Kengo Ohta

According to our database, Kengo Ohta authored at least 21 papers between 2007 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Recognition of target domain Japanese speech using language model replacement.

Daiki Mori, Kengo Ohta, Ryota Nishimura, Atsunori Ogawa, Norihide Kitaoka

EURASIP J. Audio Speech Music. Process., December, 2024

2023

Development of a model for predicting timing of back-channel in a real-time spoken dialog system.

Aito Nakata, Ryota Nishimura, Kengo Ohta, Norihide Kitaoka

Proceedings of the 12th IEEE Global Conference on Consumer Electronics, 2023

Language modeling for spontaneous speech recognition based on disfluency labeling and generation of disfluent text.

Koharu Horii, Kengo Ohta, Ryota Nishimura, Atsunori Ogawa, Norihide Kitaoka

Proceedings of the Asia Pacific Signal and Information Processing Association Annual Summit and Conference, 2023

Combining multiple end-to-end speech recognition models based on density ratio approach.

Keigo Hojo, Daiki Mori, Yukoh Wakabayashi, Kengo Ohta, Atsunori Ogawa, Norihide Kitaoka

Proceedings of the Asia Pacific Signal and Information Processing Association Annual Summit and Conference, 2023

2022

End-to-End Spontaneous Speech Recognition Using Disfluency Labeling.

Koharu Horii, Meiko Fukuda, Kengo Ohta, Ryota Nishimura, Atsunori Ogawa, Norihide Kitaoka

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2021

Response type selection for chat-like spoken dialog systems based on LSTM and multi-task learning.

Kengo Ohta, Ryota Nishimura, Norihide Kitaoka

Speech Commun., 2021

Text-to-speech system for low-resource language using cross-lingual transfer learning and data augmentation.

Zolzaya Byambadorj, Ryota Nishimura, Altangerel Ayush, Kengo Ohta, Norihide Kitaoka

EURASIP J. Audio Speech Music. Process., 2021

Advanced language model fusion method for encoder-decoder model in Japanese speech recognition.

Daiki Mori, Kengo Ohta, Ryota Nishimura, Atsunori Ogawa, Norihide Kitaoka

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2021

End-to-End Spontaneous Speech Recognition Using Hesitation Labeling.

Koharu Horii, Meiko Fukuda, Kengo Ohta, Ryota Nishimura, Atsunori Ogawa, Norihide Kitaoka

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2021

Multi-speaker TTS system for low-resource language using cross-lingual transfer learning and data augmentation.

Zolzaya Byambadorj, Ryota Nishimura, Altangerel Ayush, Kengo Ohta, Norihide Kitaoka

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2021

2019

Type of Response Selection utilizing User Utterance Word Sequence, LSTM and Multi-task Learning for Chat-like Spoken Dialog Systems.

Kengo Ohta, Ryota Nishimura, Norihide Kitaoka

Proceedings of the 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2019

2018

HMM-based Speech Synthesizer for Easily Understandable Speech Broadcasting.

Hirokazu Akadomari, Kosuke Ishikawa, Yosuke Kobayashi, Kengo Ohta, Jay Kishigami

Proceedings of the IEEE 7th Global Conference on Consumer Electronics, 2018

2017

Semantic parser for easy understandable speech broadcasting.

Yosuke Kobayashi, Kosuke Ishikawa, Kengo Ohta, Jay Kishigami

Proceedings of the IEEE 6th Global Conference on Consumer Electronics, 2017

Selecting type of response for chat-like spoken dialogue systems based on acoustic features of user utterances.

Kengo Ohta, Rikito Marumoto, Ryota Nishimura, Norihide Kitaoka

Proceedings of the 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2017

2012

Development of large vocabulary continuous speech recognition system for Mongolian language.

Seiichi Nakagawa, Erdenebat Turmunkh, Hiroshi Kibishi, Kengo Ohta, Yasuhisa Fujii, Masatoshi Tsuchiya, Kazumasa Yamamoto

Proceedings of the Third Workshop on Spoken Language Technologies for Under-resourced Languages, 2012

Developing Partially-Transcribed Speech Corpus from Edited Transcriptions.

Kengo Ohta, Masatoshi Tsuchiya, Seiichi Nakagawa

Proceedings of the Eighth International Conference on Language Resources and Evaluation, 2012

2011

Detection of precisely transcribed parts from inexact transcribed corpus.

Kengo Ohta, Masatoshi Tsuchiya, Seiichi Nakagawa

Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011

2009

Effective use of pause information in language modelling for speech recognition.

Kengo Ohta, Masatoshi Tsuchiya, Seiichi Nakagawa

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

2008

Developing Corpus of Japanese Classroom Lecture Speech Contents.

Masatoshi Tsuchiya, Satoru Kogure, Hiromitsu Nishizaki, Kengo Ohta, Seiichi Nakagawa

Proceedings of the International Conference on Language Resources and Evaluation, 2008

Evaluating spoken language model based on filler prediction model in speech recognition.

Kengo Ohta, Masatoshi Tsuchiya, Seiichi Nakagawa

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

2007

Construction of spoken language model including fillers using filler prediction model.

Kengo Ohta, Masatoshi Tsuchiya, Seiichi Nakagawa

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007