Concepedia

Nabarun Goswami

NG

Statistics

Publications

4

Citations

345

H-Index

4

Active since

2018

Affiliations

Tencent (China)(Current)

Nabarun Goswami is an author at Tencent (China) specializing in speech separation, speech processing, and machine learning.

Top concepts

EngineeringDeep LearningMachine LearningSpeech ProcessingSpeech SeparationSignal ProcessingSpeech RecognitionDeep Neural NetworksMusicLanguage

Publications per year

2018–2024

4

Publications

4

Mmdenselstm: An Efficient Combination of Convolutional and Recurrent Neural Networks for Audio Source Separation

Naoya Takahashi, Nabarun Goswami, Yuki Mitsufuji · 2018 · 164 citations

Music, Source Separation, Deep Neural Networks +15

Recursive Speech Separation for Unknown Number of Speakers

Naoya Takahashi, Parthasaarathy Sudarsanam, Nabarun Goswami et al. · 2019 · 86 citations

Source Separation, Engineering, Machine Learning +17

PhaseNet: Discretized Phase Modeling with Deep Neural Networks for Audio Source Separation

Naoya Takahashi, Purvi Agrawal, Nabarun Goswami et al. · 2018 · 74 citations

Phase Modeling, Source Separation, Deep Neural Networks +9

The Sound Demixing Challenge 2023 – Music Demixing Track

Giorgio Fabbro, Stefan Uhlich, Chieh-Hsin Lai et al. · Transactions of the International Society for Music Information Retrieval · 2024 · 21 citations · Full text

1–4 of 4