activity
20202025
most citedGeneric Speech Enhancement with Self-Supervised Representation Space Loss

4 citations · 18 across the 28 of their papers we have counts for

collaborators
Showing 2021Show all

12 papers · 1 filter

cs.CV2021★ 1 cited

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

Shota Orihashi, Yoshihiro Yamazaki, Naoki Makishima +4

This paper presents a novel training method for end-to-end scene text recognition. End-to-end scene text recognition offers high recognition accuracy, especially when using the enc…

cs.CL2021

Hierarchical Knowledge Distillation for Dialogue Sequence Labeling

Shota Orihashi, Yoshihiro Yamazaki, Naoki Makishima +4

This paper presents a novel knowledge distillation method for dialogue sequence labeling. Dialogue sequence labeling is a supervised learning task that estimates labels for each ut…

cs.CL2021★ 1 cited

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

Tomohiro Tanaka, Ryo Masumura, Mana Ihori +3

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-styl…

cs.CL2021

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

Tomohiro Tanaka, Ryo Masumura, Mana Ihori +5

We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors. Generally,…

cs.CL2021

Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation

Ryo Masumura, Daiki Okamura, Naoki Makishima +4

In this paper, we present a novel modeling method for single-channel multi-talker overlapped automatic speech recognition (ASR) systems. Fully neural network based end-to-end model…

cs.SD2021

Enrollment-less training for personalized voice activity detection

Naoki Makishima, Mana Ihori, Tomohiro Tanaka +3

We present a novel personalized voice activity detection (PVAD) learning method that does not require enrollment data during training. PVAD is a task to detect the speech segments…