Kunal Dhawan

Employment

• Nvidia (United States) Senior Research Scientist

Education

Education history is unavailable.

Projects & Funding

Projects & funding information is unavailable.

Publications (36)

• Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
  arXiv preprint arXiv:2407.03495 2024
  +Save
• Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
  arXiv 2024 DOI: 10.48550/arXiv.2407.03495
  +Save
• DISCRETE AUDIO REPRESENTATION AS AN ALTERNATIVE TO MEL-SPECTROGRAMS FOR SPEAKER AND SPEECH RECOGNITION
  ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2024 DOI: 10.1109/ICASSP48485.2024.10446998
  +Save
• Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition
  ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024
  +Save
• ENHANCING SPEAKER DIARIZATION WITH LARGE LANGUAGE MODELS: A CONTEXTUAL BEAM SEARCH APPROACH
  ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2024 DOI: 10.1109/ICASSP48485.2024.10446204
  +Save
• Enhancing speaker diarization with large language models: A contextual beam search approach
  ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024
  +Save
• Less is More: Accurate Speech Recognition & Translation without Web-Scale Data
  arXiv preprint arXiv:2406.19674 2024
  +Save
• Less is More: Accurate Speech Recognition & Translation without Web-Scale Data
  arXiv 2024 DOI: 10.48550/arXiv.2406.19674
  +Save
• SPECTRAL CODECS: SPECTROGRAM-BASED AUDIO CODECS FOR HIGH QUALITY SPEECH SYNTHESIS
  arXiv 2024 DOI: 10.48550/arXiv.2406.05298
  +Save
• Spectral Codecs: Spectrogram-Based Audio Codecs for High Quality Speech Synthesis
  arXiv preprint arXiv:2406.05298 2024
  +Save
• DISCRETE AUDIO REPRESENTATION AS AN ALTERNATIVE TO MEL-SPECTROGRAMS FOR SPEAKER AND SPEECH RECOGNITION
  arXiv 2023 DOI: 10.48550/arXiv.2309.10922
  +Save
• ENHANCING SPEAKER DIARIZATION WITH LARGE LANGUAGE MODELS: A CONTEXTUAL BEAM SEARCH APPROACH
  arXiv 2023 DOI: 10.48550/arXiv.2309.05248
  +Save
• Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation
  arXiv 2023 DOI: 10.48550/arXiv.2310.12371
  +Save
• Property-aware multi-speaker data simulation: A probabilistic modelling technique for synthetic data generation
  arXiv preprint arXiv:2310.12371 2023
  +Save
• The CHiME-7 Challenge: System Description and Performance of NeMo Team's DASR System
  arXiv preprint arXiv:2310.12378 2023
  +Save
• The CHiME-7 Challenge: System Description and Performance of NeMo Team’s DASR System
  arXiv 2023 DOI: 10.48550/arXiv.2310.12378
  +Save
• UNIFIED MODEL FOR CODE-SWITCHING SPEECH RECOGNITION AND LANGUAGE IDENTIFICATION BASED ON CONCATENATED TOKENIZER
  arXiv 2023 DOI: 10.48550/arXiv.2306.08753
  +Save
• Unified Model for Code-Switching Speech Recognition and Language Identification Based on Concatenated Tokenizer
  CALCS 2023 - Computational Approaches to Linguistic Code-Switching, Proceedings of the Workshop 2023
  +Save
• Unified Model for Code-Switching Speech Recognition and Language Identification Based on Concatenated Tokenizer
  Proceedings of the 6th Workshop on Computational Approaches to Linguistic Code-Switching 2023
  +Save
• Evaluating Speech Production-based Acoustic Features for COVID-19 Classification using Cough Signals
  Proceedings of the 2021 IEEE 18th India Council International Conference, INDICON 2021 2021 DOI: 10.1109/INDICON52576.2021.9691699
  +Save