Search Results for author: Naoki Makishima

Found 13 papers, 1 papers with code

On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis

1 code implementation28 Oct 2022 Atsushi Ando, Ryo Masumura, Akihiko Takashima, Satoshi Suzuki, Naoki Makishima, Keita Suzuki, Takafumi Moriya, Takanori Ashihara, Hiroshi Sato

This paper investigates the effectiveness and implementation of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis~(MSA).

Multimodal Sentiment Analysis

Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations

no code implementations16 Jun 2022 Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Ryo Masumura

Experimental validation reveals the effectiveness of both worst-enrollment target training and SI-loss training to improve robustness against enrollment variations, by increasing speaker discriminability.

Speaker Identification Speech Extraction

Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages

no code implementations24 Nov 2021 Shota Orihashi, Yoshihiro Yamazaki, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Ryo Masumura

To this end, the proposed method pre-trains the encoder by using a multilingual dataset that combines the resource-poor language's dataset and the resource-rich language's dataset to learn language-invariant knowledge for scene text recognition.

Scene Text Recognition

Hierarchical Knowledge Distillation for Dialogue Sequence Labeling

no code implementations22 Nov 2021 Shota Orihashi, Yoshihiro Yamazaki, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Ryo Masumura

Dialogue sequence labeling is a supervised learning task that estimates labels for each utterance in the target dialogue document, and is useful for many applications such as dialogue act estimation.

Knowledge Distillation Scene Segmentation

End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning

no code implementations7 Jul 2021 Tomohiro Tanaka, Ryo Masumura, Mana Ihori, Akihiko Takashima, Shota Orihashi, Naoki Makishima

We propose a semi-supervised learning method for building end-to-end rich transcription-style automatic speech recognition (RT-ASR) systems from small-scale rich transcription-style and large-scale common transcription-style datasets.

Automatic Speech Recognition speech-recognition

Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition

no code implementations4 Jul 2021 Tomohiro Tanaka, Ryo Masumura, Mana Ihori, Akihiko Takashima, Takafumi Moriya, Takanori Ashihara, Shota Orihashi, Naoki Makishima

However, the conventional method cannot take into account the relationships between these two different modal inputs because the input contexts are separately encoded for each modal.

Automatic Speech Recognition speech-recognition

Zero-Shot Joint Modeling of Multiple Spoken-Text-Style Conversion Tasks using Switching Tokens

no code implementations23 Jun 2021 Mana Ihori, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, Ryo Masumura

To execute multiple conversion tasks simultaneously without preparing matched datasets, our key idea is to distinguish individual conversion tasks using the on-off switch.

Automatic Speech Recognition Punctuation Restoration +2

Audio-Visual Speech Separation Using Cross-Modal Correspondence Loss

no code implementations2 Mar 2021 Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura

We present an audio-visual speech separation learning method that considers the correspondence between the separated signals and the visual signals to reflect the speech characteristics during training.

Speech Separation

Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents

no code implementations16 Feb 2021 Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi

This paper presents a novel self-supervised learning method for handling conversational documents consisting of transcribed text of human-to-human conversations.

Language Modelling Representation Learning +2

MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training

no code implementations15 Feb 2021 Mana Ihori, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, Ryo Masumura

However, these models require a large amount of paired data of spoken-style text and style normalized text, and it is difficult to prepare such a volume of data.

Machine Translation Self-Supervised Learning

Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model

no code implementations INLG (ACL) 2020 Mana Ihori, Ryo Masumura, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi

Thus, it is important to leverage memorized knowledge in the external LM for building the seq2seq model, since it is hard to prepare a large amount of paired data.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.