Asr for Automatic Directory Assistance: the Smada Project
نویسندگان
چکیده
In this paper we summarise the state-of-the-art for automatic speech recognition in automated Directory Assistance at the start of the 5th Framework project SMADA. Details are given about robust acoustic features for use in Distributed Speech Recognition, especially with respect to noise suppression. Then an overview is given of the confidence measures which are in use today, and their similarities and differences. Finally, work aimed at automatic update of acoustic models and automatic inference of language models is sketched that is becoming possible thanks to the very large amounts of data that can be recorded in operational services. In addition to summarising the state-of-the-art the paper also indicates the lines along which the research in SMADA will develop.
منابع مشابه
Introduction to the IST-HLT project speech-driven multimodal automatic directory assistance (SMADA)
This paper introduces the IST-HLT project SMADA. This project started in January 2000 and it will run for three years. We present information on the topics to be addressed in the project; in addition some preliminary results are given. Information is given on functional specifications and technical and Human Factors evaluations of Automatic Directory Assistance systems in four European countrie...
متن کاملBusiness listings in automatic directory assistance
So far most attempts to automate Directory Assistance services focused on private listings, because it is not known precisely how callers will refer to a business listings. The research de scribed in this paper, carried out in the SMADA project, tries to fill this gap. The aim of the research is to model the expres sions people use when referring to a business listing by means of rules, in or...
متن کاملDynamic scheduling of decoding processes for directory assistance
This paper deals with the difficult task of recognition of a large vocabulary of proper names in a directory assistance application. Research on the European project SMADA has shown that there is a need of an elaborate and effective decision strategy that limits the risk of false automation. This paper proposes a new strategy which integrates, as well as a general decoder, a set of decoders spe...
متن کاملAccumulated kullback divergence for analysis of ASR performance in the presence of noise
In this paper, the accumulated Kullback divergence (AKD) is used to analyze ASR performance deterioration due to the presence of background noise. The AKD represents a distance between the feature value distribution observed during training and the distri bution of the observations in the noisy test condition for each in dividual feature vector component. In our experiments the AKD summed ove...
متن کاملAutomated directory assistance system - from theory to practice
The automated directory assistance system (ADAS) is traditionally formulated as an automatic speech recognition (ASR) problem. Recently, it has been formulated as a voice search problem, where a spoken utterance is firstly converted into text, which in turn is used to search for the listing. In this paper, we focus on the design and development of the utterance-to-listing component of ADAS. We ...
متن کامل