ABELAB - publication:2020Human Centric Information Processing Lab.
http://abelab-main/
2026-05-05T06:10:00+00:00ABELAB
http://abelab-main/
http://abelab-main/_media/wiki/dokuwiki.svgtext/html2021-01-19T01:42:34+00:00Anonymous (anonymous@undisclosed.example.com)Concept Drift Adaptation for Acoustic Scene Classifier Based on Gaussian Mixture Model
http://abelab-main/publication/2020/ibunu_i_tencon2020?rev=1611020554&do=diff
sound acoustic_scene_classification p:ibunu_daqiqil_id p:sunao_hara p:masanobu_abe
Concept Drift Adaptation for Acoustic Scene Classifier Based on Gaussian Mixture Model
* , ,
* The 2020 IEEE Region 10 Conference (IEEE-TENCON 2020), pp.450–455, Online/Virtual Conference (Osaka, Japan), Nov. 2020.
Abstract
In non-stationary environments, data might change over time, leading to variations in the underlying data distributions. This phenomenon is called concept drift and it negatively impacts…text/html2021-01-19T01:38:11+00:00Anonymous (anonymous@undisclosed.example.com)Module Comparison of Transformer-TTS for Speaker Adaptation based on Fine-tuning
http://abelab-main/publication/2020/k_inoue_apsipa2020?rev=1611020291&do=diff
sound speech_synthesis p:katsuki_inoue p:sunao_hara p:masanobu_abe
Module Comparison of Transformer-TTS for Speaker Adaptation based on Fine-tuning
* , ,
* Proceedings of APSIPA Annual Summit and Conference 2020, pp.826–830, Online/Virtual Conference (Auckland, New Zealand), Dec. 2020. (Oral/ONLINE PRESENTATION)text/html2020-05-25T09:47:44+00:00Anonymous (anonymous@undisclosed.example.com)Semi-Supervised Speaker Adaptation for End-to-End Speech Synthesis with Pretrained Models
http://abelab-main/publication/2020/k_inoue_icassp2020a?rev=1590400064&do=diff
sound speech_synthesis p:katsuki_inoue p:sunao_hara p:masanobu_abe
Semi-Supervised Speaker Adaptation for End-to-End Speech Synthesis with Pretrained Models
* , , , Tomoki Hayashi, Ryuichi Yamamoto, Shinji Watanabe
* ICASSP 2020, pp. 7634--7638, Barcelona, Spain, May 2020. (Oral/ONLINE PRESENTATION)
Abstract
Recently, end-to-end text-to-speech (TTS) models have achieved a remarkable performance, however, requiring a large amount of paired text and speech data for training. On the other han…text/html2020-05-25T10:08:57+00:00Anonymous (anonymous@undisclosed.example.com)Espnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
http://abelab-main/publication/2020/k_inoue_icassp2020b?rev=1590401337&do=diff
sound speech_synthesis p:katsuki_inoue
Espnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
* Tomoki Hayashi, Ryuichi Yamamoto, , Takenori Yoshimura, Shinji Watanabe, Tomoki Toda, Kazuya Takeda, Yu Zhang, Xu Tan
* ICASSP 2020, pp. 7654--7658, Barcelona, Spain, May 2020. (Oral/ONLINE PRESENTATION)text/html2021-01-19T01:34:18+00:00Anonymous (anonymous@undisclosed.example.com)Controlling the Strength of Emotions in Speech-Like Emotional Sound Generated by WaveNet
http://abelab-main/publication/2020/k_matsumoto_interspeech2020?rev=1611020058&do=diff
sound speech_synthesis p:kento_matsumoto p:sunao_hara p:masanobu_abe
Controlling the Strength of Emotions in Speech-Like Emotional Sound Generated by WaveNet
* , ,
* Proceedings of Interspeech 2020, pp.3421--3425, Online/Virtual Conference (Shanghai, China), Oct. 2020. (Oral/ONLINE PRESENTATION)
Abstract
This paper proposes a method to enhance the controllability of a Speech-like Emotional Sound (SES). In our previous study, we proposed an algorithm to generate SES by employing WaveNet as…