The present paper proposes a new integration method of plural spoken term detection (STD) results obtained from plural subword models that we previously proposed. We confirmed that these new subword models, which are the 1/2 phone model, the 1/3 phone model, and the sub-phonetic segment (SPS) model, are effective for STD systems, which must be vocabulary-free in order to process arbitrary query...

This article investigates as an early work on speech recognition of Thai named-entities, which is a crucial out-of-vocabulary word problem in broadcast news transcription. Motivated by an analysis on Thai-name structure, a statistical class-based language model is applied on multiple-sized subword units with a constraint on subword positions. Subwords can be defined automatically by their stati...

A new type of video retrieval system is proposed that identifies a target video section by searching for a word passage submitted as a quoted speech or text query. The proposed system has two unique characteristics. The first characteristic is that it is based on subword models such as phonemes, syllables, and morphemes so the system is able to deal with any type of query, including new words a...

A language L is prefix-free if, whenever words u and v are in L and u is a prefix of v, then u = v. Suffix-, factor-, and subword-free languages are defined similarly, where “subword” means “subsequence”. A language is bifix-free if it is both prefixand suffix-free. We study the quotient complexity, more commonly known as state complexity, of operations in the classes of bifix-, factor-, and su...

Sequences of characters called words or strings are widely studied in combinatorics, and used in various fields of sciences (e.g. chemistry, physics, social sciences, biology [2, 3, 4, 11] etc.). The elements of a word are called letters. A contiguous part of a word (obtained by erasing a prefix or/and a suffix) is a subword or factor. If we erase arbitrary letters from a word, what is obtained...

This thesis concerns the problem of unknown or out-of-vocabulary (OOV) words in continuous speech recognition. Most of today's state-of-the-art speech recognition systems can recognize only words that belong to some predefined finite word vocabulary. When encountering an OOV word, a speech recognizer erroneously substitutes the OOV word with a similarly sounding word from its vocabulary. Furthe...

We determine the subword complexity of the characteristic functions of a two-parameter family fA n g 1 n=1 of innnite sequences which are associated with the winning strategies for a family of 2-player games. A special case of the family has the form A n = bnnc for all n 2 Z >0 , where is a xed positive irrational number. The characteristic functions of such sequences have been shown to have su...

We generalize the brick polytope of V. Pilaud and F. Santos to spherical subword complexes for finite Coxeter groups. This construction provides polytopal realizations for a certain class of subword complexes containing all cluster complexes of finite types. For the latter, the brick polytopes turn out to coincide with the known realizations of generalized associahedra, thus opening new perspec...