Taichi Asami

发表

Latent words recurrent neural network language models

Akinori Ito, Takanobu Oba, Ryo Masumura, 2015, INTERSPEECH.

Online End-of-Turn Detection from Speech Based on Stacked Time-Asynchronous Sequential Networks

Ryo Ishii, Ryuichiro Higashinaka, Ryo Masumura, 2017, INTERSPEECH.

Efficient data selection for speech recognition based on prior confidence estimation using speech and monophone models

Satoshi Takahashi, Taichi Asami, Hirokazu Masataki, 2014, Comput. Speech Lang..

Fast unsupervised adaptation based on efficient statistics accumulation using frame independent confidence within monophone states

Satoshi Takahashi, Atsunori Ogawa, Taichi Asami, 2013, Comput. Speech Lang..

Efficient data selection for speech recognition based on prior confidence estimation using speech and context independent models

Satoshi Takahashi, Taichi Asami, Hirokazu Masataki, 2011, INTERSPEECH.

Efficient data selection for spoken document retrieval based on prior confidence estimation using speech and context independent models

Hirokazu Masataki, Yoshikazu Yamaguchi, Satoshi Takahashi, 2010, 2010 IEEE Spoken Language Technology Workshop.

Neural Confnet Classification: Fully Neural Network Based Spoken Utterance Classification Using Word Confusion Networks

Ryuichiro Higashinaka, Yusuke Ijima, Ryo Masumura, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture

Marc Delcroix, Hiroshi Sato, Tsubasa Ochiai, 2021, Interspeech.

Viterbi Approximation of Latent Words Language Models for Automatic Speech Recognition

Takanobu Oba, Ryo Masumura, Taichi Asami, 2019, J. Inf. Process..

Agreement and disagreement utterance detection in conversational speech by extracting and integrating local features

Manabu Okamoto, Taichi Asami, Hirokazu Masataki, 2015, INTERSPEECH.

Latent Words Recurrent Neural Network Language Models for Automatic Speech Recognition

Akinori Ito, Ryo Masumura, Takanobu Oba, 2015, IEICE Trans. Inf. Syst..

Hierarchical Latent Words Language Models for Automatic Speech Recognition

Takanobu Oba, Ryo Masumura, Taichi Asami, 2021, J. Inf. Process..

N-gram Approximation of Latent Words Language Models for Domain Robust Automatic Speech Recognition

Satoshi Takahashi, Takanobu Oba, Ryo Masumura, 2016, IEICE Trans. Inf. Syst..

Investigation of Combining Various Major Language Model Technologies including Data Expansion and Adaptation

Akinori Ito, Takanobu Oba, Ryo Masumura, 2016, IEICE Trans. Inf. Syst..

Mixture of latent words language models for domain adaptation

Takanobu Oba, Ryo Masumura, Taichi Asami, 2014, INTERSPEECH.

SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?

Taichi Asami, Tomohiro Tanaka, Kohei Matsuura, 2023, INTERSPEECH 2023.

Unsupervised confidence calibration using examples of recognized words and their contexts

Satoshi Takahashi, Osamu Yoshioka, Taichi Asami, 2013, INTERSPEECH.

Spoken Document Confidence Estimation Using Contextual Coherence

Satoshi Takahashi, Taichi Asami, Hirokazu Masataki, 2011, INTERSPEECH.

Domain adaptation of DNN acoustic models using knowledge distillation

Ryo Masumura, Hirokazu Masataki, Yoshikazu Yamaguchi, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Hyperspherical Query Likelihood Models with Word Embeddings

Kugatsu Sadamitsu, Ryuichiro Higashinaka, Kyosuke Nishida, 2017, IJCNLP.

Objective Evaluation Using Association Between Dimensions Within Spectral Features for Statistical Parametric Speech Synthesis

Yusuke Ijima, Hideyuki Mizuno, Taichi Asami, 2016, INTERSPEECH.

Domain Adaptation Based on Mixture of Latent Words Language Models for Automatic Speech Recognition

Akinori Ito, Takanobu Oba, Ryo Masumura, 2018, IEICE Trans. Inf. Syst..

Speaker recognition in duration-mismatched condition using bootstrapped i-vectors

Taichi Asami, Yoshikazu Yamaguchi, Atsushi Ando, 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).