First Insight into the Processing of the Language Consulting Center Data

In this paper, we describe the initial stages of the project “Access to a Linguistically Structured Database of Enquiries from the Language Consulting Center”. This project is attempting to provide an improved access to the large archives of mainly telephone conversations collected continuously by the Institute of the Czech Language. The main goal is to open up the unique Czech data acquired from the queries to the Language Consulting Center and to build the semi-automatic system that will facilitate searching and categorizing of these queries. For this purpose, the Automatic Speech Recognizer (ASR) and the language processing methods are being designed. The vocabulary used in such queries contains many unusual words unlike the common speech (e.g. linguistic terms). In order to train the ASR system, it is necessary to manually transcribe a large amount of speech data, identify the appropriate vocabulary, and obtain relevant text for language modeling purposes. In this paper, the proposed telephone system for recording the new data and the baseline speech recognition on these data is described. The first experiments with the topic detection on these data aimed at discovering what can be found in them and also how to preprocess them is also described.

[1]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[2]  Ian R. Lane,et al.  Unsupervised vocabulary selection for real-time speech recognition of lectures , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[4]  Jan Zelinka,et al.  Neural-Network-Based Spectrum Processing for Speech Recognition and Speaker Verification , 2015, SLSP.

[5]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[6]  Petr Sojka,et al.  Software Framework for Topic Modelling with Large Corpora , 2010 .

[7]  Jan Svec,et al.  Hierarchical discriminative model for spoken language understanding , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Mi Lu,et al.  Comparisons and Selections of Features and Classifiers for Short Text Classification , 2017 .

[9]  Leif Madsen,et al.  Asterisk - The Definitive Guide: The Future of Telephony is Now: Covers Asterisk 1.8 (3. ed.) , 2011 .

[10]  Ludek Müller,et al.  Automatic Lemmatizer Construction with Focus on OOV Words Lemmatization , 2005, TSD.

[11]  Jakub Kanis,et al.  Comparison of Different Lemmatization Approaches through the Means of Information Retrieval Performance , 2010, TSD.

[12]  Ludek Müller,et al.  Benefit of Proper Language Processing for Czech Speech Retrieval in the CL-SR Task at CLEF 2006 , 2006, CLEF.

[13]  Jan Svec,et al.  System for fast lexical and phonetic spoken term detection in a Czech cultural heritage archive , 2011, EURASIP J. Audio Speech Music. Process..

[14]  Yun Zhu,et al.  Support vector machines and Word2vec for text classification with semantic features , 2015, 2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC).

[15]  Jan Cernocký,et al.  Recording of Czech and Slovak Telephone Databases within SpeechDat-E , 1999, TSD.

[16]  Pavel Ircing,et al.  What Can and Cannot Be Found in Czech Spontaneous Speech Using Document-Oriented IR Methods - UWB at CLEF 2007 CL-SR Track , 2007, CLEF.

[17]  Jan Hajic,et al.  Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition , 2014, ACL.

[18]  P. Paatero,et al.  Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values† , 1994 .