Evaluation of multi-sensory feedback on the usability of a virtual assembly environment

Virtual assembly environment (VAE) technology has the great potential for benefiting the manufacturing applications in industry. Usability is an important aspect of the VAE. This paper presents the usability evaluation of a developed multi-sensory VAE. The evaluation is conducted by using its three attributes: (a) efficiency of use; (b) user satisfaction; and (c) reliability. These are addressed by using task completion times (TCTs), questionnaires, and human performance error rates (HPERs), respectively. A peg-in-a-hole and a Sener electronic box assembly task have been used to perform the experiments, using sixteen participants. The outcomes showed that the introduction of 3D auditory and/or visual feedback could improve the usability. They also indicated that the integrated feedback (visual plus auditory) offered better usability than either feedback used in isolation. Most participants preferred the integrated feedback to either feedback (visual or auditory) or no feedback. The participants' comments demonstrated that nonrealistic or inappropriate feedback had negative effects on the usability, and easily made them feel frustrated. The possible reasons behind the outcomes are also analysed. © 2007 ACADEMY PUBLISHER.

Language model combination and adaptation using weighted finite state transducers

In speech recognition systems language model (LMs) are often constructed by training and combining multiple n-gram models. They can be either used to represent different genres or tasks found in diverse text sources, or capture stochastic properties of different linguistic symbol sequences, for example, syllables and words. Unsupervised LM adaptation may also be used to further improve robustness to varying styles or tasks. When using these techniques, extensive software changes are often required. In this paper an alternative and more general approach based on weighted finite state transducers (WFSTs) is investigated for LM combination and adaptation. As it is entirely based on well-defined WFST operations, minimum change to decoding tools is needed. A wide range of LM combination configurations can be flexibly supported. An efficient on-the-fly WFST decoding algorithm is also proposed. Significant error rate gains of 7.3% relative were obtained on a state-of-the-art broadcast audio recognition task using a history dependently adapted multi-level LM modelling both syllable and word sequences. ©2010 IEEE.

Multi-channel signal separation

The separation of independent sources from mixed observed data is a fundamental and challenging problem. In many practical situations, observations may be modelled as linear mixtures of a number of source signals, i.e. a linear multi-input multi-output system. A typical example is speech recordings made in an acoustic environment in the presence of background noise and/or competing speakers. Other examples include EEG signals, passive sonar applications and cross-talk in data communications. In this paper, we propose iterative algorithms to solve the n × n linear time invariant system under two different constraints. Some existing solutions for 2 × 2 systems are reviewed and compared.

Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. In normal cross adaptation it is assumed that useful diversity among systems exists only at acoustic level. However, complimentary features among complex LVCSR systems also manifest themselves in other layers of modelling hierarchy, e.g., subword and word level. It is thus interesting to also cross adapt language models (LM) to capture them. In this paper cross adaptation of multi-level LMs modelling both syllable and word sequences was investigated to improve LVCSR system combination. Significant error rate gains up to 6.7% rel. were obtained over ROVER and acoustic model only cross adaptation when combining 13 Chinese LVCSR subsystems used in the 2010 DARPA GALE evaluation. © 2010 ISCA.

Improving LVCSR system combination using neural network language model cross adaptation

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. The standard approach involves only cross adapting acoustic models. To fully exploit the complimentary features among sub-systems, language model (LM) cross adaptation techniques can be used. Previous research on multi-level n-gram LM cross adaptation is extended to further include the cross adaptation of neural network LMs in this paper. Using this improved LM cross adaptation framework, significant error rate gains of 4.0%-7.1% relative were obtained over acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. Copyright © 2011 ISCA.

A preliminary study of a new multi-objective optimization algorithm

This paper presents a preliminary study which describes and evaluates a multi-objective (MO) version of a recently created single objective (SO) optimization algorithm called the "Alliance Algorithm" (AA). The algorithm is based on the metaphorical idea that several tribes, with certain skills and resource needs, try to conquer an environment for their survival and to ally together to improve the likelihood of conquest. The AA has given promising results in several fields to which has been applied, thus the development of a MO variant (MOAA) is a natural extension. Here the MOAA's performance is compared with two well-known MO algorithms: NSGA-II and SPEA-2. The performance measures chosen for this study are the convergence and diversity metrics. The benchmark functions chosen for the comparison are from the ZDT and OKA families and the main classical MO problems. The results show that the three algorithms have similar overall performance. Thus, it is not possible to identify a best algorithm for all the problems; the three algorithms show a certain complementarity because they offer superior performance for different classes of problems. © 2012 IEEE.

Demonstration of Improved Passive UHF RFID Coverage using Optically-Fed Distributed Multi-Antenna System

Optically-fed distributed antenna system (DAS) technology is combined with passive ultra high frequency (UHF) radio frequency identification (RFID). It is shown that RFID signals can be carried on directly modulated radio over fiber links without impacting their performance. It is also shown that a multi-antenna DAS can greatly reduce the number of nulls experienced by RFID in a complex radio environment, increasing the likelihood of successful tag detection. Consequently, optimization of the DAS reduces nulls further. We demonstrate RFID tag reading using a three antenna DAS system over a 20mx6m area, limited by building constraints, where 100% of the test points can be successfully read. The detected signal strength from the tag is also observed to increase by an average of approximately 10dB compared with a conventional switched multi-antenna RFID system. This improvement is achieved at +31dBm equivalent isotropically radiated power (EIRP) from all three antenna units (AUs).

Syllable language models for Mandarin speech recognition: exploiting character language models.

Mandarin Chinese is based on characters which are syllabic in nature and morphological in meaning. All spoken languages have syllabiotactic rules which govern the construction of syllables and their allowed sequences. These constraints are not as restrictive as those learned from word sequences, but they can provide additional useful linguistic information. Hence, it is possible to improve speech recognition performance by appropriately combining these two types of constraints. For the Chinese language considered in this paper, character level language models (LMs) can be used as a first level approximation to allowed syllable sequences. To test this idea, word and character level n-gram LMs were trained on 2.8 billion words (equivalent to 4.3 billion characters) of texts from a wide collection of text sources. Both hypothesis and model based combination techniques were investigated to combine word and character level LMs. Significant character error rate reductions up to 7.3% relative were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using an adapted history dependent multi-level LM that performs a log-linearly combination of character and word level LMs. This supports the hypothesis that character or syllable sequence models are useful for improving Mandarin speech recognition performance.

The design of multi-element airfoils through multi-objective optimization techniques

This paper presents the development and the application of a multi-objective optimization framework for the design of two-dimensional multi-element high-lift airfoils. An innovative and efficient optimization algorithm, namely Multi-Objective Tabu Search (MOTS), has been selected as core of the framework. The flow-field around the multi-element configuration is simulated using the commercial computational fluid dynamics (cfd) suite Ansys cfx. Elements shape and deployment settings have been considered as design variables in the optimization of the Garteur A310 airfoil, as presented here. A validation and verification process of the cfd simulation for the Garteur airfoil is performed using available wind tunnel data. Two design examples are presented in this study: a single-point optimization aiming at concurrently increasing the lift and drag performance of the test case at a fixed angle of attack and a multi-point optimization. The latter aims at introducing operational robustness and off-design performance into the design process. Finally, the performance of the MOTS algorithm is assessed by comparison with the leading NSGA-II (Non-dominated Sorting Genetic Algorithm) optimization strategy. An equivalent framework developed by the authors within the industrial sponsor environment is used for the comparison. To eliminate cfd solver dependencies three optimum solutions from the Pareto optimal set have been cross-validated. As a result of this study MOTS has been demonstrated to be an efficient and effective algorithm for aerodynamic optimizations. Copyright © 2012 Tech Science Press.

Multi-Modal Image Retrieval from Construction Databases and Model-Based Systems

In the modern and dynamic construction environment it is important to access information in a fast and efficient manner in order to improve the decision making processes for construction managers. This capability is, in most cases, straightforward with today’s technologies for data types with an inherent structure that resides primarily on established database structures like estimating and scheduling software. However, previous research has demonstrated that a significant percentage of construction data is stored in semi-structured or unstructured data formats (text, images, etc.) and that manually locating and identifying such data is a very hard and time-consuming task. This paper focuses on construction site image data and presents a novel image retrieval model that interfaces with established construction data management structures. This model is designed to retrieve images from related objects in project models or construction databases using location, date, and material information (extracted from the image content with pattern recognition techniques).

Transcription of multi-genre media archives using out-of-domain data

We describe our work on developing a speech recognition system for multi-genre media archives. The high diversity of the data makes this a challenging recognition task, which may benefit from systems trained on a combination of in-domain and out-of-domain data. Working with tandem HMMs, we present Multi-level Adaptive Networks (MLAN), a novel technique for incorporating information from out-of-domain posterior features using deep neural networks. We show that it provides a substantial reduction in WER over other systems, with relative WER reductions of 15% over a PLP baseline, 9% over in-domain tandem features and 8% over the best out-of-domain tandem features. © 2012 IEEE.

Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple sub-systems that may even be developed at different sites. Cross system adaptation, in which model adaptation is performed using the outputs from another sub-system, can be used as an alternative to hypothesis level combination schemes such as ROVER. Normally cross adaptation is only performed on the acoustic models. However, there are many other levels in LVCSR systems' modelling hierarchy where complimentary features may be exploited, for example, the sub-word and the word level, to further improve cross adaptation based system combination. It is thus interesting to also cross adapt language models (LMs) to capture these additional useful features. In this paper cross adaptation is applied to three forms of language models, a multi-level LM that models both syllable and word sequences, a word level neural network LM, and the linear combination of the two. Significant error rate reductions of 4.0-7.1% relative were obtained over ROVER and acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. © 2012 Elsevier Ltd. All rights reserved.