A naïve, salience-based method for speaker identification in fiction books

This paper presents a salience-based technique for the annotation of directly quoted speech from fiction text. In particular, this paper determines to what extent a naïve (without the use of complex machine learning or knowledge-based techniques) scoring technique can be used for the identification of the speaker of speech quotes. The presented technique makes use of a scoring technique, similar to that commonly found in knowledge-poor anaphora resolution research, as well as a set of hand-coded rules for the final identification of the speaker of each quote in the text. Speaker identification is shown to be achieved using three tasks: the identification of a speech-verb associated with a quote with a recall of 94.41%; the identification of the actor associated with a quote with a recall of 88.22%; and the selection of a speaker with an accuracy of 79.40%.

Hierarchical rule generalisation for speaker identification in fiction books

This paper presents a hierarchical pattern matching and generalisation technique which is applied to the problem of locating the correct speaker of quoted speech found in fiction books. Patterns from a training set are generalised to create a small number of rules, which can be used to identify items of interest within the text. The pattern matching technique is applied to finding the Speech-Verb, Actor and Speaker of quotes found in ction books. The technique performs well over the training data, resulting in rule-sets many times smaller than the training set, but providing very high accuracy. While the rule-set generalised from one book is less effective when applied to different books than an approach based on hand coded heuristics, performance is comparable when testing on data closely related to the training set.

Text-dependent speaker recognition using the Fuzzy ARTMAP neural network

Speaker recognition is the process of automatically recognizing the speaker by analyzing individual information contained in the speech waves. In this paper, we discuss the development of an intelligent system for text-dependent speaker recognition. The system comprises two main modules, a wavelet-based signal-processing module for feature extraction of speech waves, and an artificial-neural-network-based classifier module to identify and categorize the speakers. Wavelet is used in de-noising and in compressing the speech signals. The wavelet family that we used is the Daubechies Wavelets. After extracting the necessary features from the speech waves, the features were then fed to a neural-network-based classifier to identify the speakers. We have implemented the Fuzzy ARTMAP (FAM) network in the classifier module to categorize the de-noised and compressed signals. The proposed intelligent learning system has been applied to a case study of text-dependent speaker recognition problem.

Text-dependent speaker recognition using wavelets and neural networks

An intelligent system for text-dependent speaker recognition is proposed in this paper. The system consists of a wavelet-based module as the feature extractor of speech signals and a neural-network-based module as the signal classifier. The Daubechies wavelet is employed to filter and compress the speech signals. The fuzzy ARTMAP (FAM) neural network is used to classify the processed signals. A series of experiments on text-dependent gender and speaker recognition are conducted to assess the effectiveness of the proposed system using a collection of vowel signals from 100 speakers. A variety of operating strategies for improving the FAM performance are examined and compared. The experimental results are analyzed and discussed.

Development of a speaker recognition system using wavelets and artificial neural networks

This paper addresses the problem of speaker recognition from speech signals. The study focuses on the development of a speaker recognition system comprising two modules: a wavelet-based feature extractor, and a neural-network-based classifier. We have conducted a number of experiments to investigate the applicability of Discrete Wavelet Transform (D WT) in extracting discriminative features from the speech signals, and have examined various models from the Adaptive Resonance Theory (ART) family of neural networks in classijjing the extracted features. The results indicate that DWT could be a potential feature extraction tool for speaker recognition. In addition, the ART-based classijiers have yielded very promising recognition accuracy at more than 81%.

Slipper saga begs the question – do we need a speaker at all?

Speaker of the House of Representatives Peter Slipper has stepped aside following allegations of sexual harassment and the misuse of cab-charge vouchers.

Improving English language teaching in Thailand

The teaching of English in Thailand is a matter of national concern. The national government believes that the ability of Thai people to use English for effective communication is very important for the continuing economic development of Thailand. However many students who have had primary, secondary and university exposure to English find it difficult to conduct a conversation with a native speaker of English. The reasons for this include lack of student motivation and contextual support, large classes, the dominating effects of assessment on what is taught, and the English language competency of the teachers. The research in this thesis focuses on the teaching of English as a foreign language in secondary schools in Khon Kaen. The research reported here consists of one major and three minor studies. In the major study some of the principles of action research were used to explore strategies that would improve the teaching of English in a number of secondary schools in Khon Kaen in Thailand. In the first phase of the major study I worked with two teachers to design and implement a series of classroom activities that encouraged lower secondary students to use English. In the second phase I worked with a group of teachers to design and deliver a professional development program for twenty school teachers interested in improving their English language teaching. In the third phase I used data from the first two phases to design five new activities that were used in classrooms by two teachers. Findings from the three phases indicated that working collaboratively with school teachers can be a mutually beneficial professional experience and can improve student interest and learning. In the first minor study I used interview-conversations to investigate the perceptions that subject co-ordinators and teachers have towards English language teaching. The conversations covered the merits of detailed curricula and curricula frameworks, professional development, assessment, resources, and integration of English language with other subjects. It was clear that the teachers were aware of the national government s policies for the improving English language teaching and accepted the need for change. It was equally clear that the preparation of teachers and the resources available were major limiting factors in schools to teacher effectiveness. In the second minor study I examined the teaching of Mandarin in an Australian school that suffered from some of the same resource problems as Thai schools. Although there was only one teacher available for all of the Mandarin classes in the school she was extremely effective. Her teaching was an example of best practice. It included thorough preparation, the ability to manage lessons at the pace of the learners, active classes and individual attention, detailed assessment records, and the integration of language and culture. Some or all of these could be used in Thai schools. The third minor study was an investigation of the professional development experiences of English language teachers in Thai schools. In most schools there are consultative and administrative mechanisms, acceptable to principals and teachers, in place to support professional development. Access to native speakers was seen as very important. However, the schools in Khon Kaen province have little or no access to native speakers of English. Even if they were available, the schools do not have the funds to employ them. Findings from the four studies indicate that it is quite possible to use interactive, participatory or student-centred pedagogies to teach English as a foreign language in Thai classrooms. However, one cannot expect teachers to adopt such pedagogies unless they are convinced of their value. This can be achieved most effectively through a systematic and sustained program of professional development.

Health technology assessment in Australia : insights for China

 Keynote Speaker

Imagining future selves

This thesis reports how a vision of an ideal self as a speaker of English in the imagined global community where English is being used as lingua franca (ELF) by a vastly growing number of non-native English speakers (NNESs) for a wider communication alongside their L1, positively influences Taiwanese students' engagement in learning English in an exam-dominant context.

The power of the spoken word : sociolinguistic cues influence the misinformation effect

We investigated whether the sociolinguistic information delivered by spoken, accented postevent narratives would influence the misinformation effect. New Zealand subjects listened to misleading postevent information spoken in either a New Zealand (NZ) or North American (NA) accent. Consistent with earlier research, we found that NA accents were seen as more powerful and more socially attractive. We found that accents per se had no influence on the misinformation effect but sociolinguistic factors did: both power and social attractiveness affected subjects' susceptibility to misleading postevent suggestions. When subjects rated the speaker highly on power, social attractiveness did not matter; they were equally misled. However, when subjects rated the speaker low on power, social attractiveness did matter: subjects who rated the speaker high on social attractiveness were more misled than subjects who rated it lower. There were similar effects for confidence. These results have implications for our understanding of social influences on the misinformation effect.

Insider's guide to getting published

The 'Insider's guide to getting published' features keynote speaker Associate Professor Jeffrey Faux from Victoria University, editor of the Asian Review of Accounting and editorial board member of the Malaysian Accounting Review and the International Journal of Management Education.  Associate Professor Faux will provide tips and techniques about getting published in journals - specifically, those of leading independent publisher Emerald.