publications

journal articles

  1. Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding
    Bhati, Saurabhchand, Villalba, Jesús, Zelasko, Piotr, Moro-Velazquez, Laureano, and Dehak, Najim
    IEEE/ACM Transactions on Audio, Speech, and Language Processing 2022
    PDF
  2. Regularizing Contrastive Predictive Coding for speech applications
    Bhati, Saurabhchand, Villalba, Jesús, Zelasko, Piotr, Moro-Velazquez, Laureano, and Dehak, Najim
    In submission to IEEE/ACM TASLP 2023
    PDF
  3. Discovering phonetic inventories with crosslingual automatic speech recognition
    Żelasko, Piotr, Feng, Siyuan, Velázquez, Laureano Moro, Abavisani, Ali,  Bhati, Saurabhchand, Scharenborg, Odette, Hasegawa-Johnson, Mark, and Dehak, Najim
    Computer Speech & Language 2022
  4. Unsupervised speech signal-to-symbol transformation for language identification
    Bhati, Saurabhchand, Nayak, Shekhar, and Kodukula, Sri Rama Murty
    Circuits, Systems, and Signal Processing 2020

conference articles & others

  1. Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning
    Bhati, Saurabhchand, Villalba, Jesús, Moro-Velazquez, Laureano, Thebaud, Thomas, and Dehak, Najim
    In submission 2023
    PDF
  2. Virtual phone discovery for speech synthesis without text
    Nayak, Shekhar, Kumar, C Shiva, Ramesh, G,  Bhati, Saurabhchand, and Murty, K Sri Rama
    In 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2019
  3. Unsupervised segmentation of speech signals using kernel-gram matrices
    Bhati, Saurabhchand, Nayak, Shekhar, and Sri Rama Murty, K
    In National Conference on Computer Vision, Pattern Recognition, Image Processing, and Graphics 2017
  4. Modeling sparse spatio-temporal representations for no-reference video quality assessment
    Shabeer, P Muhammed,  Bhati, Saurabhchand, and Channappayya, Sumohana S
    In 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2017
  5. Zero resource speaking rate estimation from change point detection of syllable-like units
    Nayak, Shekhar,  Bhati, Saurabhchand, and Murty, K Sri Rama
    In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019
  6. LSTM Siamese network for Parkinson’s disease detection from speech
    Bhati, Saurabhchand, Velazquez, Laureano Moro, Villalba, Jesús, and Dehak, Najim
    In 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2019
  7. Speaker Embedding Extraction with Virtual Phonetic Information
    Sreekanth, S, Murty, K Sri Rama,  Bhati, Saurabhchand, and others,
    In 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2019
  8. Unsupervised Acoustic Segmentation and Clustering Using Siamese Network Embeddings.
    Bhati, Saurabhchand, Nayak, Shekhar, Murty, K Sri Rama, and Dehak, Najim
    In INTERSPEECH 2019
  9. Segmental contrastive predictive coding for unsupervised word segmentation
    Bhati, Saurabhchand, Villalba, Jesús, Żelasko, Piotr, Moro-Velazquez, Laureano, and Dehak, Najim
    In INTERSPEECH 2021
    PDF
  10. Unsupervised Speech Signal to Symbol Transformation for Zero Resource Speech Applications.
    Bhati, Saurabhchand, Nayak, Shekhar, and Murty, K Sri Rama
    In INTERSPEECH 2017
  11. Self-expressing autoencoders for unsupervised spoken term discovery
    Bhati, Saurabhchand, Villalba, Jesús, Żelasko, Piotr, and Dehak, Najim
    In INTERSPEECH 2020
  12. Bottom-Up Unsupervised Word Discovery via Acoustic Units
    Bhati, Saurabhchand, Liu, Chunxi, Villalba, Jesús, Trmal, Jan, Khudanpur, Sanjeev, and Dehak, Najim
    In 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2019
  13. An investigation into instantaneous frequency estimation methods for improved speech recognition features
    Nayak, Shekhar,  Bhati, Saurabhchand, and Murty, K Sri Rama
    In 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2017
  14. Instantaneous frequency features for noise robust speech recognition
    Nayak, Shekhar, Shashank, Dhar B,  Bhati, Saurabhchand, Bramhendra, Koilakuntla, and Murty, K Sri Rama
    In 2019 National Conference on Communications (NCC) 2019
  15. Phoneme based embedded segmental k-means for unsupervised term discovery
    Bhati, Saurabhch, Kamper, Herman, and Murty, K Sri Rama
    In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018