Sakriani Sakti 研究室

主宰者：Sakriani Sakti

奈良先端科学技術大学院大学

兼任：北陸先端科学技術大学院大学

AI 要約（直近 5 年の研究成果）

Sakriani Sakti研究室は、音声と言語を融合させた自然言語処理の研究に取り組んでいます。特に、複数言語間での音声翻訳、音声認識、音声合成といった音声処理技術の開発が中心です。研究対象は、自動音声認識システムの精度向上、同時通訳型の音声翻訳の効率化、感情表現を保持した音声翻訳など、実世界での応用を意識した多岐にわたる課題を扱っています。手法としては、トランスフォーマーやニューラルネットワーク等の深層学習アーキテクチャを活用しながら、自己教師あり学習や拡散モデル、混合専門家モデルといった先進的な機械学習技術を組み合わせています。特に、限定されたデータセットでの学習を効率化する工夫や、複数言語・複数話者を扱うための適応的な学習戦略が重要な要素です。また、医療応用として、咳音によるテンベストリア検出や音声からの認知機能低下の検出なども行っています。主要な知見として、言語モデルと音声モデルの段階的な調整順序が認識精度に大きく影響すること、韻律情報の活用が構造的曖昧性の解決に有効であること、そして多言語環境での音声技術の開発には言語特有の特性を考慮した設計が必須であることが報告されています。これらの研究は、多様な言語・文化背景を持つユーザーが自然に相互作用できるシステムの実現に貢献しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（84 件）

[2026] SimulSense: Sense-Driven Interpreting for Efficient Simultaneous Speech Translation
DOI: https://doi.org/10.1109/icassp55912.2026.11463328
[2026] Wavenext 2: Convnext-Based Fast Neural Vocoders with Residual Denoising and Sub-Modeling for Gan And Diffusion Models
DOI: https://doi.org/10.1109/icassp55912.2026.11461371
[2026] LLM-Assisted Spanish Dialect Corpus Construction
DOI: https://doi.org/10.63317/3zod9jyperib
[2026] Automatic Generation of a Compositional QA Benchmark for Geospatial Reasoning under Spatial and Entity Constraints
DOI: https://doi.org/10.18653/v1/2026.eacl-srw.61
[2025] Stage-Wise Acoustic-Linguistic Fine-Tuning for Overlapped Speech Recognition: Does Ordering Matter?
DOI: https://doi.org/10.1109/o-cocosda68185.2025.11384906
[2025] HifiDiff: Two Stream Diffusion Models for High Fidelity Speech Generation of Unseen Languages
DOI: https://doi.org/10.1109/o-cocosda68185.2025.11384822
[2025] Tuning Tone With Age: Adapting Dialogue Response Generation Based on Llms and Self-Supervised Speaker Age Estimation
DOI: https://doi.org/10.1109/o-cocosda68185.2025.11385248
[2025] Measuring Emotion Preservation in Expressive Speech-to-Speech Translation
DOI: https://doi.org/10.1109/o-cocosda68185.2025.11385054
[2025] Toward Natural Emotional Text-to-Speech System with Fine-Grained Non-Verbal Expression Control
DOI: https://doi.org/10.1109/o-cocosda68185.2025.11385230
[2025] Joining Diarization and Multi-Speaker Automatic Speech Recognition with Overlap Handling for Long Conversations
DOI: https://doi.org/10.1109/o-cocosda68185.2025.11385084

続きを表示（残り 74 件）

[2025] Bridging Disfluent to Fluent in Speech Translation: Effective Tagging and Fine-Tuning Strategies
DOI: https://doi.org/10.1109/o-cocosda68185.2025.11384869
[2025] Exploring the Relationship Between Ostracism and Communication Apprehension in Human-Robot Interaction
DOI: https://doi.org/10.1145/3765766.3765851
[2025] Semi-supervised Acoustic Scene Classification with Label Smoothing and Hard Samples Identification
DOI: https://doi.org/10.1109/icsigsys67277.2025.11269138
[2025] Indonesian Folklore Storytelling in Japanese Language with Text-to-Speech
DOI: https://doi.org/10.1109/icsigsys67277.2025.11269173
[2025] A Comparison of Solicited and Longitudinal Cough Sounds for Tuberculosis Detection
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249364
[2025] Beyond One-Shot Dubbing: Leveraging N-Best Translation and Prompted Paraphrasing with Synchrony-Aware Re-Ranking
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249323
[2025] Rethinking Robust ASR Strategies: Can Textual in-Context Learning Improve Acoustic Robustness?
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249368
[2025] Dementia Prediction From Speech Signal Using Optimized Prosodic Features
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249322
[2025] SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition
DOI: https://doi.org/10.21437/interspeech.2025-1243
[2025] Behavioral Interdependence: a Mediator of Ostracism–Aggression Relationship in Human–Robot Interaction
DOI: https://doi.org/10.1109/arso64737.2025.11124983
[2025] Impact of Gender and Group Size on Right to Speak and Peer Pressure in Human-Robot Interaction
DOI: https://doi.org/10.1109/arso64737.2025.11124979
[2025] Role of Social Treatment and Mode of Communication in Shaping Social Acceptance
DOI: https://doi.org/10.1109/hsi66212.2025.11142386
[2025] Toward fast meeting transcription: NAIST system for CHiME-8 NOTSOFAR-1 task and its analysis
DOI: https://doi.org/10.1016/j.csl.2025.101836
[2025] From Pixels to Voice: A Simple and Efficient End-to-End Spoken Image Description Approach via Vision Codec Language Models
DOI: https://doi.org/10.1109/icassp49660.2025.10890285
[2025] Toward Visual Pronunciation Learning: A Speech-to-Articulatory Animation Pipeline Leveraging wav2vec 2.0 and rtMRI Landmarks
DOI: https://doi.org/10.1109/icassp49660.2025.10889764
[2025] Enhancing Unsupervised Acoustic Word Embedding with Visual-Grounded Speech Model and Novel Word-level ABX Evaluation Schemes
DOI: https://doi.org/10.1109/icassp49660.2025.10890820
[2025] NAIST Offline Speech Translation System for IWSLT 2025
DOI: https://doi.org/10.18653/v1/2025.iwslt-1.38
[2025] Zero-Shot Cross-Lingual Text-to-Speech With Style-Enhanced Normalization and Auditory Feedback Training Mechanism
DOI: https://doi.org/10.1109/taslpro.2025.3548429
[2025] ZeST: A Zero-Resourced Speech-to-Speech Translation Approach for Unknown, Unpaired, and Untranscribed Languages
DOI: https://doi.org/10.1109/access.2025.3527012
[2025] End-to-end Simultaneous Speech Translation with Style Tags using Human Simultaneous Interpretation Data
DOI: https://doi.org/10.5715/jnlp.32.404
[2025] NAIST Simultaneous Speech Translation System for IWSLT 2025
DOI: https://doi.org/10.18653/v1/2025.iwslt-1.39
[2025] Structural Ambiguity Resolution in Indonesian–English Speech-to-Text Translation by Utilizing Prosodic Information
DOI: https://doi.org/10.1109/access.2025.3648059
[2025] SAM Translator: Self-Paced Learning And Mixture-of-Experts for Cross-Lingual Text-to-Speech Translation
DOI: https://doi.org/10.1109/access.2025.3644647
[2025] Learning Marmoset Vocal Patterns with a Masked Autoencoder for Robust Call Segmentation, Classification, and Caller Identification
DOI: https://doi.org/10.1109/asru65441.2025.11434811
[2024] A Feedback-Driven Self-Improvement Strategy and Emotion-Aware Vocoder for Emotional Voice Conversion
DOI: https://doi.org/10.1109/o-cocosda64382.2024.10800102
[2024] Unsupervised Anomalous Sound Detection Using Timbral and Human Voice Disorder-Related Acoustic Features
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10848563
[2024] Anomalous Machine Sound Detection Based on Time Domain Gammatone Spectrogram Feature and IDNN Model
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10849225
[2024] Continual Learning in Machine Speech Chain Using Gradient Episodic Memory
DOI: https://doi.org/10.1109/o-cocosda64382.2024.10800352
[2024] Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities
DOI: https://doi.org/10.1109/o-cocosda64382.2024.10800336
[2024] Chunk Size Scheduling for Optimizing the Quality-Latency Trade-off in Simultaneous Speech Translation
DOI: https://doi.org/10.1109/o-cocosda64382.2024.10800559
[2024] An Evaluation of Neural Vocoder-Based Voice Cloning System for Dysphonia Speech Disorder
DOI: https://doi.org/10.1109/o-cocosda64382.2024.10800714
[2024] Neural End-To-End Speech Translation Leveraged by ASR Posterior Distribution
DOI: https://doi.org/10.1587/transinf.2023edp7249
[2024] Machine Speech Chain with Emotion Recognition
DOI: https://doi.org/10.1109/icaicta63815.2024.10763258
[2024] The NAIST System for the CHiME-8 NOTSOFAR-1 Task
DOI: https://doi.org/10.21437/chime.2024-13
[2024] Contrastive Feedback Mechanism for Simultaneous Speech Translation
DOI: https://doi.org/10.21437/interspeech.2024-2426
[2024] On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition
DOI: https://doi.org/10.21437/syndata4genai.2024-5
[2024] MAG-BERT-ARL for Fair Automated Video Interview Assessment
DOI: https://doi.org/10.1109/access.2024.3473314
[2024] NAIST Simultaneous Speech Translation System for IWSLT 2024
DOI: https://doi.org/10.18653/v1/2024.iwslt-1.23
[2024] Applying Syntax-Prosody Mapping Hypothesis and Boundary-Driven Theory to Neural Sequence-to-Sequence Speech Synthesis
DOI: https://doi.org/10.1109/access.2024.3487053
[2023] Leveraging the Multilingual Indonesian Ethnic Languages Dataset In Self-Supervised Models for Low-Resource ASR Task
DOI: https://doi.org/10.1109/asru57964.2023.10389730
[2023] Generating Speech with Prosodic Prominence based on SSL-Visually Grounded Models
DOI: https://doi.org/10.1109/o-cocosda60357.2023.10482965
[2023] Low-Resource Japanese-English Speech-to-Text Translation Leveraging Speech-Text Unified-model Representation Learning
DOI: https://doi.org/10.21437/sigul.2023-17
[2023] VGSAlign: Bilingual Speech Alignment of Unpaired and Untranscribed Languages using Self-Supervised Visually Grounded Speech Models
DOI: https://doi.org/10.21437/sigul.2023-12
[2023] STEN-TTS: Improving Zero-shot Cross-Lingual Transfer for Multi-Lingual TTS with Style-Enhanced Normalization Diffusion Framework
DOI: https://doi.org/10.21437/interspeech.2023-2243
[2023] Unsupervised Learning of Discrete Latent Representations with Data-Adaptive Dimensionality from Continuous Speech Streams
DOI: https://doi.org/10.21437/interspeech.2023-1321
[2023] Self-Adaptive Incremental Machine Speech Chain for Lombard TTS with High-Granularity ASR Feedback in Dynamic Noise Condition
DOI: https://doi.org/10.1109/icassp49357.2023.10096128
[2023] An Isotropy Analysis for Self-Supervised Acoustic Unit Embeddings on the Zero Resource Speech Challenge 2021 Framework
DOI: https://doi.org/10.1109/icassp49357.2023.10095119
[2023] NIX-TTS: Lightweight and End-to-End Text-to-Speech Via Module-Wise Distillation
DOI: https://doi.org/10.1109/slt54892.2023.10023322
[2023] Exploring Difficulties Encountered by Professional Interpreters in Japanese-to-English and English-to-Japanese Simultaneous Translation
DOI: https://doi.org/10.1109/o-cocosda60357.2023.10482968
[2023] NusaCrowd: Open Source Initiative for Indonesian NLP Resources
DOI: https://doi.org/10.18653/v1/2023.findings-acl.868
[2023] NAIST Simultaneous Speech-to-speech Translation System for IWSLT 2023
DOI: https://doi.org/10.18653/v1/2023.iwslt-1.31
[2023] Japanese Neural Incremental Text-to-Speech Synthesis Framework With an Accent Phrase Input
DOI: https://doi.org/10.1109/access.2023.3251657
[2023] Speech Recognition and Meaning Interpretation: Towards Disambiguation of Structurally Ambiguous Spoken Utterances in Indonesian
DOI: https://doi.org/10.18653/v1/2023.emnlp-main.1045
[2022] Improved Consistency Training for Semi-Supervised Sequence-to-Sequence ASR via Speech Chain Reconstruction and Self-Transcribing
DOI: https://doi.org/10.21437/interspeech.2022-11169
[2022] Tackling multiple object tracking with complicated motions — Re-designing the integration of motion and appearance
DOI: https://doi.org/10.1016/j.imavis.2022.104514
[2022] A Machine Speech Chain Approach for Dynamically Adaptive Lombard TTS in Static and Dynamic Noise Environments
DOI: https://doi.org/10.1109/taslp.2022.3196879
[2022] NAIST Simultaneous Speech-to-Text Translation System for IWSLT 2022
DOI: https://doi.org/10.18653/v1/2022.iwslt-1.25
[2022] Modeling Unsupervised Empirical Adaptation by DPGMM and DPGMM-RNN Hybrid Model to Extract Perceptual Features for Low-Resource ASR
DOI: https://doi.org/10.1109/taslp.2022.3150220
[2021] End-to-End Image-to-Speech Generation for Untranscribed Unknown Languages
DOI: https://doi.org/10.1109/access.2021.3071541
[2021] NAIST English-to-Japanese Simultaneous Translation System for IWSLT 2021 Simultaneous Text-to-text Task
DOI: https://doi.org/10.18653/v1/2021.iwslt-1.3
[2021] Neural Incremental Speech Recognition Toward Real-Time Machine Speech Translation
DOI: https://doi.org/10.1587/transinf.2021edp7014
[2021] Using Local Phrase Dependency Structure Information in Neural Sequence-to-Sequence Speech Synthesis
DOI: https://doi.org/10.1109/o-cocosda202152914.2021.9660456
[2021] Simultaneous Speech-to-Speech Translation System with Transformer-Based Incremental ASR, MT, and TTS
DOI: https://doi.org/10.1109/o-cocosda202152914.2021.9660477
[2021] Multi-Encoder Sequential Attention Network for Context-Aware Speech Recognition in Japanese Dialog Conversation
DOI: https://doi.org/10.1109/o-cocosda202152914.2021.9660580
[2021] Code-Switching ASR and TTS Using Semisupervised Learning with Machine Speech Chain
DOI: https://doi.org/10.1587/transinf.2021edp7005
[2021] Dynamically Adaptive Machine Speech Chain Inference for TTS in Noisy Environment: Listen and Speak Louder
DOI: https://doi.org/10.21437/interspeech.2021-946
[2021] ASR Posterior-Based Loss for Multi-Task End-to-End Speech Translation
DOI: https://doi.org/10.21437/interspeech.2021-1105
[2021] Unsupervised Neural-Based Graph Clustering for Variable-Length Speech Representation Discovery of Zero-Resource Languages
DOI: https://doi.org/10.21437/interspeech.2021-1340
[2021] Weakly-Supervised Speech-to-Text Mapping with Visually Connected Non-Parallel Speech-Text Data Using Cyclic Partially-Aligned Transformer
DOI: https://doi.org/10.21437/interspeech.2021-970
[2021] Transcribing Paralinguistic Acoustic Cues to Target Language Text in Transformer-Based Speech-to-Text Translation
DOI: https://doi.org/10.21437/interspeech.2021-1020
[2021] Neural speech synthesis using local phrase dependency structure information
[2021] Transformer-Based Direct Speech-To-Speech Translation with Transcoder
DOI: https://doi.org/10.1109/slt48900.2021.9383496
[2021] Incorporating Discriminative DPGMM Posteriorgrams for Low-Resource ASR
DOI: https://doi.org/10.1109/slt48900.2021.9383597
[2021] Multimodal Chain: Cross-Modal Collaboration Through Listening, Speaking, and Visualizing
DOI: https://doi.org/10.1109/access.2021.3077886

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（84 件）

科研費（0 件）

所属学会・役職（0 件）