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.

Coding speech signals at very low rates (below 1 kb/s) with high intelligibility

This thesis presents an original approach to parametric speech coding at rates below 1 kbitsjsec, primarily for speech storage applications. Essential processes considered in this research encompass efficient characterization of evolutionary configuration of vocal tract to follow phonemic features with high fidelity, representation of speech excitation using minimal parameters with minor degradation in naturalness of synthesized speech, and finally, quantization of resulting parameters at the nominated rates. For encoding speech spectral features, a new method relying on Temporal Decomposition (TD) is developed which efficiently compresses spectral information through interpolation between most steady points over time trajectories of spectral parameters using a new basis function. The compression ratio provided by the method is independent of the updating rate of the feature vectors, hence allows high resolution in tracking significant temporal variations of speech formants with no effect on the spectral data rate. Accordingly, regardless of the quantization technique employed, the method yields a high compression ratio without sacrificing speech intelligibility. Several new techniques for improving performance of the interpolation of spectral parameters through phonetically-based analysis are proposed and implemented in this research, comprising event approximated TD, near-optimal shaping event approximating functions, efficient speech parametrization for TD on the basis of an extensive investigation originally reported in this thesis, and a hierarchical error minimization algorithm for decomposition of feature parameters which significantly reduces the complexity of the interpolation process. Speech excitation in this work is characterized based on a novel Multi-Band Excitation paradigm which accurately determines the harmonic structure in the LPC (linear predictive coding) residual spectra, within individual bands, using the concept 11 of Instantaneous Frequency (IF) estimation in frequency domain. The model yields aneffective two-band approximation to excitation and computes pitch and voicing with high accuracy as well. New methods for interpolative coding of pitch and gain contours are also developed in this thesis. For pitch, relying on the correlation between phonetic evolution and pitch variations during voiced speech segments, TD is employed to interpolate the pitch contour between critical points introduced by event centroids. This compresses pitch contour in the ratio of about 1/10 with negligible error. To approximate gain contour, a set of uniformly-distributed Gaussian event-like functions is used which reduces the amount of gain information to about 1/6 with acceptable accuracy. The thesis also addresses a new quantization method applied to spectral features on the basis of statistical properties and spectral sensitivity of spectral parameters extracted from TD-based analysis. The experimental results show that good quality speech, comparable to that of conventional coders at rates over 2 kbits/sec, can be achieved at rates 650-990 bits/sec.

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.

Theatre audience contribution : facilitating a new text through the post-performance discussion

Theatre Audience Contribution introduces a new approach to theatre audience research: audience contribution through the post-performance discussion. This volume considers the physical and vocal behaviour of audience members as an integral part of the theatrical event that changes, adds to and informs the theatrical experience. Post-performance discussions, although rising in popularity, are yet an under-explored and under-utilised avenue for audience contribution. Beginning with an overview of reception theory and the historical role of theatre audiences, the author introduces a new method for the facilitation of post-performance discussions that encourages audience contribution and privileges the audience voice. Two case studies explore post-performance discussions that inform the theatrical event and discover a new role for the contemporary audience: audience critic. This accessible volume has significant implications for theatre theorists, practitioners and audiences alike.

IDOL

Idol is a collaborative performance work for vocal performer and dancers. The work explores movement and sound relative to a vocal interface called the eMic (Extended Microphone Interface Controller). The eMic is a gestural controller designed by the composer for live vocal performance an real-time processing. The process for generating the work involves the choreographer being provided an opportunity to experiment with gestures ad movement relative to the eMic interface. The choreographer explored the interface as an object,a prop, an instrument and as an extension of the body. the movement was then videoed and the data coming from the sensors simultaneously recorded. The data and the video were then used as part of the compositional process, allowing the composer to see what the performance looks like and to experiment with mapping strategies using the captured sensor data. This approach represents a new compositional direction for working with the eMic, in that previously the compositional process commenced at the computer, building processing patches and assigning parameters to eMic sensors. In order to play the composition, the body needed to adapt to 'playing' the instrument. This approach treats the eMic like a traditional instrument that requires the human body to develop a command over the instrument. Working with the movement as a starting point inverts the process using choreographic gestures as the basis for musical structures.

Attractiveness of venture idea amongst expert entrepreneurs : a conjoint analysis

Principal Topic Venture ideas are at the heart of entrepreneurship (Davidsson, 2004). However, we are yet to learn what factors drive entrepreneurs’ perceptions of the attractiveness of venture ideas, and what the relative importance of these factors are for their decision to pursue an idea. The expected financial gain is one factor that will obviously influence the perceived attractiveness of a venture idea (Shepherd & DeTienne, 2005). In addition, the degree of novelty of venture ideas along one or more dimensions such as new products/services, new method of production, enter into new markets/customer and new method of promotion may affect their attractiveness (Schumpeter, 1934). Further, according to the notion of an individual-opportunity nexus venture ideas are closely associated with certain individual characteristics (relatedness). Shane (2000) empirically identified that individual’s prior knowledge is closely associated with the recognition of venture ideas. Sarasvathy’s (2001; 2008) Effectuation theory proposes a high degree of relatedness between venture ideas and the resource position of the individual. This study examines how entrepreneurs weigh considerations of different forms of novelty and relatedness as well as potential financial gain in assessing the attractiveness of venture ideas. Method I use conjoint analysis to determine how expert entrepreneurs develop preferences for venture ideas which involved with different degrees of novelty, relatedness and potential gain. The conjoint analysis estimates respondents’ preferences in terms of utilities (or part-worth) for each level of novelty, relatedness and potential gain of venture ideas. A sample of 32 expert entrepreneurs who were awarded young entrepreneurship awards were selected for the study. Each respondent was interviewed providing with 32 scenarios which explicate different combinations of possible profiles open them into consideration. Results and Implications Results indicate that while the respondents do not prefer mere imitation they receive higher utility for low to medium degree of newness suggesting that high degrees of newness are fraught with greater risk and/or greater resource needs. Respondents pay considerable weight on alignment with the knowledge and skills they already posses in choosing particular venture idea. The initial resource position of entrepreneurs is not equally important. Even though expected potential financial gain gives substantial utility, result indicate that it is not a dominant factor for the attractiveness of venture idea.

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.

The 'Dirty Work' of the Lie

The panel "Duplicity/Complicity: Performing and Misperforming Lies" at PSi #15 in Croatia in July 2009 examined the half-truths, hidden assumptions and power relations embedded in every act of performance through an analysis of the way bodies, buildings, personae and communities perform and misperform lies. It was a collection of new academic voices from Australia and Croatia, intersecting and colliding and, at times, outright lying, with each other and with commentary from Alan Read. Inspired by this successful adventure in collaborative academic mis-performance, "The ‘Dirty Work’ of the Lie" takes the challenge set by the Prelude Panel at PSI #15 and subjects the ideas emerging from this panel to "friendly fire" in order to build a multi authored response to 'performance that lies', with reference to the work of A Chorus of Women, disabled artists Bill Shannon, Aaron Williamson and Kathryn Araneillo, US dance performer Ann Liv Young and US theatre and festival director Peter Sellars. In doing so, "The 'Dirty Work' of the Lie" provides a reflexive response to the duplicity inherent in the performances, and also in our own academic analyses. With Alan Read acting as interlocutor, each contributor will creatively respond to a paper presented by another, developing the key intersecting issues that emerged through the formation of the panel. These issues include impression management, self-belief and performers who are 'taken in by their own act', the dirty work of taking others in with an act, the guerrilla dimension of lying, the productivity of the lie, and questions of audience engagement and ethics. As a result, this new paper tests how the 'misperformance' of lies across different cultural sites, be it deliberate or accidental, can become a productive – and, indeed, politicised – aspect of cultural performance, betraying accepted attitudes, ideas and structures of authority and offering alternative visions. Through it’s distinctively multi vocal texture, "The 'Dirty Work' of the Lie" also interrogates the modes of analysis available to us, questioning the 'duplicity' in our reflecting, responding and listening to each other as well as the work.

Re-framing fashion : from original and copy to adaptation

This article discusses the interaction between original and adaptation in the fashion system; the study also analyses, at a micro level, practices of adaptation adopted by consumers when making and re-making fashionable clothes. The article shows that the distinction between original and copy is historically determined as it grew out of the romantic notion of the authentic work of art. This article suggests that, in the impossibility to determine copyright in fashion, adaptation is a better descriptor of practices that transform garments; the concept of adaptation also abolishes trite notions of fashion as pastiche or bricolage, arguing for as a way to look at the many variations and re-contextualisations of garments historically and cross-culturally.

That's a rap : the making of an Australian hip hop integrated musical film

To date, the majority of films that utilise or feature hip hop music and culture, have either been in the realms of documentary, or in ‘show musicals’ (where the film musical’s device of characters’ bursting into song, is justified by the narrative of a pursuit of a career in the entertainment industry). Thus, most films that feature hip hop expression have in some way been tied to the subject of hip hop. A research interest and enthusiasm was developed for utilising hip hop expression in film in a new way, which would extend the narrative possibilities of hip hop film to wider topics and themes. The creation of the thesis film Out of My Cloud, and the writing of this accompanying exegesis, investigates a research concern of the potential for the use of hip hop expression in an ‘integrated musical’ film (where characters’ break into song without conceit or explanation). Context and rationale for Out of My Cloud (an Australian hip hop ‘integrated musical’ film) is provided in this writing. It is argued that hip hop is particularly suitable for use in a modern narrative film, and particularly in an ‘integrated musical’ film, due to its: current vibrancy and popularity, rap (vocal element of hip hop) music’s focus on lyrical message and meaning, and rap’s use as an everyday, non-performative method of communication. It is also argued that Australian hip hop deserves greater representation in film and literature due to: its current popularity, and its nature as a unique and distinct form of hip hop. To date, representation of Australian hip hop in film and television has almost solely been restricted to the documentary form. Out of My Cloud borrows from elements of social realist cinema such as: contrasts with mainstream cinema, an exploration/recognition of the relationship between environment and development of character, use of non-actors, location-shooting, a political intent of the filmmaker, displaying sympathy for an underclass, representation of underrepresented character types and topics, and a loose narrative structure that does not offer solid resolution. A case is made that it may be appropriate to marry elements of social realist film with hip hop expression due to common characteristics, such as: representation of marginalised or underrepresented groups and issues in society, political objectives of the artist/s, and sympathy for an underclass. In developing and producing Out of My Cloud, a specific method of working with, and filming actor improvisation was developed. This method was informed by improvisation and associated camera techniques of filmmakers such as Charlie Chaplin, Mike Leigh, Khoa Do, Dogme 95 filmmakers, and Lars von Trier (post-Dogme 95). A review of techniques used by these filmmakers is provided in this writing, as well as the impact it has made on my approach. The method utilised in Out of My Cloud was most influenced by Khoa Do’s technique of guiding actors to improvise fairly loosely, but with a predetermined endpoint in mind. A variation of this technique was developed for use in Out of My Cloud, which involved filming with two cameras to allow edits from multiple angles. Specific processes for creating Out of My Cloud are described and explained in this writing. Particular attention is given to the approaches regarding the story elements and the music elements. Various significant aspects of the process are referred to including the filming and recording of live musical performances, the recording of ‘freestyle’ performances (lyrics composed and performed spontaneously) and the creation of a scored musical scene involving a vocal performance without regular timing or rhythm. The documentation of processes in this writing serve to make the successful elements of this film transferable and replicable to other practitioners in the field, whilst flagging missteps to allow fellow practitioners to avoid similar missteps in future projects. While Out of My Cloud is not without its shortcomings as a short film work (for example in the areas of story and camerawork) it provides a significant contribution to the field as a working example of how hip hop may be utilised in an ‘integrated musical’ film, as well as being a rare example of a narrative film that features Australian hip hop. This film and the accompanying exegesis provide insights that contribute to an understanding of techniques, theories and knowledge in the field of filmmaking practice.

Resonance : a music director’s theomusicological study of ‘praise’ and ‘glory’ in a selection of four liturgical music excerpts

Some of my most powerful spiritual experiences have come from the splendorous and sublime sounding hymns performed by a choir and church organ at the traditional Anglican church I’ve attended since I was very young. In the later stage of my life, my pursuit of education in the field of engineering caused me to move to Australia where I regularly attended a contemporary evangelical church and subsequently became a music director in the faith community. This environmental and cultural shift altered my perception and musical experiences of Christian music and led me to enquire about the relationship between Christian liturgy and church music. Throughout history church musicians and composers have synthesised the theological, congregational, cultural and musical aspects of church liturgy. Many great composers have taken into account the conditions surrounding the process of sacred composition and arrangement of music to enhance the experience of religious ecstasy – they sought resonances with Christian values and beliefs to draw congregational participation into the light of praising and glorifying God. As a music director in an evangelical church this aspiration has become one I share. I hope to identify and define the qualities of these resonances that have been successful and apply them to my own practice. Introduction and Structure of the Thesis In this study I will examine four purposively selected excerpts of Christian church vocal music combining theomusicological and semiotic analysis to help identify guidelines that might be useful in my practice as a church music director. The four musical excerpts have been selected based upon their sustained musical and theological impact over time, and their ability to affect ecstatic responses from congregations. This thesis documents a personal journey through analysis of music and uses a context that draws upon ethno-musicological, theological and semiotic tools that lead to a preliminary framework and principles which can then be applied to the identified qualities of resonance in church music today. The thesis is comprised of four parts. Part 1 presents a literature study on the relationship between sacred music, the effects of religious ecstasy and the Christian church. Multiple lenses on this phenomenon are drawn from the viewpoints of prominent western church historians, Biblical theologians, and philosophers. The literature study continues in Part 2, where the role of embodiment is examined from the current perspective of cognitive learning environments. This study offers a platform for a critical reflection on two distinctive musical liturgical systems that have treated differently the notion of embodied understanding amidst a shifting church paradigm. This allows an in-depth theological and philosophical understanding of the liturgical conditions around sacred music-making that relates to the monistic and dualistic body/mind. Part 3 involves undertaking a theomusicological methodology that utilises creative case studies of four purposively selected spiritual pieces. A semiotic study focuses on specific sections of sacred vocal works that express the notions of ‘praise’ and ‘glorification’, particularly in relation to these effects,which combine an analysis of theological perspectives around religious ecstasy and particular spiritual themes. Part 4 presents the critiques and findings gathered from the study that incorporate theoretical and technological means to analyse the purposive selected musical artefact, particularly with the sonic narratives expressing notions of ‘Praise' and 'Glory’. The musical findings are further discussed in relation to the notion of resonance, and then a conceptual framework for the role of contemporary musicdirector is proposed. The musical and Christian terminologies used in the thesis are explained in the glossary, and the appendices includes tables illustrating the musical findings, conducted surveys, written musical analyses and audio examples of selected sacred pieces available on the enclosed compact disc.

Gimmelife : listening for dialogic voices in the email self-narratives of gifted young adolescents

The art of listening for voices within narrative research is a positive endeavour that has specific value within research design and subsequent approaches to analysis. This paper details an investigation into the dialogic nature of voices among gifted young adolescents who engaged in the co-construction of email-generated self-narratives. Data are drawn from a study involving ten adolescents, aged between ten and fourteen years, diagnosed as gifted according to Australian guidelines. Individual participants were asked to produce self-managed journal entries written and sent as asynchronous emails to the researcher who was the sole recipient and respondent. Within this approach, specific techniques of listening were used to examine a series of multi-vocal narratives generated over a period of six months. This paper proposes that an adaptation of the everyday convenience of email with the traditional journal format as a self-report mechanism creates a synergy that fosters self-disclosure. Individual excerpts are presented to show that the harnessing of personal narratives within an email context has potential to yield valuable insights into the emotions, personal realities and experiences of gifted young adolescents. Furthermore, the co-construction of self-expressive and explanatory narratives supported by a facilitative adult listener appeared to promote healthy self-awareness amongst participants. This paper contributes to narrative exploration in two distinct ways: first, in using online methods for gaining access to the everyday, emotional realities of participants; and, second, in demonstrating the value of listening as a narrative technique for uncovering layers of voices across a body of texts produced over time. These methods represent an innovative attempt to move beyond face-to-face approaches and away from a focus on content and coding techniques that might oversimplify complex emotions.

Choreographic approaches to music composition for a new musical interface : the eMic

Gesture in performance is widely acknowledged in the literature as an important element in making a performance expressive and meaningful. The body has been shown to play an important role in the production and perception of vocal performance in particular. This paper is interested in the role of gesture in creative works that seek to extend vocal performance via technology. A creative work for vocal performer, laptop computer and a Human Computer Interface called the eMic (Extended Microphone Stand Interface controller) is presented as a case study, to explore the relationships between movement, voice production, and musical expression. The eMic is an interface for live vocal performance that allows the singers’ gestures and interactions with a sensor based microphone stand to be captured and mapped to musical parameters. The creative work discussed in this paper presents a new compositional approach for the eMic by working with movement as a starting point for the composition and thus using choreographed gesture as the basis for musical structures. By foregrounding the body and movement in the creative process, the aim is to create a more visually engaging performance where the performer is able to more effectively use the body to express their musical objectives.

“They’re lunatics on the road” : Exploring the normative influences of parents, friends, and police on young novices’ risky driving decisions

Purpose: Young novice drivers experience significantly greater risk of being injured or killed in car crashes than older more experienced drivers. This research utilised a qualitative approach guided by the framework of Akers’ social learning theory. It explored young novice drivers’ perspectives on risky driving including rewards and punishments expected from and administered by parents, friends, and police, imitation of parents’ and friends’ driving, and advantages and disadvantages of risky driving. Methods: Twenty-one young drivers (12 females, 9 males) aged 16–25 years (M = 17.71 years, SD = 2.15) with a Learner (n = 11) or Provisional (n = 10) driver licence participated in individual or small group interviews. Findings and conclusions: Content analysis supported four themes: (1) rewards and (2) punishments for risky driving, and the influence of (3) parents and (4) friends. The young novice drivers differed in their vulnerability to the negative influences of friends and parents, with some novices advising they were able to resist risky normative influences whilst others felt they could not. The authority of the police as enforcers of road rules was either accepted and respected or seen as being used to persecute young novices. These findings suggest that road safety interventions should consider the normative influence of parents and friends on the risky and safe behaviour of young novices. Police were also seen as influential upon behaviour. Future research should explore the complicated relationship between parents, friends, the police, young novices, and their risky driving behaviour.

The pomegranate cycle : reconfiguring opera through performance, technology & composition

The Pomegranate Cycle is a practice-led enquiry consisting of a creative work and an exegesis. This project investigates the potential of self-directed, technologically mediated composition as a means of reconfiguring gender stereotypes within the operatic tradition. This practice confronts two primary stereotypes: the positioning of female performing bodies within narratives of violence and the absence of women from authorial roles that construct and regulate the operatic tradition. The Pomegranate Cycle redresses these stereotypes by presenting a new narrative trajectory of healing for its central character, and by placing the singer inside the role of composer and producer. During the twentieth and early twenty-first century, operatic and classical music institutions have resisted incorporating works of living composers into their repertory. Consequently, the canon’s historic representations of gender remain unchallenged. Historically and contemporarily, men have almost exclusively occupied the roles of composer, conductor, director and critic, and therefore men have regulated the pedagogy, performance practices, repertoire and organisations that sustain classical music. In this landscape, women are singers, and few have the means to challenge the constructions of gender they are asked to reproduce. The Pomegranate Cycle uses recording technologies as the means of driving change because these technologies have already challenged the regulation of the classical tradition by changing people’s modes of accessing, creating and interacting with music. Building on the work of artists including Phillips and van Veen, Robert Ashley and Diamanda Galas, The Pomegranate Cycle seeks to broaden the definition of what opera can be. This work examines the ways in which the operatic tradition can be hybridised with contemporary musical forms such as ambient electronica, glitch, spoken word and concrete sounds as a way of bringing the form into dialogue with contemporary music cultures. The ultilisation of other sound cultures within the context of opera enables women’s voices and stories to be presented in new ways, while also providing a point of friction with opera’s traditional storytelling devices. The Pomegranate Cycle simulates aesthetics associated with Western art music genres by drawing on contemporary recording techniques, virtual instruments and sound-processing plug-ins. Through such simulations, the work disrupts the way virtuosic human craft has been used to generate authenticity and regulate access to the institutions that protect and produce Western art music. The DIY approach to production, recording, composition and performance of The Pomegranate Cycle demonstrates that an opera can be realised by a single person. Access to the broader institutions which regulate the tradition are not necessary. In short, The Pomegranate Cycle establishes that a singer can be more than a voice and a performing body. She can be her own multimedia storyteller. Her audience can be anywhere.