ML- Audio (TTS & Voice Modelling)

• Design and implement Text-to-Speech (TTS) systems to produce natural and expressive synthetic voices.
• Collaborate with cross-functional teams to integrate TTS models into various applications and services.
• Voice Modeling:
• Develop voice synthesis models that capture the nuances of human speech for a diverse range of applications.
• Work on voice modulation and expression to enhance the naturalness of synthesized voices.
• Data Processing and Annotation:
• Work closely with data scientists to pre-process and annotate large voice datasets for training TTS and voice modelling models.
• Implement strategies for effective data augmentation and feature extraction.
• Optimization and Scalability:
• Optimize TTS and voice modelling systems for efficiency, scalability, and seamless integration into production environments.
• Collaborate with DevOps and infrastructure teams to ensure smooth deployment and operation.
• Research and Innovation:
• Stay abreast of the latest advancements in TTS, voice synthesis, and related fields.
• Contribute to the development of proprietary advancements, incorporating state-of-the-art techniques into our projects.
• Requirements

• Masters or Ph.D. in Computer Science, Machine Learning, or a related field but however if you are a great problem solver, a dropout is also welcome.
• Proven experience in developing Text-to-Speech (TTS) systems and voice modelling.
• Proficiency in machine learning frameworks such as TensorFlow or PyTorch.Strong programming skills in Python and familiarity with relevant libraries and tools.
• Solid understanding of signal processing, speech synthesis, and related technologies.
• Experience with voice data processing, annotation, and dataset preparation.Excellent problem-solving skills and ability to work collaboratively in a team

environment.

• This position is for the Nagpur office, candidates willing to relocate to Nagpur may only apply.