Dieter Geller

Improvements in connected digit recognition using linear discriminant analysis and mixture densities

Four methods were used to reduce the error rate of a continuous-density hidden Markov-model-based speech recognizer on the TI/NIST connected-digits recognition task. Energy thresholding sets a lower limit on the energy in each frequency channel to suppress spurious distortion accumulation caused by random noise. This led to an improvement in error rate by 15%. Spectrum normalization was used to compensate for across-speaker variations, resulting in an additional improvement by 20%. The acoustic resolution was increased up to 32 component densities per mixture. Each doubling of the number of component densities yielded a reduction in error rate by roughly 20%. Linear discriminant analysis was used for improved feature selection. A single class-independent transformation matrix was applied to a large input vector consisting of several adjacent frames, resulting in an improvement by 20% for high acoustic resolution. The final string error rate was 0.84%.<<ETX>>

The Philips Research system for continuous-speech recognition

This paper gives an overview of the Philips Research system for continuous-speech recognition. The recognition architecture is based on an integrated statistical approach. The system has been successfully applied to various tasks in American English and German, ranging from small vocabulary tasks to very large vocabulary tasks and from recognition only to speech understanding. Here, we concentrate on phoneme-based continuous-speech recognition for large vocabulary recognition as used for dictation, which covers a significant part of our research work on speech recognition. We describe this task and report on experimental results. In order to allow a comparison with the performance of other systems, a section with an evaluation on the standard North American Business news (NAB2) task (dictation of American English newspaper text) is supplied.

Continuous speech dictation: from theory to practice

This paper gives an overview of the Philips research system for phoneme-based, large-vocabulary, continuousspeech recognition. The system has been successfully applied to various tasks in the German and (American) English languages, ranging from small vocabulary tasks to very large vocabulary tasks. Here, we concentrate on continuousspeech recognition for dictation in real applications, the dictation of legal reports and radiology reports in German. We describe this task and report on experimental results. We also describe a commercial PC-based dictation system which includes a PC implementation of our scientific recognition prototype. In order to allow for a comparison with the performance of other systems, a section with an evaluation on the standard Wall Street Journal task (dictation of American English newspaper text) is supplied. The recognition architecture is based on an integrated statistical approach. We describe the characteristic features of the system as opposed to other systems: 1. the Viterbi criterion is consistently applied both in training and testing; 2. continuous mixture densities are used without tying or smoothing; 3. time-synchronous beam search in connection with a phoneme look-ahead is applied to a tree-organized lexicon.

Speech recognition algorithms for voice control interfaces

Recognition accuracy has been the primary objective of most speech recognition research, and impressive results have been obtained, e.g. less than 0.3% word error rate on a speaker-independent digit recognition task. When it comes to real-world applications, robustness and real-time response might be more important issues. For the first requirement we review some of the work on robustness and discuss one specific technique, spectral normalization, in more detail. The requirement of real-time response has to be considered in the light of the limited hardware resources in voice control applications, which are due to the tight cost constraints. In this paper we discuss in detail one specific means to reduce the processing and memory demands: a clustering technique applied at various levels within the acoustic modelling.

Design and use of speech recognition algorithms for a mobile radio telephone

To decrease the hazards of using mobile phones while driving, voice processing provides several tools that simplify their use: echo cancellation allows comfortable hands-free conversation, feedback and user guidance by voice allow to operate the phone in eyes-busy situations, and last not least speech recognition frees from keypad data entry to operate the telephone. A comprehensive view of a device incorporating the above mentioned technologies, which has been realized as an add-on for the Philips car telephone family, will be presented. Emphasis is placed on the speech recognition algorithms. Robustness of the algorithms to changing acoustic environment was improved by estimating and subtracting the long-term spectrum. We will show that, if this operation is done recursively, it is equivalent to the high-pass filtering or RASTA (Relative Spectral Approaches) methods recently proposed in the literature.

Visualizing the beating heart: interactive direct volume rendering of high-resolution CT time series using standard PC hardware

Modern multi-slice CT (MSCT) scanners allow acquisitions of 3D data sets covering the complete heart at different phases of the cardiac cycle. This enables the physician to non-invasively study the dynamic behavior of the heart, such as wall motion artifacts. To this end an interactive 4D visualization of the heart in motion is desirable. However, the application of well-known volume rendering algorithms enforces considerable sacrifices in terms of image quality to ensure interactive frame rates, even when accelerated by standard graphics processors (GPUs). Thereby, the performance of pure CPU implementations of direct volume rendering algorithms is limited even for moderate volume sizes by both the number of required computations and the available memory bandwidth. Despite of offering higher computational performance and more memory bandwidth GPU accelerated implementations cannot provide interactive visualizations of large 4D data sets since data sets that do not fit into the onboard graphics memory are often not handled efficiently. In this paper we present a software architecture for GPU-based direct volume rendering algorithms that allows the interactive high-quality visualization of large medical time series data sets. In contrast to other work, our architecture exploits the complete memory hierarchy for high cache and bandwidth efficiency. Additionally, several data-dependent techniques are incorporated to reduce the amount of volume data to be transferred and rendered. None of these techniques sacrifices image quality in order to improve speed. By applying the method to several multi phase MSCT cardiac data sets we show that we can achieve interactive frame rates on currently available standard PC hardware.

Toward knowledge-enhanced viewing using encyclopedias and model-based segmentation

To make accurate decisions based on imaging data, radiologists must associate the viewed imaging data with the corresponding anatomical structures. Furthermore, given a disease hypothesis possible image findings which verify the hypothesis must be considered and where and how they are expressed in the viewed images. If rare anatomical variants, rare pathologies, unfamiliar protocols, or ambiguous findings are present, external knowledge sources such as medical encyclopedias are consulted. These sources are accessed using keywords typically describing anatomical structures, image findings, pathologies. In this paper we present our vision of how a patients imaging data can be automatically enhanced with anatomical knowledge as well as knowledge about image findings. On one hand, we propose the automatic annotation of the images with labels from a standard anatomical ontology. These labels are used as keywords for a medical encyclopedia such as STATdx to access anatomical descriptions, information about pathologies and image findings. On the other hand we envision encyclopedias to contain links to region- and finding-specific image processing algorithms. Then a finding is evaluated on an image by applying the respective algorithm in the associated anatomical region. Towards realization of our vision, we present our method and results of automatic annotation of anatomical structures in 3D MRI brain images. Thereby we develop a complex surface mesh model incorporating major structures of the brain and a model-based segmentation method. We demonstrate the validity by analyzing the results of several training and segmentation experiments with clinical data focusing particularly on the visual pathway.

Quantile-based classification of Alzheimer's disease, frontotemporal dementia and asymptomatic controls from SPECT data

Nuclear imaging techniques, namely single photon emission computed tomography (SPECT) and positron emission tomography (PET), are commonly used for the study of neurodegenerative diseases such as Alzheimers disease (AD) and frontotemporal dementia (FTD). Many methods have been proposed to identify different types of dementia based on SPECT and PET images. In order to cope with the low number of datasets compared to the high number of independent variables (voxels of the dataset), they either perform a dimensionality reduction prior to classification, which implies identical influence of all available datasets, or try to extract the relevant variables for the prediction, which may be affected by statistical fluctuation resulting from mislabeled data or intrinsic noise within data samples In order to overcome these limitations, this paper presents an alternative method for classification of SPECT image data of asymptomatic controls (HC), AD and FTD participants. The proposed method produces a voxel mask that weights or ignores voxels according to their relevance for classification. The algorithm is based on quantiles and is less sensitive to the non-Gaussian statistical distribution of the classes to separate, which is a very desirable in case of dementia classification. Special care is taken to assess the robustness of the proposed approach. The classification accuracy assessed with bootstrap resampling is presented and the robustness against outliers and misdiagnosed training samples is investigated and compared with a PCA-MVA based approach. As a result, the proposed approach shows comparable results with respect to robustness, but better classification accuracy than PCA-based approaches.

Efficient hardware accelerated rendering of multiple volumes by data dependent local render functions

The inspection of a patients data for diagnostics, therapy planning or therapy guidance involves an increasing number of 3D data sets, e.g. acquired by different imaging modalities, with different scanner settings or at different times. To enable viewing of the data in one consistent anatomical context fused interactive renderings of multiple 3D data sets are desirable. However, interactive fused rendering of typical medical data sets using standard computing hardware remains a challenge. In this paper we present a method to render multiple 3D data sets. By introducing local rendering functions, i.e. functions that are adapted to the complexity of the visible data contained in the different regions of a scene, we can ensure that the overall performance for fused rendering of multiple data sets depends on the actual amount of visible data. This is in contrast to other approaches where the performance depends mainly on the number of rendered data sets. We integrate the method into a streaming rendering architecture with brick-based data representations of the volume data. This enables efficient handling of data sets that do not fit into the graphics board memory and a good utilization of the texture caches. Furthermore, transfer and rendering of volume data that does not contribute to the final image can be avoided. We illustrate the benefits of our method by experiments with clinical data.