PDF inaccessibility is an ongoing challenge that hinders individuals with visual impairments from reading and navigating PDFs using screen readers.This paper presents a step-by-step process for both novice and experienced users to create accessible PDF documents, including an approach for creating alternative text for mathematical formulas without expert knowledge.In a study involving nineteen participants, we evaluated our prototype PAVE 2.0 by comparing it against Adobe Acrobat Pro, the existing standard for remediating PDFs.Our study shows that experienced users improved their tagging scores from 42.0% to 80.1%, and novice users from 39.2% to 75.2% with PAVE 2.0.Overall, fifteen participants stated that they would prefer to use PAVE 2.0 in the future, and all participants would recommend it for novice users.Our work demonstrates PAVE 2.0's potential for increasing PDF accessibility for people with visual impairments and highlights remaining challenges. CCS Concepts• Human

In this paper a framework for a novel kind of applications called Augmented-Mobile-Tagging (AMT) applications is presented. AMT applications augment classic Mobile Tagging applications with information from existing Location Based Services (LBS) in a seamless way. This leads to very powerful mobile applications without loosing the efficiency, intuitiveness and robustness of the visual tagging application. We have implemented two AMT applications based on this concept and are currently running two field trials, one a campus information system on the university campus and another, called LocalTagging, running in the town and surroundings of Winterthur.

The issue of a priori threshold setting in speaker verification is a key problem for field applications. In the context of the Caller Verification in Banking and Telecommunications (CAVE) project, we compared several methods for estimating speaker-independent and speaker-dependent decision thresholds. Relevant parameters are estimated from development data only, i.e. without resorting to additional client data. The various approaches are tested on the Dutch SESP database.

This paper summarizes the main results from the Speaker Verification (SV) research pursued so far in the CAVE project. Different state-of-the art SV algorithms were implemented in a common HMM framework and compared on two databases : YOHO (office environment speech) and SESP (telephone speech). This paper is concerned with the different design issues for LR-HMM-based SV algorithms which emerged from our investigations and which led to our current SV system, which delivers Equal Error Rates below 0.5 % on a very realistic telephone speech database. 1. CONTEXT The CAVE project (CAller VErification in Banking and Telecommunications) is a 2 year project supported by the Language Engineering Sector of the Telematics Applications Programme of the European Union, and for the Swiss partners by the Office F'ed'eral de l'Education et de la Science (Bundesamt fur Bildung und Wissenschaft). The partners are Dutch PTT Telecom, KUN, KTH, ENST, UBILAB, IDIAP, VOCALIS, TELIA and Swiss Telecom PTT. ...

The paper compares a newly proposed hybrid connectionist-SCHMM approach [Hutter and Pfister 1994] with other hybrid approaches. In the new approach a multilayer perceptron (MLP) replaces the conventional codebooks of semi-continuous HMMs. The MLP is therefore trained on so-called basic elements (phones and phone parts) in such a way that the outputs of the network estimate the a posteriori probabilities of these elements, given a context of input vectors. These a posteriori estimates are converted into scaled likelihoods, which are then used as observation probabilities in the framework of classical SCHMMs. The remaining parameters of the SCHMMs are trained with the well-known Baum-Welch algorithm using the estimated likelihoods of the MLP. This approach compared favorably with other proposed hybrid systems and classical approaches on an isolated German digit recognition task over telephone lines. It exhibited the highest recognition rate of all systems, followed by an approach using LVQ3 optimization of the codebook.