Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Hiroaki Nanjo"'
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28:391-401
In computer-assisted pronunciation training (CAPT), the scarcity of large-scale non-native corpora and human expert annotations are two fundamental challenges to non-native acoustic modeling. Most existing approaches of acoustic modeling in CAPT are
Autor:
Yuichi Nakamura, Siyang Yu, Masatake Dantsuji, Takayuki Nakajima, Hiroaki Nanjo, Kazuaki Kondo
Publikováno v:
IEICE Transactions on Information and Systems. :156-164
Pronunciation is a fundamental factor in speaking and listening. However, instructions for important articulation have not been sufficiently provided in conventional computer-assisted language learning (CALL) systems. One typical case is the articula
Publikováno v:
APSIPA
We propose a rescoring method using words related to a query obtained by Web search and word vectors for spoken term detection (STD). In this paper, we assume that words associated with the topic in speech data and co-occurring with the query are cal
Publikováno v:
ICASSP
Articulatory feedback is effective for computer-assisted pronunciation training (CAPT) systems. This paper investigates efficient model learning methods for providing articulatory information to language learners. We first propose an articulatory att
Publikováno v:
SLaTE
Publikováno v:
INTED proceedings.
We have been doing research on an effective training method for Japanese speakers to be able to discriminate between the Mandarin Chinese nasal codas “-n” and “-ng”, which is one of the most difficult phonemic contrasts for Japanese speakers.
Publikováno v:
Journal of Language Teaching and Research. 9:7
The aim of this study is to examine the effect of high variability training on “-n” and “-ng” in Mandarin Chinese. 46 Japanese native speakers who study Mandarin Chinese as a second foreign language at a university in Japan were divided into
Autor:
Yoichi Yamashita, Katunobu Itou, Hiromitsu Nishizaki, Yoshiaki Itoh, Norihito Yasuda, Tatsuya Kawahara, Tomoyosi Akiba, Kiyoaki Aikawa, Hiroaki Nanjo
Publikováno v:
Journal of Information Processing. 17:82-94
The lecture is one of the most valuable genres of audiovisual data. Though spoken document processing is a promising technology for utilizing the lecture in various ways, it is difficult to evaluate because the evaluation require a subjective judgmen
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 12(4):409-419
A new method for automatic detection of section boundaries and extraction of key sentences from lecture audio archives is proposed. The method makes use of 'discourse markers' (DMs), which are characteristic expressions used in initial utterances of
Autor:
Tatsuya Kawahara, Hiroaki Nanjo
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 12:391-400
The paper addresses adaptation methods to language model and speaking rate (SR) of individual speakers which are two major problems in automatic transcription of spontaneous presentation speech. To cope with a large variation in expression and pronun