111 citations · 552 across the 49 of their papers we have counts for
50 papers
Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval
Fan Yang, Yang Wu, Zheng Wang +3
Although sketch-to-photo retrieval has a wide range of applications, it is costly to obtain paired and rich-labeled ground truth. Differently, photo retrieval data is easier to acq…
Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos
Fan Yang, Norimichi Ukita, Sakriani Sakti +1
The success of deep learning on video Action Recognition (AR) has motivated researchers to progressively promote related tasks from the coarse level to the fine-grained level. Comp…
Speech Artifact Removal from EEG Recordings of Spoken Word Production with Tensor Decomposition
Holy Lovenia, Hiroki Tanaka, Sakriani Sakti +2
Research about brain activities involving spoken word production is considerably underdeveloped because of the undiscovered characteristics of speech artifacts, which contaminate e…
Simultaneous Neural Machine Translation with Constituent Label Prediction
Yasumasa Kano, Katsuhito Sudoh, Satoshi Nakamura
Simultaneous translation is a task in which translation begins before the speaker has finished speaking, so it is important to decide when to start the translation process. However…
Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation
Yui Oka, Katsuhito Sudoh, Satoshi Nakamura
Non-autoregressive neural machine translation (NAT) usually employs sequence-level knowledge distillation using autoregressive neural machine translation (AT) as its teacher model.…
ARTA: Collection and Classification of Ambiguous Requests and Thoughtful Actions
Shohei Tanaka, Koichiro Yoshino, Katsuhito Sudoh +1
Human-assisting systems such as dialogue systems must take thoughtful, appropriate actions not only for clear and unambiguous user requests, but also for ambiguous user requests, e…
Simultaneous Speech-to-Speech Translation System with Neural Incremental ASR, MT, and TTS
Katsuhito Sudoh, Takatomo Kano, Sashi Novitasari +3
This paper presents a newly developed, simultaneous neural speech-to-speech translation system and its evaluation. The system consists of three fully-incremental neural processing…
Cross-Lingual Machine Speech Chain for Javanese, Sundanese, Balinese, and Bataks Speech Recognition and Synthesis
Sashi Novitasari, Andros Tjandra, Sakriani Sakti +1
Even though over seven hundred ethnic languages are spoken in Indonesia, the available technology remains limited that could support communication within indigenous communities as…
Sequence-to-Sequence Learning via Attention Transfer for Incremental Speech Recognition
Sashi Novitasari, Andros Tjandra, Sakriani Sakti +1
Attention-based sequence-to-sequence automatic speech recognition (ASR) requires a significant delay to recognize long utterances because the output is generated after receiving en…
Incremental Machine Speech Chain Towards Enabling Listening while Speaking in Real-time
Sashi Novitasari, Andros Tjandra, Tomoya Yanagita +2
Inspired by a human speech chain mechanism, a machine speech chain framework based on deep learning was recently proposed for the semi-supervised development of automatic speech re…
Augmenting Images for ASR and TTS through Single-loop and Dual-loop Multimodal Chain Framework
Johanes Effendi, Andros Tjandra, Sakriani Sakti +1
Previous research has proposed a machine speech chain to enable automatic speech recognition (ASR) and text-to-speech synthesis (TTS) to assist each other in semi-supervised learni…
Image Captioning with Visual Object Representations Grounded in the Textual Modality
Dušan Variš, Katsuhito Sudoh, Satoshi Nakamura
We present our work in progress exploring the possibilities of a shared embedding space between textual and visual modality. Leveraging the textual nature of object detection label…
Reflection-based Word Attribute Transfer
Yoichi Ishibashi, Katsuhito Sudoh, Koichiro Yoshino +1
Word embeddings, which often represent such analogic relations as king - man + woman = queen, can be used to change a word's attribute, including its gender. For transferring king…
ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation
Fan Yang, Xin Chang, Chenyu Dang +4
We aim to improve the performance of Multiple Object Tracking and Segmentation (MOTS) by refinement. However, it remains challenging for refining MOTS results, which could be attri…
Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
In this paper, we report our submitted system for the ZeroSpeech 2020 challenge on Track 2019. The main theme in this challenge is to build a speech synthesizer without any textual…
Caption Generation of Robot Behaviors based on Unsupervised Learning of Action Segments
Koichiro Yoshino, Kohei Wakimoto, Yuta Nishimura +1
Bridging robot action sequences and their natural language captions is an important task to increase explainability of human assisting robots in their recently evolving field. In t…
Simultaneous Neural Machine Translation using Connectionist Temporal Classification
Katsuki Chousa, Katsuhito Sudoh, Satoshi Nakamura
Simultaneous machine translation is a variant of machine translation that starts the translation process before the end of an input. This task faces a trade-off between translation…
Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate
Fan Yang, Feiran Li, Yang Wu +2
3D panoramic multi-person localization and tracking are prominent in many applications, however, conventional methods using LiDAR equipment could be economically expensive and also…
Speech-to-speech Translation between Untranscribed Unknown Languages
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
In this paper, we explore a method for training speech-to-speech translation tasks without any transcription or linguistic supervision. Our proposed method consists of two steps: F…
Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networks
Andros Tjandra, Chunxi Liu, Frank Zhang +5
Deep acoustic models typically receive features in the first layer of the network, and process increasingly abstract representations in the subsequent layers. Here, we propose to f…
Make Skeleton-based Action Recognition Model Smaller, Faster and Better
Fan Yang, Sakriani Sakti, Yang Wu +1
Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To…
Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
Shohei Tanaka, Koichiro Yoshino, Katsuhito Sudoh +1
We propose a novel method for selecting coherent and diverse responses for a given dialogue context. The proposed method re-ranks response candidates generated from conversational…
Listening while Speaking and Visualizing: Improving ASR through Multimodal Chain
Johanes Effendi, Andros Tjandra, Sakriani Sakti +1
Previously, a machine speech chain, which is based on sequence-to-sequence deep learning, was proposed to mimic speech perception and production behavior. Such chains separately pr…
VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
Andros Tjandra, Berrak Sisman, Mingyang Zhang +3
We describe our submitted system for the ZeroSpeech Challenge 2019. The current challenge theme addresses the difficulty of constructing a speech synthesizer without any text or ph…