Lexical Access using Minimum Message

نویسندگان

  • Ian Thomas
  • Ingrid Zukerman
  • Jonathan Oliver
  • Bhavani Raskutti
چکیده

A method for deriving equivalence classes for lexical access in speech recognition is considered, which automatically derives equivalence classes from training data using unsupervised learning and the Minimum Message Length Criterion. These classes model insertions, deletions and substitutions in an input phoneme string due to mis-recognition and mis-pronunciation, and allow unlikely word candidates to be eliminated quickly. This in turn allows a more detailed examination of the remaining candidates to be carried out eeciently.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Lexical Access for Speech Understanding using Minimum Message Length Encoding

Lexicon entry1: Data: The Lexical Access Problem consists of determining the intended sequence of words corresponding to an input sequence of phonemes (basic speech sounds) that come from a low-level phoneme recognizer. In this paper we present an information-theoretic approach based on the Minimum Message Length Criterion for solving the Lexical Access Problem. We model sentences using phoneme...

متن کامل

A Minimum Message Length Evaluation Metric for Lexical Access in Speech Understanding

We describe an information-theoretic measure for evaluating sentence hypotheses during speech understanding. Our measure, which is based on the Minimum Message Length (MML) criterion, allows us to evaluate a postulated sequence of words that corresponds to a sequence of input phonemes (basic speech sounds) obtained from a phoneme recogniser. Our measure is used for ranking partial sentence hypo...

متن کامل

Extracting Phoneme Pronunciation Information from Corpora

We present a procedure that determines a set of phonemes possibly intended by a speaker from a recognized or uttered phone. This information will be used to allow a speech recognizer to take pronunciation into account or to consider input from a noisy source during lexical access. We investigate the hypothesis that different pronunciations of a phone occur within groups of sounds physically pro...

متن کامل

Lexical Access in Persian Normal Speakers: Picture Naming, Verbal Fluency and Spontaneous Speech

Objectives: Lexical access is the process by which the basic conceptual, syntactical and morpho-phonological information of words are activated. Most studies of lexical access have focused on picture naming. There is hardly any previous research on other parameters of lexical access such as verbal fluency and analysis of connected speech in Persian normal participants. This study investigates t...

متن کامل

The production of lexical categories (VP) and functional categories (copula) at the initial stage of child L2 acquisition

This is a longitudinal case study of two Farsi-speaking children learning English: ‘Bernard’ and ‘Melissa’, who were 7;4 and 8;4 at the start of data collection. The research deals with the initial state and further development in the child second language (L2) acquisition of syntax regarding the presence or absence of copula as a functional category, as well as the role and degree of L1 influe...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1996