Zobrazeno 1 - 10 of 83 pro vyhledávání: '"Takanobu, Oba"'
5
Generalized Large-Context Language Models Based on Forward-Backward Hierarchical Recurrent Encoder-Decoder Models
Autor: Tomohiro Tanaka, Mana Ihori, Takanobu Oba, Kyosuke Nishida, Ryo Masumura, Saito Itsumi
Publikováno v: ASRU
This paper presents a generalized form of large-context language models (LCLMs) that can take linguistic contexts beyond utterance boundaries into consideration. In discourse-level and conversation-level automatic speech recognition (ASR) tasks, whic
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a935f535cfb8118d665de8c47a84805a
https://doi.org/10.1109/asru46091.2019.9003857
Zobrazit plný text záznamu
6
Improving Speech-Based End-of-Turn Detection Via Cross-Modal Representation Learning with Punctuated Text Data
Autor: Takanobu Oba, Ando Atsushi, Ryo Masumura, Ryo Ishii, Ryuichiro Higashinaka, Mana Ihori, Tomohiro Tanaka
Publikováno v: ASRU
This paper presents a novel training method for speech-based end-of-turn detection for which not only manually annotated speech data sets but also punctuated text data sets are utilized. The speech-based end-of-turn detection estimates whether a targ
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3c340259c9989898a931689065caf99e
https://doi.org/10.1109/asru46091.2019.9003816
Zobrazit plný text záznamu
7
Can We Simulate Generative Process of Acoustic Modeling Data? Towards Data Restoration for Acoustic Modeling
Autor: Takanobu Oba, Ryo Masumura, Satoshi Kobashikawa, Yusuke Ijima, Yushi Aono
Publikováno v: APSIPA
In this paper, we present an initial study on data restoration for acoustic modeling in automatic speech recognition (ASR). In the ASR field, the speech log data collected during practical services include customers' personal information, so the log
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2608ee3b5fee8c15e5d59339a1fe241d
https://doi.org/10.1109/apsipaasc47483.2019.9023184
Zobrazit plný text záznamu
8
Disfluency Detection Based on Speech-Aware Token-by-Token Sequence Labeling with BLSTM-CRFs and Attention Mechanisms
Autor: Tomohiro Tanaka, Yushi Aono, Takafumi Moriya, Takanobu Oba, Ryo Masumura
Publikováno v: APSIPA
This paper presents a new method for token-by-token sequence labeling that can leverage not only lexical information but also speech information without any alignments. Our motivation is to detect disfluencies such as fillers and word fragments robus
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fce9a806dcafddf5bd025c669d7d78d8
https://doi.org/10.1109/apsipaasc47483.2019.9023119
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje