Acoustic keyword spotting in speech with applications to data mining

Keyword Spotting is the task of detecting keywords of interest within continu- ous speech. The applications of this technology range from call centre dialogue systems to covert speech surveillance devices. Keyword spotting is particularly well suited to data mining tasks such as real-time keyword monitoring and unre- stricted vocabulary audio document indexing. However, to date, many keyword spotting approaches have su®ered from poor detection rates, high false alarm rates, or slow execution times, thus reducing their commercial viability. This work investigates the application of keyword spotting to data mining tasks. The thesis makes a number of major contributions to the ¯eld of keyword spotting. The ¯rst major contribution is the development of a novel keyword veri¯cation method named Cohort Word Veri¯cation. This method combines high level lin- guistic information with cohort-based veri¯cation techniques to obtain dramatic improvements in veri¯cation performance, in particular for the problematic short duration target word class. The second major contribution is the development of a novel audio document indexing technique named Dynamic Match Lattice Spotting. This technique aug- ments lattice-based audio indexing principles with dynamic sequence matching techniques to provide robustness to erroneous lattice realisations. The resulting algorithm obtains signi¯cant improvement in detection rate over lattice-based audio document indexing while still maintaining extremely fast search speeds. The third major contribution is the study of multiple veri¯er fusion for the task of keyword veri¯cation. The reported experiments demonstrate that substantial improvements in veri¯cation performance can be obtained through the fusion of multiple keyword veri¯ers. The research focuses on combinations of speech background model based veri¯ers and cohort word veri¯ers. The ¯nal major contribution is a comprehensive study of the e®ects of limited training data for keyword spotting. This study is performed with consideration as to how these e®ects impact the immediate development and deployment of speech technologies for non-English languages.

Learning power and language expressiveness

The topic of the present work is to study the relationship between the power of the learning algorithms on the one hand, and the expressive power of the logical language which is used to represent the problems to be learned on the other hand. The central question is whether enriching the language results in more learning power. In order to make the question relevant and nontrivial, it is required that both texts (sequences of data) and hypotheses (guesses) be translatable from the “rich” language into the “poor” one. The issue is considered for several logical languages suitable to describe structures whose domain is the set of natural numbers. It is shown that enriching the language does not give any advantage for those languages which define a monadic second-order language being decidable in the following sense: there is a fixed interpretation in the structure of natural numbers such that the set of sentences of this extended language true in that structure is decidable. But enriching the original language even by only one constant gives an advantage if this language contains a binary function symbol (which will be interpreted as addition). Furthermore, it is shown that behaviourally correct learning has exactly the same power as learning in the limit for those languages which define a monadic second-order language with the property given above, but has more power in case of languages containing a binary function symbol. Adding the natural requirement that the set of all structures to be learned is recursively enumerable, it is shown that it pays o6 to enrich the language of arithmetics for both finite learning and learning in the limit, but it does not pay off to enrich the language for behaviourally correct learning.

Mind change complexity of learning logic programs

The present paper motivates the study of mind change complexity for learning minimal models of length-bounded logic programs. It establishes ordinal mind change complexity bounds for learnability of these classes both from positive facts and from positive and negative facts. Building on Angluin’s notion of finite thickness and Wright’s work on finite elasticity, Shinohara defined the property of bounded finite thickness to give a sufficient condition for learnability of indexed families of computable languages from positive data. This paper shows that an effective version of Shinohara’s notion of bounded finite thickness gives sufficient conditions for learnability with ordinal mind change bound, both in the context of learnability from positive data and for learnability from complete (both positive and negative) data. Let Omega be a notation for the first limit ordinal. Then, it is shown that if a language defining framework yields a uniformly decidable family of languages and has effective bounded finite thickness, then for each natural number m >0, the class of languages defined by formal systems of length <= m: • is identifiable in the limit from positive data with a mind change bound of Omega (power)m; • is identifiable in the limit from both positive and negative data with an ordinal mind change bound of Omega × m. The above sufficient conditions are employed to give an ordinal mind change bound for learnability of minimal models of various classes of length-bounded Prolog programs, including Shapiro’s linear programs, Arimura and Shinohara’s depth-bounded linearly covering programs, and Krishna Rao’s depth-bounded linearly moded programs. It is also noted that the bound for learning from positive data is tight for the example classes considered.

Automatic spoken language identification utilizing acoustic and phonetic speech information

Automatic spoken Language Identi¯cation (LID) is the process of identifying the language spoken within an utterance. The challenge that this task presents is that no prior information is available indicating the content of the utterance or the identity of the speaker. The trend of globalization and the pervasive popularity of the Internet will amplify the need for the capabilities spoken language identi¯ca- tion systems provide. A prominent application arises in call centers dealing with speakers speaking di®erent languages. Another important application is to index or search huge speech data archives and corpora that contain multiple languages. The aim of this research is to develop techniques targeted at producing a fast and more accurate automatic spoken LID system compared to the previous National Institute of Standards and Technology (NIST) Language Recognition Evaluation. Acoustic and phonetic speech information are targeted as the most suitable fea- tures for representing the characteristics of a language. To model the acoustic speech features a Gaussian Mixture Model based approach is employed. Pho- netic speech information is extracted using existing speech recognition technol- ogy. Various techniques to improve LID accuracy are also studied. One approach examined is the employment of Vocal Tract Length Normalization to reduce the speech variation caused by di®erent speakers. A linear data fusion technique is adopted to combine the various aspects of information extracted from speech. As a result of this research, a LID system was implemented and presented for evaluation in the 2003 Language Recognition Evaluation conducted by the NIST.

A programming language for software components

Component software has many benefits, most notably increased software re-use; however, the component software process places heavy burdens on programming language technology, which modern object-oriented programming languages do not address. In particular, software components require specifications that are both sufficiently expressive and sufficiently abstract, and, where possible, these specifications should be checked formally by the programming language. This dissertation presents a programming language called Mentok that provides two novel programming language features enabling improved specification of stateful component roles. Negotiable interfaces are interface types extended with protocols, and allow specification of changing method availability, including some patterns of out-calls and re-entrance. Type layers are extensions to module signatures that allow specification of abstract control flow constraints through the interfaces of a component-based application. Development of Mentok's unique language features included creation of MentokC, the Mentok compiler, and formalization of key properties of Mentok in mini-languages called MentokP and MentokL.

Contextualising the teaching and learning of measurement within Torres Strait Islander schools

A one year mathematics project that focused on measurement was conducted with six Torres Strait Islander schools and communities. Its key focus was to contextualise the teaching and learning of measurement within the students’ culture, communities and home languages. There were six teachers and two teacher aides who participated in the project. This paper reports on the findings from the teachers’ and teacher aides’ survey questionnaire used in the first Professional Development session to identify: a) teachers’ experience of teaching in Torres Strait Islands, b) teachers’ beliefs about effective ways to teach Torres Strait Islander students, and c) contexualising measurement within Torres Strait Islander culture, Communities and home languages. A wide range of differing levels of knowledge and understanding about how to contextualise measurement to support student learning were identified and analysed. For example, an Indigenous teacher claimed that mathematics and the environment are relational, that is, they are not discrete and in isolation from one another, rather they interconnect with mathematical ideas emerging from the environment of the Torres Strait Communities.

On model typing

Where object-oriented languages deal with objects as described by classes, model-driven development uses models, as graphs of interconnected objects, described by metamodels. A number of new languages have been and continue to be developed for this model- based paradigm, both for model transformation and for general programming using models. Many of these use single-object approaches to typing, derived from solutions found in object-oriented systems, while others use metamodels as model types, but without a clear notion of polymorphism. Both of these approaches lead to brittle and overly restrictive reuse characteristics. In this paper we propose a simple extension to object-oriented typing to better cater for a model-oriented context, including a simple strategy for typing models as a collection of interconnected objects. We suggest extensions to existing type system formalisms to support these concepts and their manipulation. Using a simple example we show how this extended approach permits more flexible reuse, while preserving type safety.

The nonconceptual gateway to early word learning

My research investigates why nouns are learned disproportionately more frequently than other kinds of words during early language acquisition (Gentner, 1982; Gleitman, et al., 2004). This question must be considered in the context of cognitive development in general. Infants have two major streams of environmental information to make meaningful: perceptual and linguistic. Perceptual information flows in from the senses and is processed into symbolic representations by the primitive language of thought (Fodor, 1975). These symbolic representations are then linked to linguistic input to enable language comprehension and ultimately production. Yet, how exactly does perceptual information become conceptualized? Although this question is difficult, there has been progress. One way that children might have an easier job is if they have structures that simplify the data. Thus, if particular sorts of perceptual information could be separated from the mass of input, then it would be easier for children to refer to those specific things when learning words (Spelke, 1990; Pylyshyn, 2003). It would be easier still, if linguistic input was segmented in predictable ways (Gentner, 1982; Gleitman, et al., 2004) Unfortunately the frequency of patterns in lexical or grammatical input cannot explain the cross-cultural and cross-linguistic tendency to favor nouns over verbs and predicates. There are three examples of this failure: 1) a wide variety of nouns are uttered less frequently than a smaller number of verbs and yet are learnt far more easily (Gentner, 1982); 2) word order and morphological transparency offer no insight when you contrast the sentence structures and word inflections of different languages (Slobin, 1973) and 3) particular language teaching behaviors (e.g. pointing at objects and repeating names for them) have little impact on children's tendency to prefer concrete nouns in their first fifty words (Newport, et al., 1977). Although the linguistic solution appears problematic, there has been increasing evidence that the early visual system does indeed segment perceptual information in specific ways before the conscious mind begins to intervene (Pylyshyn, 2003). I argue that nouns are easier to learn because their referents directly connect with innate features of the perceptual faculty. This hypothesis stems from work done on visual indexes by Zenon Pylyshyn (2001, 2003). Pylyshyn argues that the early visual system (the architecture of the "vision module") segments perceptual data into pre-conceptual proto-objects called FINSTs. FINSTs typically correspond to physical things such as Spelke objects (Spelke, 1990). Hence, before conceptualization, visual objects are picked out by the perceptual system demonstratively, like a finger pointing indicating ‘this’ or ‘that’. I suggest that this primitive system of demonstration elaborates on Gareth Evan's (1982) theory of nonconceptual content. Nouns are learnt first because their referents attract demonstrative visual indexes. This theory also explains why infants less often name stationary objects such as plate or table, but do name things that attract the focal attention of the early visual system, i.e., small objects that move, such as ‘dog’ or ‘ball’. This view leaves open the question how blind children learn words for visible objects and why children learn category nouns (e.g. 'dog'), rather than proper nouns (e.g. 'Fido') or higher taxonomic distinctions (e.g. 'animal').

Distributing sensitive information in the MPEG-21 multimedia framework

The MPEG-21 Multimedia Framework provides for controlled distribution of multimedia works through its Intellectual Property Management and Protection ("IPMP") Components and Rights Expression Language ("MPEG REL"). The IPMP Components provide a framework by which the components of an MPEG-21 digital item can be protected from undesired access, while MPEG REL provides a mechanism for describing the conditions under which a component of a digital item may be used and distributed. This chapter describes how the IPMP Components and MPEG REL were used to implement a series of digital rights management applications at the Cooperative Research Centre for Smart Internet Technology in Australia. While the IPMP Components and MPEG REL were initially designed to facilitate the protection of copyright, the applications also show how the technology can be adapted to the protection of private personal information and sensitive corporate information.

The inadequacy of embedded markup for cultural heritage texts

Embedded generalized markup, as applied by digital humanists to the recording and studying of our textual cultural heritage, suffers from a number of serious technical drawbacks. As a result of its evolution from early printer control languages, generalized markup can only express a document’s ‘logical’ structure via a repertoire of permissible printed format structures. In addition to the well-researched overlap problem, the embedding of markup codes into texts that never had them when written leads to a number of further difficulties: the inclusion of potentially obsolescent technical and subjective information into texts that are supposed to be archivable for the long term, the manual encoding of information that could be better computed automatically, and the obscuring of the text by highly complex technical data. Many of these problems can be alleviated by asserting a separation between the versions of which many cultural heritage texts are composed, and their content. In this way the complex inter-connections between versions can be handled automatically, leaving only simple markup for individual versions to be handled by the user.

Automatic generation of assertions to detect potential security vulnerabilities in C programs that use union and pointer types

Type unions, pointer variables and function pointers are a long standing source of subtle security bugs in C program code. Their use can lead to hard-to-diagnose crashes or exploitable vulnerabilities that allow an attacker to attain privileged access over classified data. This paper describes an automatable framework for detecting such weaknesses in C programs statically, where possible, and for generating assertions that will detect them dynamically, in other cases. Exclusively based on analysis of the source code, it identifies required assertions using a type inference system supported by a custom made symbol table. In our preliminary findings, our type system was able to infer the correct type of unions in different scopes, without manual code annotations or rewriting. Whenever an evaluation is not possible or is difficult to resolve, appropriate runtime assertions are formed and inserted into the source code. The approach is demonstrated via a prototype C analysis tool.

A review of simulation models for railway systems

With the advances in computer hardware and software development techniques in the past 25 years, digital computer simulation of train movement and traction systems has been widely adopted as a standard computer-aided engineering tool [1] during the design and development stages of existing and new railway systems. Simulators of different approaches and scales are used extensively to investigate various kinds of system studies. Simulation is now proven to be the cheapest means to carry out performance predication and system behaviour characterisation. When computers were first used to study railway systems, they were mainly employed to perform repetitive but time-consuming computational tasks, such as matrix manipulations for power network solution and exhaustive searches for optimal braking trajectories. With only simple high-level programming languages available at the time, full advantage of the computing hardware could not be taken. Hence, structured simulations of the whole railway system were not very common. Most applications focused on isolated parts of the railway system. It is more appropriate to regard those applications as primarily mechanised calculations rather than simulations. However, a railway system consists of a number of subsystems, such as train movement, power supply and traction drives, which inevitably contains many complexities and diversities. These subsystems interact frequently with each other while the trains are moving; and they have their special features in different railway systems. To further complicate the simulation requirements, constraints like track geometry, speed restrictions and friction have to be considered, not to mention possible non-linearities and uncertainties in the system. In order to provide a comprehensive and accurate account of system behaviour through simulation, a large amount of data has to be organised systematically to ensure easy access and efficient representation; the interactions and relationships among the subsystems should be defined explicitly. These requirements call for sophisticated and effective simulation models for each component of the system. The software development techniques available nowadays allow the evolution of such simulation models. Not only can the applicability of the simulators be largely enhanced by advanced software design, maintainability and modularity for easy understanding and further development, and portability for various hardware platforms are also encouraged. The objective of this paper is to review the development of a number of approaches to simulation models. Attention is, in particular, given to models for train movement, power supply systems and traction drives. These models have been successfully used to enable various ‘what-if’ issues to be resolved effectively in a wide range of applications, such as speed profiles, energy consumption, run times etc.

Managing process model collections with AProMoRe

As organizations reach higher levels of Business Process Management maturity, they tend to collect numerous business process models. Such models may be linked with each other or mutually overlap, supersede one another and evolve over time. Moreover, they may be represented at different abstraction levels depending on the target audience and modeling purpose, and may be available in multiple languages (e.g. due to company mergers). Thus, it is common that organizations struggle with keeping track of their process models. This demonstration introduces AProMoRe (Advanced Process Model Repository) which aims to facilitate the management of (large) process model collections.

Rights versus reality : the difficulty of providing 'access to English' in Queensland Courts

This report was developed out of a Legal Practitioner on Trust Account Fund grant from the Department of Justice and Attorney-General in Queensland, to review the Aboriginal English in the Courts Handbook. Judges, Magistrates, barristers and court staff were interviewed about the Handbook. The findings extend beyond Aboriginal English into access to English in Queensland Courts. Recommendations are made about language difficulties faced by witnessed and the ability to the courts to respond to them.

Listening to voices of self : digital journaling among gifted young adolescents

The lives of gifted young adolescents are often subject to adult-generated and expert narratives that can impact a developing sense of self. However, opportunities for gifted young adolescents to represent themselves as informants can emerge through digital forms of qualitative research. This paper reports on the value of digital writing of journal entries, delivered by email to a researcher over several months, as an alternative to face-to-face interviews. Journaling methods combined with techniques of 'listening for voices' can support young adolescents in generating their own multi-vocal narratives of self. This method capturing self-narratives in email form has the potential to produce rich understandings of individual young adolescents' self-constructions.