Towards improved speech recognition for resource poor languages

In recent times, the improved levels of accuracy obtained by Automatic Speech Recognition (ASR) technology has made it viable for use in a number of commercial products. Unfortunately, these types of applications are limited to only a few of the world’s languages, primarily because ASR development is reliant on the availability of large amounts of language specific resources. This motivates the need for techniques which reduce this language-specific, resource dependency. Ideally, these approaches should generalise across languages, thereby providing scope for rapid creation of ASR capabilities for resource poor languages. Cross Lingual ASR emerges as a means for addressing this need. Underpinning this approach is the observation that sound production is largely influenced by the physiological construction of the vocal tract, and accordingly, is human, and not language specific. As a result, a common inventory of sounds exists across languages; a property which is exploitable, as sounds from a resource poor, target language can be recognised using models trained on resource rich, source languages. One of the initial impediments to the commercial uptake of ASR technology was its fragility in more challenging environments, such as conversational telephone speech. Subsequent improvements in these environments has gained consumer confidence. Pragmatically, if cross lingual techniques are to considered a viable alternative when resources are limited, they need to perform under the same types of conditions. Accordingly, this thesis evaluates cross lingual techniques using two speech environments; clean read speech and conversational telephone speech. Languages used in evaluations are German, Mandarin, Japanese and Spanish. Results highlight that previously proposed approaches provide respectable results for simpler environments such as read speech, but degrade significantly when in the more taxing conversational environment. Two separate approaches for addressing this degradation are proposed. The first is based on deriving better target language lexical representation, in terms of the source language model set. The second, and ultimately more successful approach, focuses on improving the classification accuracy of context-dependent (CD) models, by catering for the adverse influence of languages specific phonotactic properties. Whilst the primary research goal in this thesis is directed towards improving cross lingual techniques, the catalyst for investigating its use was based on expressed interest from several organisations for an Indonesian ASR capability. In Indonesia alone, there are over 200 million speakers of some Malay variant, provides further impetus and commercial justification for speech related research on this language. Unfortunately, at the beginning of the candidature, limited research had been conducted on the Indonesian language in the field of speech science, and virtually no resources existed. This thesis details the investigative and development work dedicated towards obtaining an ASR system with a 10000 word recognition vocabulary for the Indonesian language.

The design and testing of a daylighting device : optimising the energy and optical performance of Australian commercial buildings

The effective daylighting of multistorey commercial building interiors poses an interesting problem for designers in Australia’s tropical and subtropical context. Given that a building exterior receives adequate sun and skylight as dictated by location-specific factors such as weather, siting and external obstructions; then the availability of daylight throughout its interior is dependant on certain building characteristics: the distance from a window façade (room depth), ceiling or window head height, window size and the visible transmittance of daylighting apertures. The daylighting of general stock, multistorey commercial buildings is made difficult by their design limitations with respect to some of these characteristics. The admission of daylight to these interiors is usually exclusively by vertical windows. Using conventional glazing, such windows can only admit sun and skylight to a depth of approximately 2 times the window height. This penetration depth is typically much less than the depth of the office interiors, so that core areas of these buildings receive little or no daylight. This issue is particularly relevant where deep, open plan office layouts prevail. The resulting interior daylight pattern is a relatively narrow perimeter zone bathed in (sometimes too intense) light, contrasted with a poorly daylit core zone. The broad luminance range this may present to a building occupant’s visual field can be a source of discomfort glare. Furthermore, the need in most tropical and subtropical regions to restrict solar heat gains to building interiors for much of the year has resulted in the widespread use of heavily tinted or reflective glazing on commercial building façades. This strategy reduces the amount of solar radiation admitted to the interior, thereby decreasing daylight levels proportionately throughout. However this technique does little to improve the way light is distributed throughout the office space. Where clear skies dominate weather conditions, at different times of day or year direct sunlight may pass unobstructed through vertical windows causing disability or discomfort glare for building occupants and as such, its admission to an interior must be appropriately controlled. Any daylighting system to be applied to multistorey commercial buildings must consider these design obstacles, and attempt to improve the distribution of daylight throughout these deep, sidelit office spaces without causing glare conditions. The research described in this thesis delineates first the design optimisation and then the actual prototyping and manufacture process of a daylighting device to be applied to such multistorey buildings in tropical and subtropical environments.

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.

Self-service technology and the moderating effects of consumer characteristics

The incidence of self-service technology, where the consumer delivers the service themselves using technology, is increasing in the service encounter. One area that is under-explored is the potential impact of self-service technology on consumer satisfaction and affective commitment. Accordingly, this paper presents an empirical study that investigates the relative impact of self-service technology on consumer satisfaction (both overall and transaction-specific) and affective commitment, accounting for the moderating effects of consumer characteristics. The results highlight the importance of personal service for evaluations of satisfaction and commitment, and the importance of social competency as a moderator in this relationship. An understanding of these consumer perceptions will allow organisations to develop strategies to deliver the services expected by their consumers, improving consumer satisfaction and commitment.

The record producer as nexus : creative inspiration, technology and the recording industry

What is a record producer? There is a degree of mystery and uncertainty about just what goes on behind the studio door. Some producers are seen as Svengali-like figures manipulating artists into mass consumer product. Producers are sometimes seen as mere technicians whose job is simply to set up a few microphones and press the record button. Close examination of the recording process will show how far this is from a complete picture. Artists are special—they come with an inspiration, and a talent, but also with a variety of complications, and in many ways a recording studio can seem the least likely place for creative expression and for an affective performance to happen. The task of the record producer is to engage with these artists and their songs and turn these potentials into form through the technology of the recording studio. The purpose of the exercise is to disseminate this fixed form to an imagined audience—generally in the hope that this audience will prove to be real. Finding an audience is the role of the record company. A record producer must also engage with the commercial expectations of the interests that underwrite a recording. This dissertation considers three fields of interest in the recording process: the performer and the song; the technology of the recording context; and the commercial ambitions of the record company—and positions the record producer as a nexus at the interface of all three. The author reports his structured recollection of five recordings, with three different artists, that all achieved substantial commercial success. The processes are considered from the author’s perspective as the record producer, and from inception of the project to completion of the recorded work. What were the processes of engagement? Do the actions reported conform to the template of nexus? This dissertation proposes that in all recordings the function of producer/nexus is present and necessary—it exists in the interaction of the artistry and the technology. The art of record production is to engage with these artists and the songs they bring and turn these potentials into form.

Assessment of the influence of cultural barriers to HDR supervision of non-English speaking background (NESD) students in engineering and information technology (IT) disciplines

The paper details the results of the first phase of an on-going research into the sociocultural factors that influence the supervision of higher degrees research (HDR) engineering students in the Faculty of Built Environment and Engineering (BEE) and Faculty of Science and Technology (FaST) at Queensland University of Technology. A quantitative analysis was performed on the results from an online survey that was administered to 179 engineering students. The study reveals that cultural barriers impact their progression and developing confidence in their research programs. We argue that in order to assist international and non-English speaking background (NESB) research students to triumph over such culturally embedded challenges in engineering research, it is important for supervisors to understand this cohort's unique pedagogical needs and develop intercultural sensitivity in their pedagogical practice in postgraduate research supervision. To facilitate this, the governing body (Office of Research) can play a vital role in not only creating the required support structures but also their uniform implementation across the board.