International speakers visit QLD

The HLA Regional Committee QLD invited Tony McSéan and Carol Lefebvre to head north following the 2007 Information Online Conference to present to Queensland librarians. Jenny Hall and Jill McTaggart, from the University of Queensland Library Service, report on two speakers who presented on very different but equally important topics.

Speaker identification using higher order spectral phase features and their effectiveness vis-a-vis Mel-Cepstral features

The effectiveness of higher-order spectral (HOS) phase features in speaker recognition is investigated by comparison with Mel Cepstral features on the same speech data. HOS phase features retain phase information from the Fourier spectrum unlikeMel–frequency Cepstral coefficients (MFCC). Gaussian mixture models are constructed from Mel– Cepstral features and HOS features, respectively, for the same data from various speakers in the Switchboard telephone Speech Corpus. Feature clusters, model parameters and classification performance are analyzed. HOS phase features on their own provide a correct identification rate of about 97% on the chosen subset of the corpus. This is the same level of accuracy as provided by MFCCs. Cluster plots and model parameters are compared to show that HOS phase features can provide complementary information to better discriminate between speakers.

Art for architecture's sake?

The Architecture, Disciplinarity and the Arts symposium was organised by the Architecture. Theory, Criticism and History (ATCH) research group at the University of Queensland, run by John Macarthur and Antony Moulis, together with Andrew Leach who joined them last year and organised much of the symposium. The symposium ran for three days in a small room at the Institute of Modern Art (IMA) in Fortitude Valley, Brisbane (generously donated by director Robert Leonard), with about 40 people in attendance. Together with a long question time of an hour after every three speakers, the size of the room and the small number of people made it very different from most architecture or design conferences. The intellectual level of the symposium was high, without the speed dating aspect that one often sees at the Society of Architectural Historians, Australia and New Zealand (SAHANZ) meetings, where endless parallel sessions of short papers create an occasionally disorientating cacophony of words. The symposium was deliberately, unapologetically academic and the intimate nature of the forum made the discussion rich and collaborative, with an active audience. The title of the symposium, 'Architecture, Disciplinarity and the Arts', reflects the connection that already exists between the art history and the architectural history community in Brisbane, with both groups regularly attending each other's functions.

Presentations in English : find your voice as a presenter

With estimates of more than thirty million given each day, presentations have become an integral part of modern society. They can signify the difference between gaining or losing a job, or being successful or unsuccessful at university and a future career. Presentations in English, combining a 128-page book and DVD, is an innovative and complete course aimed specifically at non-native speakers of English.

Creative Industries

We are experiencing a period of profound social and economic transformation. This is a shift from an industrial economy to a knowledge economy (or a “creative economy”; or an “economy of the imagination”.) This new, emerging economic system is fundamentally organised around people (not machines or buildings); and around place. We heard Richard Florida argue that creative, talented people won’t go to where the job is, but vice versa, the job will come to them. So according to Florida, where we live is becoming the primary factor in global economic development. (Incidentally, it is worth contrasting this idea with the alternative proposition - put by speakers at this Forum - of “new nomadism”, that is, that creativity is nomadic and not bound by place.)

Robust speech recognition using speech enhancement

Automatic Speech Recognition (ASR) has matured into a technology which is becoming more common in our everyday lives, and is emerging as a necessity to minimise driver distraction when operating in-car systems such as navigation and infotainment. In “noise-free” environments, word recognition performance of these systems has been shown to approach 100%, however this performance degrades rapidly as the level of background noise is increased. Speech enhancement is a popular method for making ASR systems more ro- bust. Single-channel spectral subtraction was originally designed to improve hu- man speech intelligibility and many attempts have been made to optimise this algorithm in terms of signal-based metrics such as maximised Signal-to-Noise Ratio (SNR) or minimised speech distortion. Such metrics are used to assess en- hancement performance for intelligibility not speech recognition, therefore mak- ing them sub-optimal ASR applications. This research investigates two methods for closely coupling subtractive-type enhancement algorithms with ASR: (a) a computationally-efficient Mel-filterbank noise subtraction technique based on likelihood-maximisation (LIMA), and (b) in- troducing phase spectrum information to enable spectral subtraction in the com- plex frequency domain. Likelihood-maximisation uses gradient-descent to optimise parameters of the enhancement algorithm to best fit the acoustic speech model given a word se- quence known a priori. Whilst this technique is shown to improve the ASR word accuracy performance, it is also identified to be particularly sensitive to non-noise mismatches between the training and testing data. Phase information has long been ignored in spectral subtraction as it is deemed to have little effect on human intelligibility. In this work it is shown that phase information is important in obtaining highly accurate estimates of clean speech magnitudes which are typically used in ASR feature extraction. Phase Estimation via Delay Projection is proposed based on the stationarity of sinusoidal signals, and demonstrates the potential to produce improvements in ASR word accuracy in a wide range of SNR. Throughout the dissertation, consideration is given to practical implemen- tation in vehicular environments which resulted in two novel contributions – a LIMA framework which takes advantage of the grounding procedure common to speech dialogue systems, and a resource-saving formulation of frequency-domain spectral subtraction for realisation in field-programmable gate array hardware. The techniques proposed in this dissertation were evaluated using the Aus- tralian English In-Car Speech Corpus which was collected as part of this work. This database is the first of its kind within Australia and captures real in-car speech of 50 native Australian speakers in seven driving conditions common to Australian environments.

Intellectual property : designing 4 success. Safeguarding your innovations - rights, obligations and opportunities in creating intellectual property by design

Design talks LOUDLY!!! Is a series of interactive presentations exploring issues and opportunities involving professional design. --------------- These seminars are organised by the Industrial Design Network Queensland (IDnetQLD) in coordination with the Design Institute of Australia (DIA). This event was held at the State Library of Queensland (SLQ) with invited public presentations by a panel of industry experts from the Australian Government – IP Australia. --------------- The first seminar "Intellectual Property : designing 4 success" highlighted to design professionals how the various forms of Intellectual Property interact, what protections and pitfalls exist, and how these impact upon the work and responsibilities of designers. The overlaps, gaps and in congruencies in the various IP protection systems were highlighted by the expert line-up of speakers. --------------- The underlying message is that a clear understanding of all IP types is necessary in order to gain the best advantage from IP protection and therefore eliminate potential IP ownership issues before they become a problem.

Sustainable futures : the new design landscape

Design talks LOUDLY!!! Is a series of interactive presentations exploring issues and opportunities involving professional design. These seminars are organised by the Industrial Design Network Queensland (IDnetQLD) in coordination with the Design Institute of Australia (DIA). This event was held at the State Library of Queensland (SLQ) with invited public presentations by a panel of industry experts from Brisbane City Council, Sims Recycling Solutions and BEST Futures. The second seminar "Sustainable Futures: The New Design Landscape" highlighted to design professionals the positive effect the design industry can achieve in moving towards a sustainable future. A series of presentations from specialist speakers outlined the new generation of design and how design can surf the sustainable shift. A product’s journey from concept to creation and a life beyond was presented and discussed as a basis of designing for sustainability. The intent of the seminar was to inject a brand new sense of purpose into the design world through inspiring designers to find solutions which move forward into this new sustainable landscape.

Green cane impact on sugar processing : ISSCT process workshop 2008

The ISSCT Process Section workshop held in Réunion 20–23 October 2008 was attended by 51 delegates from 10 countries. The theme was Green cane impact on sugar processing. The workshop provided a valuable and timely opportunity to review and discuss the impact on factory operations and performance from a green cane supply that could include significant levels of trash. It was particularly relevant to those mills that were considering options to boost their biomass intake for increased co-generation capacity. Several of the speakers related their experiences with processing ‘whole of crop’ cane supplies through the factory. Speakers detailed the problems and increased losses that were incurred when processing cane with high trash levels. The consensus of the delegates was that the best scenario would involve a cane-cleaning plant at the factory so that only clean cane would be processed through the factory. The forum recommended that more research was required to address the issues of increased impurities in the process streams associated with high trash levels. Site visits to the two factories and a cane-delivery station were arranged as part of the workshop.

Speech recognition using ad-hoc microphone arrays

While close talking microphones give the best signal quality and produce the highest accuracy from current Automatic Speech Recognition (ASR) systems, the speech signal enhanced by microphone array has been shown to be an effective alternative in a noisy environment. The use of microphone arrays in contrast to close talking microphones alleviates the feeling of discomfort and distraction to the user. For this reason, microphone arrays are popular and have been used in a wide range of applications such as teleconferencing, hearing aids, speaker tracking, and as the front-end to speech recognition systems. With advances in sensor and sensor network technology, there is considerable potential for applications that employ ad-hoc networks of microphone-equipped devices collaboratively as a virtual microphone array. By allowing such devices to be distributed throughout the users’ environment, the microphone positions are no longer constrained to traditional fixed geometrical arrangements. This flexibility in the means of data acquisition allows different audio scenes to be captured to give a complete picture of the working environment. In such ad-hoc deployment of microphone sensors, however, the lack of information about the location of devices and active speakers poses technical challenges for array signal processing algorithms which must be addressed to allow deployment in real-world applications. While not an ad-hoc sensor network, conditions approaching this have in effect been imposed in recent National Institute of Standards and Technology (NIST) ASR evaluations on distant microphone recordings of meetings. The NIST evaluation data comes from multiple sites, each with different and often loosely specified distant microphone configurations. This research investigates how microphone array methods can be applied for ad-hoc microphone arrays. A particular focus is on devising methods that are robust to unknown microphone placements in order to improve the overall speech quality and recognition performance provided by the beamforming algorithms. In ad-hoc situations, microphone positions and likely source locations are not known and beamforming must be achieved blindly. There are two general approaches that can be employed to blindly estimate the steering vector for beamforming. The first is direct estimation without regard to the microphone and source locations. An alternative approach is instead to first determine the unknown microphone positions through array calibration methods and then to use the traditional geometrical formulation for the steering vector. Following these two major approaches investigated in this thesis, a novel clustered approach which includes clustering the microphones and selecting the clusters based on their proximity to the speaker is proposed. Novel experiments are conducted to demonstrate that the proposed method to automatically select clusters of microphones (ie, a subarray), closely located both to each other and to the desired speech source, may in fact provide a more robust speech enhancement and recognition than the full array could.

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.