Imran Sheikh

Employment

• Vivoka AI Researcher
  2021 - Present
• Inria Centre de Recherche Nancy Grand Est
  2019 - 2021
• Université de Lorraine Research Associate
  2014 - 2016
• Tata Consultancy Services Ltd Researcher
  2008 - 2013

Education

• Université de Lorraine PhD
  2014 - 2016
• University of Mumbai Bachelor of Electronics Engineering
  2003 - 2007

Projects & Funding

Projects & funding information is unavailable.

Publications (39)

• Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription
  2025 33rd European Signal Processing Conference (EUSIPCO) 2025 DOI: 10.23919/eusipco63237.2025.11226137
  +Save
• End-to-End Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training Data
  2025 33rd European Signal Processing Conference (EUSIPCO) 2025 DOI: 10.23919/eusipco63237.2025.11226249
  +Save
• Training RNN language models on uncertain ASR hypotheses in limited data scenarios
  Computer Speech & Language 2024 DOI: 10.1016/j.csl.2023.101555
  +Save
• Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
  The Speaker and Language Recognition Workshop (Odyssey 2024) 2024 DOI: 10.21437/odyssey.2024-15
  +Save
• End-to-End Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis
  2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2023 DOI: 10.1109/asru57964.2023.10389729
  +Save
• Transformer versus LSTM Language Models trained on Uncertain ASR Hypotheses in Limited Data Scenarios
  Proceedings of the Thirteenth Language Resources and Evaluation Conference 2022
  +Save
• Method and system for muting classified information from an audio
  2021
  +Save
• On Semi-Supervised LF-MMI Training of Acoustic Models with Limited Data
  Interspeech 2020 2020 DOI: 10.21437/interspeech.2020-2242
  +Save
• Audio-visual fusion for sentiment classification using cross-modal autoencoder
  32nd conference on neural information processing systems (NIPS 2018) 2019
  +Save
• Label-Driven Time-Frequency Masking for Robust Speech Command Recognition
  Text, Speech, and Dialogue 2019 DOI: 10.1007/978-3-030-27947-9_29
  +Save