The primary objective of sentence segmentation process is to determine the sentence boundaries of a stream of words output by the automatic speech recognizers. Statistical methods developed for sentence segmentation requires a significant amount of labeled data which is time-consuming, labor intensive and expensive. In this work, we propose new multi-view semi-supervised learning strategies for sentence boundary classification problem using lexical, prosodic, and morphological information. The aim is to find effective semi-supervised machine learning strategies when only small sets of sentence boundary labeled data are available. We primarily investigate two semi-supervised learning approaches, called self-training and co-training. Differen...
In this paper, we present some recent improvements in our automatic speech segmentation system, whic...
Abstract: This article presents a cross-lingual study for agglutinative, fixed stressed languages, l...
Some connectionist models of speech segmentation have exploited the utterance boundary strategy, whe...
Text in English ; Abstract: English and TurkishIncludes bibliographical references (leaves 124-132)x...
We investigate the application of the co-training learning algorithm on the sentence boundary classi...
The sentence is a standard textual unit in natural language processing applications. In many languag...
We explore the use of prosodic features beyond pauses, including duration, pitch, and energy feature...
3rd International Conference on Advances in Information Systems -- OCT 20-22, 2004 -- Izmir, TURKEYW...
Innovations in Intelligent Systems and Applications Conference (ASYU) -- OCT 04-06, 2018 -- Adana, T...
This paper presents experiments on sentence boundary detection in transcripts of spoken dialogues. S...
2018 Innovations in Intelligent Systems and Applications Conference, ASYU 2018 --4 October 2018 thro...
Automatic sentence segmentation of speech is important for enriching speech recognition output and a...
International audienceIn this article we deal with the text segmentation problem in statistical lang...
Enriching speech recognition output with sentence boundaries improves its human readability and enab...
This dissertation proposes a method for the automatic design and extraction of prosodic features. T...
In this paper, we present some recent improvements in our automatic speech segmentation system, whic...
Abstract: This article presents a cross-lingual study for agglutinative, fixed stressed languages, l...
Some connectionist models of speech segmentation have exploited the utterance boundary strategy, whe...
Text in English ; Abstract: English and TurkishIncludes bibliographical references (leaves 124-132)x...
We investigate the application of the co-training learning algorithm on the sentence boundary classi...
The sentence is a standard textual unit in natural language processing applications. In many languag...
We explore the use of prosodic features beyond pauses, including duration, pitch, and energy feature...
3rd International Conference on Advances in Information Systems -- OCT 20-22, 2004 -- Izmir, TURKEYW...
Innovations in Intelligent Systems and Applications Conference (ASYU) -- OCT 04-06, 2018 -- Adana, T...
This paper presents experiments on sentence boundary detection in transcripts of spoken dialogues. S...
2018 Innovations in Intelligent Systems and Applications Conference, ASYU 2018 --4 October 2018 thro...
Automatic sentence segmentation of speech is important for enriching speech recognition output and a...
International audienceIn this article we deal with the text segmentation problem in statistical lang...
Enriching speech recognition output with sentence boundaries improves its human readability and enab...
This dissertation proposes a method for the automatic design and extraction of prosodic features. T...
In this paper, we present some recent improvements in our automatic speech segmentation system, whic...
Abstract: This article presents a cross-lingual study for agglutinative, fixed stressed languages, l...
Some connectionist models of speech segmentation have exploited the utterance boundary strategy, whe...