Yosuke Kashiwagi

65 papers A 13C 3Misc 12Journal 32Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback. CoRR Siddhant Arora, Jinchuan Tian, Jiatong Shi, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2026	J	`jnl`	Phonological Tokenizer: Prosody-Aware Phonetic Token via Multi-Objective Fine-Tuning with Differentiable K-Means. CoRR Kentaro Onda, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2025	J	`jnl`	Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems. CoRR Siddhant Arora, Jinchuan Tian, Hayato Futami, Jiatong Shi, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2025	A	`conf`	Chain-of-Thought Training for Open E2E Spoken Dialogue Systems. INTERSPEECH Siddhant Arora, Jinchuan Tian, Hayato Futami, Jee-weon Jung, Jiatong Shi, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2025	J	`jnl`	Chain-of-Thought Training for Open E2E Spoken Dialogue Systems. CoRR Siddhant Arora, Jinchuan Tian, Hayato Futami, Jee-weon Jung, Jiatong Shi, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2025	A	`conf`	Differentiable K-means for Fully-optimized Discrete Token-based ASR. INTERSPEECH Kentaro Onda, Yosuke Kashiwagi, Emiru Tsunoo, Hayato Futami, Shinji Watanabe
2025	J	`jnl`	Differentiable K-means for Fully-optimized Discrete Token-based ASR. CoRR Kentaro Onda, Yosuke Kashiwagi, Emiru Tsunoo, Hayato Futami, Shinji Watanabe
2025	—	`conf`	ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems. NAACL (System Demonstrations) Siddhant Arora, Yifan Peng, Jiatong Shi, Jinchuan Tian, William Chen, Shikhar Bharadwaj, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Shuichiro Shimizu, Vaibhav Srivastav, Shinji Watanabe
2025	J	`jnl`	ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems. CoRR Siddhant Arora, Yifan Peng, Jiatong Shi, Jinchuan Tian, William Chen, Shikhar Bharadwaj, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Shuichiro Shimizu, Vaibhav Srivastav, Shinji Watanabe
2025	Misc	`conf`	Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens. ICASSP Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo, Siddhant Arora, Shinji Watanabe
2025	A	`conf`	Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs. INTERSPEECH Hayato Futami, Emiru Tsunoo, Yosuke Kashiwagi, Yuki Ito, Hassan Shahmohammadi, Siddhant Arora, Shinji Watanabe
2025	J	`jnl`	Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs. CoRR Hayato Futami, Emiru Tsunoo, Yosuke Kashiwagi, Yuki Ito, Hassan Shahmohammadi, Siddhant Arora, Shinji Watanabe
2025	C	`conf`	Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting. ASRU Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe
2025	J	`jnl`	Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting. CoRR Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe
2025	J	`jnl`	Whale: Large-Scale multilingual ASR model with w2v-BERT and E-Branchformer with large speech data. CoRR Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo, Satoshi Asakawa
2024	A	`conf`	Decoder-only Architecture for Streaming End-to-end Speech Recognition. INTERSPEECH Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe
2024	J	`jnl`	Decoder-only Architecture for Streaming End-to-end Speech Recognition. CoRR Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe
2024	A	`conf`	Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model. INTERSPEECH Hayato Futami, Siddhant Arora, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2024	J	`jnl`	Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model. CoRR Hayato Futami, Siddhant Arora, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2024	J	`jnl`	Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens. CoRR Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo, Siddhant Arora, Shinji Watanabe
2024	Misc	`conf`	Phoneme-Aware Encoding for Prefix-Tree-Based Contextual ASR. ICASSP Hayato Futami, Emiru Tsunoo, Yosuke Kashiwagi, Hiroaki Ogawa, Siddhant Arora, Shinji Watanabe
2024	A	`conf`	Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting. INTERSPEECH Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo, Siddhant Arora, Shinji Watanabe
2024	J	`jnl`	Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting. CoRR Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo, Siddhant Arora, Shinji Watanabe
2024	J	`jnl`	Task Arithmetic for Language Expansion in Speech Translation. CoRR Yao-Fei Cheng, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Wen Shen Teo, Siddhant Arora, Shinji Watanabe
2024	—	`conf`	UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions. NAACL-HLT Siddhant Arora, Hayato Futami, Jee-weon Jung, Yifan Peng, Roshan S. Sharma, Yosuke Kashiwagi, Emiru Tsunoo, Karen Livescu, Shinji Watanabe
2023	Misc	`conf`	A Study on the Integration of Pipeline and E2E SLU Systems for Spoken Semantic Parsing Toward Stop Quality Challenge. ICASSP Siddhant Arora, Hayato Futami, Shih-Lun Wu, Jessica Huynh, Yifan Peng, Yosuke Kashiwagi, Emiru Tsunoo, Brian Yan, Shinji Watanabe
2023	J	`jnl`	A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge. CoRR Siddhant Arora, Hayato Futami, Shih-Lun Wu, Jessica Huynh, Yifan Peng, Yosuke Kashiwagi, Emiru Tsunoo, Brian Yan, Shinji Watanabe
2023	J	`jnl`	Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation. CoRR Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe
2023	Misc	`conf`	E-Branchformer-Based E2E SLU Toward Stop on-Device Challenge. ICASSP Yosuke Kashiwagi, Siddhant Arora, Hayato Futami, Jessica Huynh, Shih-Lun Wu, Yifan Peng, Brian Yan, Emiru Tsunoo, Shinji Watanabe
2023	A	`conf`	Integrating Pretrained ASR and LM to Perform Sequence Generation for Spoken Language Understanding. INTERSPEECH Siddhant Arora, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Brian Yan, Shinji Watanabe
2023	J	`jnl`	Integrating Pretrained ASR and LM to Perform Sequence Generation for Spoken Language Understanding. CoRR Siddhant Arora, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Brian Yan, Shinji Watanabe
2023	A	`conf`	Integration of Frame- and Label-synchronous Beam Search for Streaming Encoder-decoder Speech Recognition. INTERSPEECH Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe
2023	J	`jnl`	Integration of Frame- and Label-synchronous Beam Search for Streaming Encoder-decoder Speech Recognition. CoRR Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe
2023	J	`jnl`	Phoneme-aware Encoding for Prefix-tree-based Contextual ASR. CoRR Hayato Futami, Emiru Tsunoo, Yosuke Kashiwagi, Hiroaki Ogawa, Siddhant Arora, Shinji Watanabe
2023	Misc	`conf`	Streaming Joint Speech Recognition and Disfluency Detection. ICASSP Hayato Futami, Emiru Tsunoo, Kentaro Shibata, Yosuke Kashiwagi, Takao Okuda, Siddhant Arora, Shinji Watanabe
2023	A	`conf`	Tensor decomposition for minimization of E2E SLU model toward on-device processing. INTERSPEECH Yosuke Kashiwagi, Siddhant Arora, Hayato Futami, Jessica Huynh, Shih-Lun Wu, Yifan Peng, Brian Yan, Emiru Tsunoo, Shinji Watanabe
2023	J	`jnl`	The Pipeline System of ASR and NLU with MLM-based Data Augmentation toward STOP Low-resource Challenge. CoRR Hayato Futami, Jessica Huynh, Siddhant Arora, Shih-Lun Wu, Yosuke Kashiwagi, Yifan Peng, Brian Yan, Emiru Tsunoo, Shinji Watanabe
2023	Misc	`conf`	The Pipeline System of ASR and NLU with MLM-based data Augmentation Toward Stop Low-Resource Challenge. ICASSP Hayato Futami, Jessica Huynh, Siddhant Arora, Shih-Lun Wu, Yosuke Kashiwagi, Yifan Peng, Brian Yan, Emiru Tsunoo, Shinji Watanabe
2023	J	`jnl`	UniverSLU: Universal Spoken Language Understanding for Diverse Classification and Sequence Generation Tasks with a Single Network. CoRR Siddhant Arora, Hayato Futami, Jee-weon Jung, Yifan Peng, Roshan S. Sharma, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2022	Misc	`conf`	Improving Character Error Rate is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-Box Acoustic Models. ICASSP Ryosuke Sawata, Yosuke Kashiwagi, Shusuke Takahashi
2022	Misc	`conf`	Joint Speech Recognition and Audio Captioning. ICASSP Chaitanya Narisetty, Emiru Tsunoo, Xuankai Chang, Yosuke Kashiwagi, Michael Hentschel, Shinji Watanabe
2022	J	`jnl`	Joint Speech Recognition and Audio Captioning. CoRR Chaitanya Narisetty, Emiru Tsunoo, Xuankai Chang, Yosuke Kashiwagi, Michael Hentschel, Shinji Watanabe
2022	A	`conf`	Residual Language Model for End-to-end Speech Recognition. INTERSPEECH Emiru Tsunoo, Yosuke Kashiwagi, Chaitanya Prasad Narisetty, Shinji Watanabe
2022	J	`jnl`	Residual Language Model for End-to-end Speech Recognition. CoRR Emiru Tsunoo, Yosuke Kashiwagi, Chaitanya Narisetty, Shinji Watanabe
2022	Misc	`conf`	Run-and-Back Stitch Search: Novel Block Synchronous Decoding For Streaming Encoder-Decoder ASR. ICASSP Emiru Tsunoo, Chaitanya Narisetty, Michael Hentschel, Yosuke Kashiwagi, Shinji Watanabe
2022	J	`jnl`	Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR. CoRR Emiru Tsunoo, Chaitanya Narisetty, Michael Hentschel, Yosuke Kashiwagi, Shinji Watanabe
2022	J	`jnl`	Streaming Joint Speech Recognition and Disfluency Detection. CoRR Hayato Futami, Emiru Tsunoo, Kentaro Shibata, Yosuke Kashiwagi, Takao Okuda, Siddhant Arora, Shinji Watanabe
2021	A	`conf`	Data Augmentation Methods for End-to-End Speech Recognition on Distant-Talk Scenarios. Interspeech Emiru Tsunoo, Kentaro Shibata, Chaitanya Narisetty, Yosuke Kashiwagi, Shinji Watanabe
2021	J	`jnl`	Data Augmentation Methods for End-to-end Speech Recognition on Distant-Talk Scenarios. CoRR Emiru Tsunoo, Kentaro Shibata, Chaitanya Narisetty, Yosuke Kashiwagi, Shinji Watanabe
2021	J	`jnl`	Gaussian Kernelized Self-Attention for Long Sequence Data and Its Application to CTC-based Speech Recognition. CoRR Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2021	Misc	`conf`	Gaussian Kernelized Self-Attention for Long Sequence Data and its Application to CTC-Based Speech Recognition. ICASSP Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
2021	J	`jnl`	Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models. CoRR Ryosuke Sawata, Yosuke Kashiwagi, Shusuke Takahashi
2021	—	`conf`	Streaming Transformer Asr With Blockwise Synchronous Beam Search. SLT Emiru Tsunoo, Yosuke Kashiwagi, Shinji Watanabe
2020	J	`jnl`	Streaming Transformer ASR with Blockwise Synchronous Inference. CoRR Emiru Tsunoo, Yosuke Kashiwagi, Shinji Watanabe
2019	A	`conf`	End-to-End Adaptation with Backpropagation Through WFST for On-Device Speech Recognition System. INTERSPEECH Emiru Tsunoo, Yosuke Kashiwagi, Satoshi Asakawa, Toshiyuki Kumakura
2019	J	`jnl`	End-to-end Adaptation with Backpropagation through WFST for On-device Speech Recognition System. CoRR Emiru Tsunoo, Yosuke Kashiwagi, Satoshi Asakawa, Toshiyuki Kumakura
2019	J	`jnl`	Towards Online End-to-end Transformer Automatic Speech Recognition. CoRR Emiru Tsunoo, Yosuke Kashiwagi, Toshiyuki Kumakura, Shinji Watanabe
2019	C	`conf`	Transformer ASR with Contextual Block Processing. ASRU Emiru Tsunoo, Yosuke Kashiwagi, Toshiyuki Kumakura, Shinji Watanabe
2019	J	`jnl`	Transformer ASR with Contextual Block Processing. CoRR Emiru Tsunoo, Yosuke Kashiwagi, Toshiyuki Kumakura, Shinji Watanabe
2016	A	`conf`	Automatic Assessment and Error Detection of Shadowing Speech: Case of English Spoken by Japanese Learners. INTERSPEECH Shuju Shi, Yosuke Kashiwagi, Shohei Toyama, Junwei Yue, Yutaka Yamauchi, Daisuke Saito, Nobuaki Minematsu
2016	Misc	`conf`	Divergence estimation based on deep neural networks and its use for language identification. ICASSP Yosuke Kashiwagi, Congying Zhang, Daisuke Saito, Nobuaki Minematsu
2015	—	`conf`	Noise-robust and stress-free visualization of pronunciation diversity of World Englishes using a learner's self-centered viewpoint. O-COCOSDA/CASLRE Yuichi Sato, Yosuke Kashiwagi, Nobuaki Minematsu, Daisuke Saito, Keikichi Hirose
2014	Misc	`conf`	Semi-supervised noise dictionary adaptation for exemplar-based noise robust speech recognition. ICASSP Yi Luan, Daisuke Saito, Yosuke Kashiwagi, Nobuaki Minematsu, Keikichi Hirose
2013	C	`conf`	Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognition. ASRU Yosuke Kashiwagi, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose
2012	—	`conf`	Audio-visual feature integration based on piecewise linear transformation for noise robust automatic speech recognition. SLT Yosuke Kashiwagi, Masayuki Suzuki, Nobuaki Minematsu, Keikichi Hirose