed from GB858527913A external-priority patent/GB8527913D0/en
Application filed by National Research Development Corp UK filed Critical National Research Development Corp UK
Priority to GB8824487A priority Critical patent/GB2209419B/en
Publication of GB8824487D0 publication Critical patent/GB8824487D0/en
Publication of GB2209419A publication Critical patent/GB2209419A/en
Application granted granted Critical
Publication of GB2209419B publication Critical patent/GB2209419B/en
Expired legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Testing Of Balance (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

In speech recognition words to be recognised may be represented by finite state machines and recognition is based on analysing transitions through the machines as an utterance occurs. One value which is required for each state of each machine in a timescale which is compatible with continuous speech recognition is minimum cumulative distance; that is the smallest value on reaching one of the states from a starting position, considering all possible paths. In the present invention a specially constructed Viterbi engine is provided for calculating cumulative distances at high speed. Latch circuits 50, 51, 52 holding pointers allow a RAM 41 to be read to provide, for a current machine state, both stored cumulative distances of states with transitions. A logic circuit comprising latch circuits 60 and 65 and an ALU 61 finds the cumulative distance for each path as far as the current state, selects the minimum using a latch circuit 56 and adds another penalty dependent on the current state. Thus a minimum cumulative distance is provided for storage and for a speech recognition decision making circuit. The process is repeatedly carried out for each state of each machine under the control of a controller 45. The total number of iterations of the engine in reaching each mimimum cumulative distance is also held in the RAM 41 and updated by the logic circuit. <IMAGE>
GB8824487A 1985-11-12 1988-10-19 Apparatus and methods for analysing transitions in finite state machines Expired GB2209419B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
GB8824487A GB2209419B (en) 1985-11-12 1988-10-19 Apparatus and methods for analysing transitions in finite state machines

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GB858527913A GB8527913D0 (en) 1985-11-12 1985-11-12 Analysing transitions in finite state machines
GB8824487A GB2209419B (en) 1985-11-12 1988-10-19 Apparatus and methods for analysing transitions in finite state machines

Publications (3)

Publication Number Publication Date
GB8824487D0 GB8824487D0 (en) 1988-11-23
GB2209419A GB2209419A (en) 1989-05-10
GB2209419B true GB2209419B (en) 1989-10-11

Family

ID=26290002

Family Applications (1)

Application Number Title Priority Date Filing Date
GB8824487A Expired GB2209419B (en) 1985-11-12 1988-10-19 Apparatus and methods for analysing transitions in finite state machines

Country Status (1)

Country Link
GB (1) GB2209419B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2179483A (en) * 1985-08-20 1987-03-04 Nat Res Dev Speech recognition

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2179483A (en) * 1985-08-20 1987-03-04 Nat Res Dev Speech recognition

Also Published As

Publication number Publication date
GB8824487D0 (en) 1988-11-23
GB2209419A (en) 1989-05-10

Similar Documents

Publication Publication Date Title
GB2183072B (en) Apparatus and methods for analysing transitions in finite state machines
Ikehara et al. Toward an MT System without Pre-Editing---Effects of New Methods in ALT-J/E---
Kneser et al. On the dynamic adaptation of stochastic language models
Ferrer i Cancho et al. Two regimes in the frequency of words and the origins of complex Lexicons: Zipf’s law revisited∗
Schmid Improvements in part-of-speech tagging with an application to German
Hill et al. Stronger forms of Zipf's law
DK0419432T3 (en) Method for generating quality factors for binary digits generated by the Viterbian analysis of a signal
GB2209419B (en) Apparatus and methods for analysing transitions in finite state machines
CN109684643A (en) Text recognition method, electronic equipment and computer-readable medium based on sentence vector
Ristad et al. New techniques for context modeling
GB8824486D0 (en) Apparatus &amp; methods for analysing transitions in finite state machines
Padró et al. A named entity recognition system based on a finite automata acquisition algorithm
Einieh et al. Fine tuning an arat5 transformer for arabic abstractive summarization
Sanfilippo Word knowledge acquisition, lexicon construction and dictionary compilation
SE8100735L (en) DIGITAL PROCESSOR DEVICE
JPS5478042A (en) Language information processing unit
Hogenhout et al. A fast method for statistical grammar induction
JPS57153343A (en) Compile method for architecture program
KR900004213Y1 (en) Equipment for treat of undercut for inclined hole of injection mould
Carpineto Shift of Bias without Operators.
Farkaš et al. A self-organizing neural network model of the acquisition of word meaning
JPS5788375A (en) Electronic clock
JP3353769B2 (en) Character recognition device, character recognition method, and character recognition program recording medium
Ramsay Underdetermined Feature Sets
JPS57100354A (en) Quality deciding method for electronic parts

Legal Events

Date Code Title Description
PCNP Patent ceased through non-payment of renewal fee