Topic Segmentation Research Articles

Automatic multimedia indexing: combining audio, speech, and visual information to index broadcast news

This paper describes an indexing system that automatically creates metadata for multimedia broadcast news content by integrating audio, speech, and visual information. The automatic multimedia content indexing system includes acoustic segmentation (AS), automatic speech recognition (ASR), topic segmentation (TS), and video indexing features. The new spectral-based features and smoothing method in the AS module improved the speech detection performance from the audio stream of the input news content. In the speech recognition module, automatic selection of acoustic models achieved both a low WER, as with parallel recognition using multiple acoustic models, and fast recognition, as with the single acoustic model. The TS method using word concept vectors achieved more accurate results than the conventional method using local word frequency vectors. The information integration module provides the functionality of integrating results from the AS module, TS module, and SC module. The story boundary detection accuracy was improved by combining it with the AS results and the SC results compared to the sole TS results

Report on the ACM International Workshop on Methodologies and Evaluation of Lexical Cohesion Techniques in Real-World Applications (ELECTRA 2005) held at SIGIR 2005

The workshop on Methodologies and Evaluation of Lexical Cohesion Techniques in Real-World Applications (ELECTRA 2005) was held in Salvador, Brazil on August 19 in conjunction with the 28 th ACM Annual International Conference on Research and Development in Information Retrieval (SIGIR 2005). The aim of the workshop was to bring together researchers in NLP and IR to discuss the use of lexical cohesion in text applications, such as document and passage retrieval, question answering, topic segmentation and text summarization. There were a number of related workshops in the past: MEMURA 2004 Workshop on Methodologies and Evaluation of Multiword Units in Real-World Applications in association with the 4th International Conference on Language Resources (LREC 2004) [1], Multiword Expressions: Integrating Processing Workshop in association with the 42nd Annual Meeting of the Association for Computational Linguistics (ACL 2004) [2], and Multiword Expressions: Analysis, Acquisition and Treatment Workshop in association with the 41st Annual Meeting of the Association for Computational Linguistics (ACL 2003) [3]. The goal of this workshop was to address a wider range of lexical cohesion phenomena in text, not only multiword units, but also relations between words on the sentence, passage and document level, and how they can be useful for information retrieval applications.

Automatic Recognition of Spontaneous Speech for Access to Multilingual Oral History Archives

Much is known about the design of automated systems to search broadcast news, but it has only recently become possible to apply similar techniques to large collections of spontaneous speech. This paper presents initial results from experiments with speech recognition, topic segmentation, topic categorization, and named entity detection using a large collection of recorded oral histories. The work leverages a massive manual annotation effort on 10 000 h of spontaneous speech to evaluate the degree to which automatic speech recognition (ASR)-based segmentation and categorization techniques can be adapted to approximate decisions made by human annotators. ASR word error rates near 40% were achieved for both English and Czech for heavily accented, emotional and elderly spontaneous speech based on 65-84 h of transcribed speech. Topical segmentation based on shifts in the recognized English vocabulary resulted in 80% agreement with manually annotated boundary positions at a 0.35 false alarm rate. Categorization was considerably more challenging, with a nearest-neighbor technique yielding F=0.3. This is less than half the value obtained by the same technique on a standard newswire categorization benchmark, but replication on human-transcribed interviews showed that ASR errors explain little of that difference. The paper concludes with a description of how these capabilities could be used together to search large collections of recorded oral histories.

A statistical information extraction system for Turkish

This paper presents the results of a study on information extraction from unrestricted Turkish text using statistical language processing methods. In languages like English, there is a very small number of possible word forms with a given root word. However, languages like Turkish have very productive agglutinative morphology. Thus, it is an issue to build statistical models for specific tasks using the surface forms of the words, mainly because of the data sparseness problem. In order to alleviate this problem, we used additional syntactic information, i.e. the morphological structure of the words. We have successfully applied statistical methods using both the lexical and morphological information to sentence segmentation, topic segmentation, and name tagging tasks. For sentence segmentation, we have modeled the final inflectional groups of the words and combined it with the lexical model, and decreased the error rate to 4.34%, which is 21% better than the result obtained using only the surface forms of the words. For topic segmentation, stems of the words (especially nouns) have been found to be more effective than using the surface forms of the words and we have achieved 10.90% segmentation error rate on our test set according to the weighted TDT-2 segmentation cost metric. This is 32% better than the word-based baseline model. For name tagging, we used four different information sources to model names. Our first information source is based on the surface forms of the words. Then we combined the contextual cues with the lexical model, and obtained some improvement. After this, we modeled the morphological analyses of the words, and finally we modeled the tag sequence, and reached an F-Measure of 91.56%, according to the MUC evaluation criteria. Our results are important in the sense that, using linguistic information, i.e. morphological analyses of the words, and a corpus large enough to train a statistical model significantly improves these basic information extraction tasks for Turkish.

France Mihelič in Simon Dobrišek, Govorne tehnologije: pridobivanje in pregled govornih zbirk za slovenski jezik

Speech corpora are an essential infrastructure element for speech technologies research in a given language. Speech corpora consist of machine–readable speech recordings. They are further equipped with additional data, such as speaker and recording session descriptors and different segmentation and annotation elements, e.g. graphemic, phonetic and prosodic transcriptions or descriptors. In the article we describe the process of designing a speech corpus – from text or topic selection, recording, segmentation and labelling procedures. We conclude with an overview of speech corpora for the Slovene language.