We have been proposing a Spoken Term Detection (STD) method for Out-Of-Vocabulary (OOV) query terms integrating various subword recognition results using monophone, triphone, demiphone, one third phone, and Sub-phonetic segment (SPS) models. In the proposed method, subword-based ASR (Automatic Speech Recognition) is performed for all spoken documents and subword recognition results are generate...

Utterance verification is used in spoken language dialog systems to reject the speech that does not belong to the task and to correctly recognize the sentences that do. Current verification systems use context dependent (CD) or context independent (CI) subword models and CI anti-subword models. We propose many methods of modeling the CD anti-subword models. We have compared these anti-models an...

The basic numerical quantity investigated in this paper is |w|u, the number of occurrences of a word u as a scattered subword of a word w. Arithmetical combinations of such quantities yield a so-called subword history. We investigate the information content of subword histories. Reducing subword histories to linear ones, as well as the recently introduced Parikh matrices, will be important tool...

We begin a systematic study of the relations between subword complexity of infinite words and their power avoidance. Among other things, we show that – the Thue-Morse word has the minimum possible subword complexity over all overlapfree binary words and all (73)-power-free binary words, but not over all ( 7 3) +-power-free binary words; – the twisted Thue-Morse word has the maximum possible sub...

Because in agglutinative languages the number of observed word forms is very high, subword units are often utilized in speech recognition. However, the proper use of subword units requires careful consideration of details such as silence modeling, position-dependent phones, and combination of the units. In this paper, we implement subword modeling in the Kaldi toolkit by creating modified lexic...

We propose a general approach for translating Chinese unknown words (UNK) for SMT. This approach takes advantage of the properties of Chinese word composition rules, i.e., all Chinese words are formed by sequential characters. According to the proposed approach, the unknown word is re-split into a subword sequence followed by subword translation with a subwordbased translation model. “Subword” ...

We are interested in the state complexity of languages that are defined via the subword closure operation. The subword closure of a set S of fixed-length words is the set of all words w for which any subword of w of the fixed length is in S. This type of constraint appears to be useful in various situations related to data encodings and in particular to DNA encodings. We present a few results r...

This paper deals with a subword-unit-based isolated word recognition system with enhanced speaker-independency. The subword is defined as a part of word whose central portion has rather stationary or time-invariant short-time spectra with its portions near its ends having rapidly varying short-time spectra. In this system each isolated word is decomposed into a sequence of subwords, each of whi...