Scribd Logo
Upload

Welcome to Scribd!

  • FST Explained

    Uploaded by

    Nuttagrit Chakane
    7 views7 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    7 views7 pages

    FST Explained

    Uploaded by

    Nuttagrit Chakane

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    of 7

    FSM(Finite State Machine)

    A finite-state machine, or FSM for short, is a model of computation


    based on a hypothetical machine made of one or more states. Only a
    single state can be active at the same time, so the machine must
    transition from one state to another in order to perform different
    actions.
    FST(Finite State Transducer)

    A finite state transducer (FST) is a finite state automaton (FSA, FA) which produces output as well as
    reading input, which means it is useful for parsing (while a "bare" FSA can only be used for recognizing,
    i.e. pattern matching).

    An FST consists of a finite number of states which are linked by transitions labeled with an input/output
    pair. The FST starts out in a designated start state and jumps to different states depending on the input,
    while producing output according to its transition table.

    FSTs are useful in NLP and speech recognition because they have nice algebraic properties, most notably
    that they can be freely combined (form an algebra) under composition, which implements relational
    composition on regular relations (think of this as non-deterministic function composition) while staying
    very compact. FSTs can do parsing of regular languages into strings in linear time.

    As an example, I once implemented morphological parsing as a bunch of FSTs. My main FST for verbs
    would turn a regular verb, say "walked", into "walk+PAST". I also had an FST for the verb "to be", which
    would turn "is" into "be+PRESENT+3rd" (3rd person), and similarly for other irregular verbs. All the FSTs
    were combined into a single one using an FST compiler, which produced a single FST that was much
    smaller than the sum of its parts and ran very fast. FSTs can be built by a variety of tools that accept an
    extended regular expression syntax.
    The ARPA-MIT LM format

    An ARPA-style language model file comes in two parts - the header and
    the  -gram definitions. The header contains a description of the contents
    of the file.
    <header> = { ngram <int>=<int> }
    The first <int> gives the  -gram order and the second <int> gives
    the number of  -gram entries stored.

    For example, a trigram language model consists of three sections - the


    unigram, bigram and trigram sections respectively. The corresponding
    entry in the header indicates the number of entries for that section. This
    can be used to aid the loading-in procedure. The body part contains all
    sections of the language model and is defined as follows:
    <body> = { <lmpart1> } <lmpart2>
    <lmpart1> = \<int>-grams:
    { <ngramdef1> }
    <lmpart2> = \<int>-grams:
    { <ngramdef2> }
    <ngramdef1> = <float> { <word> } <float>
    <ngramdef2> = <float> { <word> }
    Each %-gram definition starts with a probability value stored
    as log10 followed by a sequence of % words describing the actual  -
    gram. In all sections excepts the last one this is followed by a back-off
    weight which is also stored as log10. The following example shows an
    extract from a trigram language model stored in the ARPA-text format.
    \data\
    ngram 1=19979
    ngram 2=4987955
    ngram 3=6136155

    \1-grams:
    -1.6682 A -2.2371
    -5.5975 A'S -0.2818
    -2.8755 A. -1.1409
    -4.3297 A.'S -0.5886
    -5.1432 A.S -0.4862
    ...

    \2-grams:
    -3.4627 A BABY -0.2884
    -4.8091 A BABY'S -0.1659
    -5.4763 A BACH -0.4722
    -3.6622 A BACK -0.8814
    ...

    \3-grams:
    -4.3813 !SENT_START A CAMBRIDGE
    -4.4782 !SENT_START A CAMEL
    -4.0196 !SENT_START A CAMERA
    -4.9004 !SENT_START A CAMP
    -3.4319 !SENT_START A CAMPAIGN
    ...
    \end\
    Discrete Cosine Transform

    A discrete cosine transform (DCT) expresses a finite sequence


    of data points in terms of a sum of cosine functions oscillating at
    different frequencies
    Widely used transformation technique in signal
    processing and data compression(JPEG)
    CMVN
    CMVN minimizes distortion by noise contamination for
    robust feature extraction by linearly transforming the cepstral
    coefficients to have the same segmental statistics.[2] Cepstral
    Normalization has been effective in the CMU Sphinx for
    maintaining a high level of recognition accuracy over a wide
    variety of acoustical environments.[

    You might also like