We determine the subword complexity of the characteristic functions of a twoparameter family {An}∞n=1 of infinite sequences which are associated with the winning strategies for a family of 2-player games. A special case of the family has the form An = bnαc for all n ∈ Z>0, where α is a fixed positive irrational number. The characteristic functions of such sequences have been shown to have subwo...

| We show a comparative study of subword unit segmentation of Mandarin speech data. Most HMM recognition systems use intial//nals as subword units for Mandarin speech. We nd that such a division of monosylla-ble data into intial//nal units are not always supported by acoustic evidences. We implement a delta MFCC based seg-mentation method and compare its output with that of Viterbi segmentation...

In a given word, one can count the number of occurrences of other words as a scattered subword. These counts can be “added” and/or “multiplied.” A subword history gives an instruction of what words to be counted and how these counts to be added and multiplied with other counts or integer constants, and hence, determines its unique value in a given word. Mateescu, Salomaa, and Yu asked: “is it d...

In this paper, we investigate the feasibility of using machine learning method and subword units for spoken document categorization as an alternative to using words generated by word recognition or keyword spotting. An advantage of using subword acoustic unit representations to spoken document categorization is that it does not require prior knowledge about the contents of the spoken document a...

In this paper, we use subword complexes to provide a uniform approach to finite-type cluster complexes and multi-associahedra. We introduce, for any finite Coxeter group and any nonnegative integer k, a spherical subword complex called multi-cluster complex. For k = 1, we show that this subword complex is isomorphic to the cluster complex of the given type. We show that multi-cluster complexes ...

This paper deals with a hybrid word-subword recognition system for spoken term detection. The decoding is driven by a hybrid recognition network and the decoder directly produces hybrid word-subword lattices. One phone and two multigram models were tested to represent sub-word units. The systems were evaluated in terms of spoken term detection accuracy and the size of index. We concluded that t...

Subword complexity • The subword complexity c(x) of a string x is the number of distinct substrings of x (of any length) • Also called " complexity index " or " linguistic complexity " • Intuition: sequence with low complexity tend to be " repetitive " (easy to compress)

We provide an exact estimate on the maximal subword complexity for quasiperiodic infinite words. To this end we give a representation of the set of finite and of infinite words having a certain quasiperiod q via a finite language derived from q. It is shown that this language is a suffix code having a bounded delay of decipherability. Our estimate of the subword complexity uses this property, e...

A major challenge in speech recognition based on acoustic subword units is creating a lexicon which is robust to inter-and intra-speaker variations. In this paper we present a joint seg-mentation and labelling scheme to incorporate word-level linguistic knowledge into the training procedure. The proposed system is also based on a combined optimisation of the base-forms and the subword models. F...

A major challenge in speech recognition based on acoustic subword units is creating a lexicon which is robust to interand intra-speaker variations. In this paper we present two di erent approaches for incorporating simple word-level linguistic knowledge into the labelling step of the training procedure. The proposed systems also utilise a scheme for combined optimisation of baseforms and subwor...