| Mmdenselstm: An efficient combination of convolutional and recurrent neural networks for audio source separation N Takahashi, N Goswami, Y Mitsufuji 2018 16th International workshop on acoustic signal enhancement (IWAENC …, 2018 | 220 | 2018 |
| Recursive speech separation for unknown number of speakers N Takahashi, S Parthasaarathy, N Goswami, Y Mitsufuji arXiv preprint arXiv:1904.03065, 2019 | 104 | 2019 |
| PhaseNet: Discretized Phase Modeling with Deep Neural Networks for Audio Source Separation. N Takahashi, P Agrawal, N Goswami, Y Mitsufuji Interspeech, 2713-2717, 2018 | 86 | 2018 |
| The Sound Demixing Challenge 2023$\unicode {x2013} $ Music Demixing Track G Fabbro, S Uhlich, CH Lai, W Choi, M Martínez-Ramírez, W Liao, ... arXiv preprint arXiv:2308.06979, 2023 | 20 | 2023 |
| System and method for processing video content based on emotional state detection P Chintalapoodi, N Goswami, H Sadhwani, M Sulibhavi US Patent 10,529,379, 2020 | 14 | 2020 |
| Device and method for generating a panoramic image N Goswami, M Sulibhavi, P Chintalapoodi US Patent 10,298,841, 2019 | 13 | 2019 |
| System and method for sharing multimedia content with synched playback controls N Goswami, M Sulibhavi US Patent 10,778,742, 2020 | 9 | 2020 |
| DenseNet with pre-activated deconvolution for estimating depth map from single image S Sharma, RP Padhy, SK Choudhury, N Goswami, PK Sa Conference on Activity Monitoring by Multiple Distributed Sensing (AMMDS …, 2017 | 5 | 2017 |
| SATTS: Speaker attractor text to speech, learning to speak by learning to separate N Goswami, T Harada arXiv preprint arXiv:2207.06011, 2022 | 4 | 2022 |
| Hypervq: Mlr-based vector quantization in hyperbolic space N Goswami, Y Mukuta, T Harada arXiv preprint arXiv:2403.13015, 2024 | 3 | 2024 |
| Advancing large multi-modal models with explicit chain-of-reasoning and visual question generation K Uehara, N Goswami, H Wang, T Baba, K Tanaka, T Hashimoto, K Wang, ... arXiv preprint arXiv:2401.10005, 2024 | 3 | 2024 |
| ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model X Chu, N Goswami, Z Cui, H Wang, T Harada arXiv preprint arXiv:2502.20323, 2025 | | 2025 |
| Method and system to generate one or more multi-dimensional videos N Goswami US Patent 11,082,754, 2021 | | 2021 |
| T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask Learning N Goswami, H Wang, T Harada The Thirteenth International Conference on Learning Representations, 0 | | |
Yuki MitsufujiDistinguished Engineer, Sony; Specially Appointed Associate Professor, Tokyo Institute of Technologyایمیل تأیید شده در sony.com