Browsing by Author "Arısoy, Ebru"
Now showing items 1-14 of 14
-
Bidirectional recurrent neural network language models for automatic speech recognition
Recurrent neural network language models have enjoyed great success in speech recognition, partially due to their ability to model longer-distance context than word n-gram models. In recurrent neural networks (RNNs), ... -
Compositional neural network language models for agglutinative languages
Arısoy, Ebru; Saraçlar, Murat (2016)Continuous space language models (CSLMs) have been proven to be successful in speech recognition. With proper training of the word embeddings, words that are semantically or syntactically related are expected to be mapped ... -
A decade of discriminative language modeling for automatic speech recognition
Saraçlar, Murat; Dikici, Erinc; Arısoy, Ebru (2015)This paper summarizes the research on discriminative language modeling focusing on its application to automatic speech recognition (ASR). A discriminative language model (DLM) is typically a linear or log-linear model ... -
Developing an automatic transcription and retrieval system for spoken lectures in Turkish
Arısoy, Ebru (2017)With the increase of online video lectures, using speech and language processing technologies for education has become quite important. This paper presents an automatic transcription and retrieval system developed for ... -
Domain adaptation approaches for acoustic modeling
Fakhan, Enver; Arısoy, Ebru (IEEE, 2020)In the recent years, with the development of neural network based models, ASR systems have achieved a tremendous performance increase. However, this performance increase mostly depends on the amount of training data and ... -
A Framework for Automatic Generation of Spoken Question-Answering Data
Menevşe, M.Ü.; Arısoy, Ebru; Manav, Y.; Özgür, A. (Association for Computational Linguistics (ACL), 2022)This paper describes a framework to automatically generate a spoken question answering (QA) dataset. The framework consists of a question generation (QG) module to generate questions automatically from given text documents, ... -
Highlighting of lecture video closed captions
Öztufan, Huseyin Efe; Yıldırım, Göktuğ; Arısoy, Ebru (IEEE, 2020)The main purpose of this study is to automatically highlight important regions of lecture video subtitles. Even though watching videos is an effective way of learning, the main disadvantage of video-based education is ... -
Improving the usage of subword-based units for Turkish speech recognition
Çetinkaya, Gözde; Arısoy, Ebru; Saraçlar, Murat (IEEE, 2020)Subword units are often utilized to achieve better performance in speech recognition because of the high number of observed words in agglutinative languages. In this study, the proper use of subword units is explored in ... -
Language modeling for Turkish text and speech processing
Arısoy, Ebru; Saraçlar, Murat (Springer, 2018)This chapter presents an overview of language modeling followed by a discussion of the challenges in Turkish language modeling. Sub-lexical units are commonly used to reduce the high out-of-vocabulary (OOV) rates of ... -
Multi-stream long short-term memory neural network language model
Arısoy, Ebru; Saraçlar, Murat (2015)Long Short-Term Memory (LSTM) neural networks are recurrent neural networks that contain memory units that can store contextual information from past inputs for arbitrary amounts of time. A typical LSTM neural network ... -
Question answering for spoken lecture processing
Ünlü, Merve; Arısoy, Ebru; Saraçlar, Murat (Institute of Electrical and Electronics Engineers (IEEE), 2019)This paper presents a question answering (QA) system developed for spoken lecture processing. The questions are presented to the system in written form and the answers are returned from lecture videos. In contrast to the ... -
Turkish Broadcast News Transcription Revisited
Arısoy, Ebru; Saraçlar, Murat (2018)Bu çalışmada yaklaşık on yıl önce gerçeklenen Türkçe haber programları için otomatik konuşma tanımayla yazılandırma sistemi güncel yöntemlerle yenilenerek aynı veri üzerindeki başarımı ölçülmüştür. Son yıllarda yapay sinir ... -
Turkish speech recognition
Arısoy, Ebru; Saraçlar, Murat (2018)Automatic speech recognition (ASR) is one of the most important applications of speech and language processing, as it forms the bridge between spoken and written language processing. This chapter presents an overview of ... -
Uncertainty-Aware Representations for spoken question answering
Arısoy, Ebru; Ünlü, Merve (Institute of Electrical and Electronics Engineers Inc., 2021)This paper describes a spoken question answering system that utilizes the uncertainty in automatic speech recognition (ASR) to mitigate the effect of ASR errors on question answering. Spoken question answering is typically ...
