Taichi Asami

According to our database, Taichi Asami authored at least 50 papers between 2004 and 2024.

Collaborative distances:

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

2024

What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis.

Takanori Ashihara, Marc Delcroix, Takafumi Moriya, Kohei Matsuura, Taichi Asami, Yusuke Ijima

CoRR, 2024

2023

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

Takanori Ashihara, Takafumi Moriya, Kohei Matsuura, Tomohiro Tanaka, Yusuke Ijima, Taichi Asami, Marc Delcroix, Yukinori Honma

CoRR, 2023

Coarse-Age Loss: A New Training Method Using Coarse-Age Labeled Data for Speaker Age Estimation.

Yuki Kitagishi, Hosana Kamiyama, Naohiro Tawara, Atsunori Ogawa, Noboru Miyazaki, Taichi Asami

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

An Improved Approximation Algorithm for Wage Determination and Online Task Allocation in Crowd-Sourcing.

Yuya Hikima, Yasunori Akagi, Hideaki Kim, Taichi Asami

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Fast Bayesian Estimation of Point Process Intensity as Function of Covariates.

Hideaki Kim, Taichi Asami, Hiroyuki Toda

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Hierarchical Latent Words Language Models for Automatic Speech Recognition.

Ryo Masumura, Taichi Asami, Takanobu Oba, Sumitaka Sakauchi

J. Inf. Process., 2021

The Effects of Physically Embodied Multiple Conversation Robots on the Elderly.

Toshiaki Nishio, Yuichiro Yoshikawa, Kazuki Sakai, Takamasa Iio, Mariko Chiba, Taichi Asami, Yoshinori Isoda, Hiroshi Ishiguro

Frontiers Robotics AI, 2021

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

Takafumi Moriya, Tomohiro Tanaka, Takanori Ashihara, Tsubasa Ochiai, Hiroshi Sato, Atsushi Ando, Ryo Masumura, Marc Delcroix, Taichi Asami

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

2019

Viterbi Approximation of Latent Words Language Models for Automatic Speech Recognition.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi

J. Inf. Process., 2019

Latent Words Recurrent Neural Network Language Models for Automatic Speech Recognition.

Ryo Masumura, Taichi Asami, Takanobu Oba, Sumitaka Sakauchi, Akinori Ito

IEICE Trans. Inf. Syst., 2019

Recurrent out-of-vocabulary word detection based on distribution of features.

Taichi Asami, Ryo Masumura, Yushi Aono, Koichi Shinoda

Comput. Speech Lang., 2019

2018

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

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

IEICE Trans. Inf. Syst., 2018

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

Ryo Masumura, Yusuke Ijima, Taichi Asami, Hirokazu Masataki, Ryuichiro Higashinaka

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Progressive Neural Network-based Knowledge Transfer in Acoustic Models.

Takafumi Moriya, Ryo Masumura, Taichi Asami, Yusuke Shinohara, Marc Delcroix, Yoshikazu Yamaguchi, Yushi Aono

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

2017

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

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Ryo Ishii, Ryuichiro Higashinaka

Proceedings of the Interspeech 2017, 2017

Prosody Aware Word-Level Encoder Based on BLSTM-RNNs for DNN-Based Speech Synthesis.

Yusuke Ijima, Nobukatsu Hojo, Ryo Masumura, Taichi Asami

Proceedings of the Interspeech 2017, 2017

Hyperspherical Query Likelihood Models with Word Embeddings.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Kugatsu Sadamitsu, Kyosuke Nishida, Ryuichiro Higashinaka

Proceedings of the Eighth International Joint Conference on Natural Language Processing, 2017

Cumulative moving averaged bottleneck speaker vectors for online speaker adaptation of CNN-based acoustic models.

Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, Taichi Asami, Shigeru Katagiri, Tomohiro Nakatani

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Parallel phonetically aware DNNs and LSTM-RNNS for frame-by-frame discriminative modeling of spoken language identification.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Cross-modal transfer with neural word vectors for image feature learning.

Go Irie, Taichi Asami, Shuhei Tarashima, Takayuki Kurozumi, Tetsuya Kinebuchi

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Domain adaptation of DNN acoustic models using knowledge distillation.

Taichi Asami, Ryo Masumura, Yoshikazu Yamaguchi, Hirokazu Masataki, Yushi Aono

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Joint unsupervised adaptation of n-gram and RNN language models via LDA-based hybrid mixture modeling.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono

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

2016

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

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Satoshi Takahashi

IEICE Trans. Inf. Syst., 2016

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

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

IEICE Trans. Inf. Syst., 2016

Language Identification Based on Generative Modeling of Posteriorgram Sequences Extracted from Frame-by-Frame DNNs and LSTM-RNNs.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono, Sumitaka Sakauchi

Proceedings of the Interspeech 2016, 2016

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

Yusuke Ijima, Taichi Asami, Hideyuki Mizuno

Proceedings of the Interspeech 2016, 2016

Recurrent Out-of-Vocabulary Word Detection Using Distribution of Features.

Taichi Asami, Ryo Masumura, Yushi Aono, Koichi Shinoda

Proceedings of the Interspeech 2016, 2016

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

Atsushi Ando, Taichi Asami, Yoshikazu Yamaguchi, Yushi Aono

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2016

2015

Latent words recurrent neural network language models.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

Proceedings of the INTERSPEECH 2015, 2015

Combinations of various language model technologies including data expansion and adaptation in spontaneous speech recognition.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

Proceedings of the INTERSPEECH 2015, 2015

Training data selection for acoustic modeling via submodular optimization of joint kullback-leibler divergence.

Taichi Asami, Ryo Masumura, Hirokazu Masataki, Manabu Okamoto, Sumitaka Sakauchi

Proceedings of the INTERSPEECH 2015, 2015

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

Atsushi Ando, Taichi Asami, Manabu Okamoto, Hirokazu Masataki, Sumitaka Sakauchi

Proceedings of the INTERSPEECH 2015, 2015

Hierarchical Latent Words Language Models for Robust Modeling to Out-Of Domain Tasks.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015

2014

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

Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Comput. Speech Lang., 2014

Mixture of latent words language models for domain adaptation.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi

Proceedings of the INTERSPEECH 2014, 2014

Read and spontaneous speech classification based on variance of GMM supervectors.

Taichi Asami, Ryo Masumura, Hirokazu Masataki, Sumitaka Sakauchi

Proceedings of the INTERSPEECH 2014, 2014

2013

Normalizing Complex Functional Expressions in Japanese Predicates: Linguistically-Directed Rule-Based Paraphrasing and Its Application.

Tomoko Izumi, Kenji Imamura, Taichi Asami, Kuniko Saito, Gen-ichiro Kikui, Satoshi Sato

ACM Trans. Asian Lang. Inf. Process., 2013

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

Satoshi Kobashikawa, Atsunori Ogawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Comput. Speech Lang., 2013

Unsupervised confidence calibration using examples of recognized words and their contexts.

Taichi Asami, Satoshi Kobashikawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the INTERSPEECH 2013, 2013

2012

Efficient prior and incremental beam width control to suppress excessive speech recognition time based on score range estimation.

Satoshi Kobashikawa, Takaaki Hori, Yoshikazu Yamaguchi, Taichi Asami, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), 2012

Efficient Beam Width Control to Suppress Excessive Speech Recognition Computation Time Based on Prior Score Range Normalization.

Satoshi Kobashikawa, Takaaki Hori, Yoshikazu Yamaguchi, Taichi Asami, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the INTERSPEECH 2012, 2012

Speech Data Clustering Based on Phoneme Error Trend for Unsupervised Acoustic Model Adaptation.

Taichi Asami, Satoshi Kobashikawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the INTERSPEECH 2012, 2012

2011

Spoken Document Confidence Estimation Using Contextual Coherence.

Taichi Asami, Narichika Nomoto, Satoshi Kobashikawa, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the INTERSPEECH 2011, 2011

Extracting call-reason segments from contact center dialogs by using automatically acquired boundary expressions.

Takaaki Fukutomi, Satoshi Kobashikawa, Taichi Asami, Tsubasa Shinozaki, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

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

Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the 2010 IEEE Spoken Language Technology Workshop, 2010

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

Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the INTERSPEECH 2010, 2010

2008

Evaluation of a Noise-Robust Multi-Stream Speaker Verification Method Using <i>F</i>₀ Information.

Taichi Asami, Koji Iwano, Sadaoki Furui

IEICE Trans. Inf. Syst., 2008

2006

A Stream-Weight and Threshold Estimation Method Using Adaboost for Multi-Stream Speaker Verification.

Taichi Asami, Koji Iwano, Sadaoki Furui

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005

Stream-weight optimization by LDA and adaboost for multi-stream speaker verification.

Taichi Asami, Koji Iwano, Sadaoki Furui

Proceedings of the INTERSPEECH 2005, 2005

2004

Noise-robust speaker verification using F0 features.

Koji Iwano, Taichi Asami, Sadaoki Furui

Proceedings of the INTERSPEECH 2004, 2004