Topic extraction based on continuous speech recognition in broadcast-news speech

Ohtsuki, Katsutoshi; Matsunaga, Shoichi; Matsuoka, Tatsuo; Furui, Sadaoki

doi:10.1109/asru.1997.659132

Cited by 11 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compare scenes on a computer, the topic information for each scene must be converted to some kind of index. TF-IDF [2,4], the quantity of mutual information [5] considering TF-IDF, and the χ 2 value [9] are often used as indexes. Also, a method is proposed wherein text is converted to indexes, in which the dimensionality is independent of the vocabulary size, using latent semantic analysis (LSA) [10] of word and text matrices and/or latent semantic analysis [11] of co-occurrence matrices.…”

Section: Methods For Converting Scenes To Indexesmentioning

confidence: 99%

Subtopic segmentation in lecture speech for the creation of lecture video contents

et al. 2006

View full text Add to dashboard Cite

SUMMARYAlthough still rare, video instructional materials which can be used over a network are on the increase. One of the reasons for the rarity of video instructional materials is thought to be the time and effort necessary for video editing. In this paper, the authors examine a method for automatically estimating subtopic segmentation positions from the speech information of an unedited lecture video, with the purpose of supporting the preparation of video instructional materials. Subtopic segmentation positions were estimated with comparisons of successive indexes using dynamic programming. The indexes were obtained by independent component analysis of text information attained from the speech recognition processing of the video. Through an experiment using unedited lecture video from five instructors, the proposed method was found to have a segmentation capacity equal to or better than the Hearst method, while allowing the number of segments to be set freely. It was also confirmed that the subtopic segmentation capacity using speech recognition output was equivalent to the use of transcribed text.

show abstract

Section: Methods For Converting Scenes To Indexesmentioning

confidence: 99%

Subtopic segmentation in lecture speech for the creation of lecture video contents

et al. 2006

View full text Add to dashboard Cite

show abstract

“…The system first extracts speech intervals via the audio segmentation process. The extracted speech intervals are then fed to the automatic speech recognition process [2]. The linguistic topic segmentation process next analyzes the resulting timestamped transcript.…”

Section: Introductionmentioning

confidence: 99%

Speech-based and video-supported indexing of multimedia broadcast news

Hayashi

Ohtsuki

Bessho

et al. 2003

Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval

View full text Add to dashboard Cite

This paper describes an automatic content indexing system for news programs, with a special emphasis on its segmentation process. The process can successfully segment an entire news program into topic-centered news stories; the primary tool is a linguistic topic segmentation algorithm. Experiments show that the resulting speech-based segments are fairly accurate, and scene change points supplied by an external video processor can be of help in improving segmentation effectiveness.

show abstract

“…An example is the classification of written documents such as newspaper articles [4]. Another type of classification is the classification of spoken documents such as news programs [5][6][7][8]. In most of these approaches, the relevance scores for descriptions and topics are calculated from the mutual information or TF-IDF for the word and the topic in the description.…”

Section: Introductionmentioning

confidence: 99%

Detection of topic and speech act type on utterance-by-utterance basis for conversational interfaces

Asami

Takezawa²,

Kikui³

2005

Syst. Comp. Jpn.

View full text Add to dashboard Cite

SUMMARYA conversational interface must extract information from texts transcribed by a speech recognizer and utilize the information for various kinds of applications. We propose a method for detecting topic and speech act type of an utterance as a fundamental technique for such a conversational interface. First, in the training phase of the proposed method, the score is determined on the basis of training data with topic and speech act tags, representing relevance scores for words relative to topic or speech acts. In the execution phase, for the words contained in the input utterance, the sum of the scores determined in the training phase is calculated for each topic or speech act, and the topic or speech act of the input utterance is inferred from the order of the sum. The score in this study is determined from the mutual information on the occurrence pattern of the words and the topics or speech acts in the training data, as well as the entropy of the occurrence of the word. The proposed method considers only the one-to-one relevance between the word and the topic or speech act, and the co-occurrence of multiple words is not considered. Consequently, the method works effectively for short sentences, such as often occur in conversation. In experiments using a conversational expression corpus with short mean length of utterances on diversified topics, a correct topic estimation rate of approximately 83% and a correct speech act estimation

show abstract

Topic extraction based on continuous speech recognition in broadcast-news speech

Cited by 11 publications

References 13 publications

Subtopic segmentation in lecture speech for the creation of lecture video contents

Subtopic segmentation in lecture speech for the creation of lecture video contents

Speech-based and video-supported indexing of multimedia broadcast news

Detection of topic and speech act type on utterance-by-utterance basis for conversational interfaces

Contact Info

Product

Resources

About