Responsibility :

- Development of ASR engine using frameworks like ESPNET or FairSeq or Athena or Deep Speech using PyTorch or Tensorflow or Kaldi.

- Working on speech tech like Multilingual ASR, Contextual biasing, Text to Speech, Voice Biometric, speaker separation, and so on.

- Assist to define technology required for Speech Technology besides core engine and to design integration of these technologies.

- Work on improvement of adapting the model to multiple domains and channels.

Desired experience :

- If fresher, projects should be in alignment with our domain.

- Good understanding of signal processing, machine learning (ML) tools.

- Should be well versed in classical speech processing methodologies like hidden Markov models (HMMs), Gaussian mixture models (GMMs), Artificial neural networks (ANNs), Language modeling, etc.

- Experience in working with low-latency and optimization techniques.

- Understanding of traditional speech decoders.

- Hands-on experience current deep learning (DL) techniques like Convolutional neural networks (CNNs), recurrent neural networks (RNNs), long-term short-term memory (LSTM), connectionist temporal classification (CTC), Transformer, etc used for speech processing is essential.

- The candidate should have hands-on experience and any of the end-to-end implementation of ASR tools such as ESPNET or FairSeq or Athena or Deep Speech