[go: up one dir, main page]

GB2209418B - Apparatus amd methods for analysing transitions in finite state machines - Google Patents

Apparatus amd methods for analysing transitions in finite state machines

Info

Publication number
GB2209418B
GB2209418B GB8824486A GB8824486A GB2209418B GB 2209418 B GB2209418 B GB 2209418B GB 8824486 A GB8824486 A GB 8824486A GB 8824486 A GB8824486 A GB 8824486A GB 2209418 B GB2209418 B GB 2209418B
Authority
GB
United Kingdom
Prior art keywords
state
transitions
machine
finite state
words
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
GB8824486A
Other versions
GB8824486D0 (en
GB2209418A (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.)
NAT RES DEV
National Research Development Corp UK
Original Assignee
NAT RES DEV
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 NAT RES DEV, National Research Development Corp UK filed Critical NAT RES DEV
Priority to GB8824486A priority Critical patent/GB2209418B/en
Publication of GB8824486D0 publication Critical patent/GB8824486D0/en
Publication of GB2209418A publication Critical patent/GB2209418A/en
Application granted granted Critical
Publication of GB2209418B publication Critical patent/GB2209418B/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)
  • Machine Translation (AREA)
  • Complex Calculations (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 is minimum cumulative distance; that is the smallest value on reaching one of the states from a starting position, considering all possible paths. Since words are spoken one after another, a finite state machine representing one word has transitions to another machine representing another word. The network of such transitions is complex and varies between different pairs of words. In the present invention, rather than use such a network, each finite state machine is given a start state (SD) at the beginning and an end state (ED) at the end. A Viterbi engine finds the minimum cumulative distance for each normal state of each machine and also determines the minimum cumulative distance for each end state. Traceback pointers for each end state are determined which indicate the number of transitions traversed in reaching that end state. A further distance dependent on the traceback pointer for each end state is added to that state to form a word ending score. The best score is then used to update start states selected on a grammatical basis, other start states being updated with a maximum value. <IMAGE>
GB8824486A 1985-11-12 1988-10-19 Apparatus amd methods for analysing transitions in finite state machines Expired GB2209418B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
GB8824486A GB2209418B (en) 1985-11-12 1988-10-19 Apparatus amd 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
GB8824486A GB2209418B (en) 1985-11-12 1988-10-19 Apparatus amd methods for analysing transitions in finite state machines

Publications (3)

Publication Number Publication Date
GB8824486D0 GB8824486D0 (en) 1988-11-23
GB2209418A GB2209418A (en) 1989-05-10
GB2209418B true GB2209418B (en) 1989-10-11

Family

ID=26290001

Family Applications (1)

Application Number Title Priority Date Filing Date
GB8824486A Expired GB2209418B (en) 1985-11-12 1988-10-19 Apparatus amd methods for analysing transitions in finite state machines

Country Status (1)

Country Link
GB (1) GB2209418B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6073098A (en) 1997-11-21 2000-06-06 At&T Corporation Method and apparatus for generating deterministic approximate weighted finite-state automata
JP2000242293A (en) * 1999-02-23 2000-09-08 Motorola Inc Method for voice recognition device
WO2001084534A2 (en) * 2000-05-04 2001-11-08 Motorola Inc. Method of traceback matrix storage in a speech recognition system
US20030065505A1 (en) 2001-08-17 2003-04-03 At&T Corp. Systems and methods for abstracting portions of information that is represented with finite-state devices
US7257575B1 (en) 2002-10-24 2007-08-14 At&T Corp. Systems and methods for generating markup-language based expressions from multi-modal and unimodal inputs

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
GB8824486D0 (en) 1988-11-23
GB2209418A (en) 1989-05-10

Similar Documents

Publication Publication Date Title
US5268990A (en) Method for recognizing speech using linguistically-motivated hidden Markov models
KR100883577B1 (en) Low Memory Decision Tree
EP1215662A1 (en) Speech recognition device and speech recognition method, and recording medium
DE3687815D1 (en) METHOD AND DEVICE FOR VOICE ANALYSIS.
DE3481388D1 (en) TEXT TO LANGUAGE TRANSLATION SYSTEM.
US9858038B2 (en) Correction menu enrichment with alternate choices and generation of choice lists in multi-pass recognition systems
CN106782537A (en) The method and system of weather is inquired about in robot
GB2209418B (en) Apparatus amd methods for analysing transitions in finite state machines
EP1225567A3 (en) Method and apparatus for speech recognition
EP0285222A3 (en) Method for detecting associatively pronounced words
Chow et al. Speech understanding using a unification grammar
JP2003515777A (en) Speech recognition using a complementary language model for typical errors in conversation
Dickens The history of so-called strengthening in Tswana
EP1320086A1 (en) Method for generating and/or adapting language models
Lowerre The Harpy speech recognition system[Ph. D. Thesis]
Mousa et al. Sub-lexical language models for German LVCSR
Jouvet et al. Speaker-independent spelling recognition over the telephone
Hain A hybrid approach for grapheme-to-phoneme conversion based on a combination of partial string matching and a neural network.
Levinson et al. A new system for continuous speech recognition-Preliminary results
Tappert Experiments with a tree-search method for converting noisy phonetic representation into standard orthography
Ouh-Young et al. A Chinese text-to-speech system based upon a syllable concatenation model
Chen et al. A Study on Using Word-Level HMMs to Improve ASR Performance over State-of-the-Art Phone-Level Acoustic Modeling for LVCSR.
Hori et al. Improved phoneme-history-dependent search method for large-vocabulary continuous-speech recognition
JPH0713587A (en) Hidden markov connection learning method
JP2615643B2 (en) Word speech recognition device

Legal Events

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