Voice/Speech Architect - Technical Expert

This position leads the development and deployment of Honeywell Voice/Speech Speech product/service line strategy. This role will support and enable growth by leveraging internal talent, IT capabilities and external ecosystem.

Role :

As a Voice/Speech Architect, the candidate is expected to function as the leader for all the domain initiatives. The candidate will be responsible for creating the roadmap for HTS offerings in Voice/ Speech domain.

Job Responsibilities :

- Work with strategic industry partners and ecosystem to implement Voice/ Speech embedded solutions which will place Honeywell in a key strategic position.

- Partner with Honeywell's High Growth Regions to create customized solutions which can drive significant customer value.

- Should mentor Senior Engineers to design and develop new algorithms in speech, speaker recognition and signal processing

- Should be hands-on and well versed with the IT practices and processes like proof of concept (POC) and prototyping. Should be able to drive results - right and fast.

- Assess voice/ speech technology choices to determine relevance for Honeywell's offerings.

- Act as a trusted advisor for Honeywell's select clients from a voice solutions standpoint.

- Establish and maintain the strong partnership with business leadership, Engineering, Strategic Marketing, and IT Innovation and delivery teams in making technology and architectural choices to bring in the right software, hardware and people capabilities, inside and outside of HON.

- Should be a thought leader in the domain and look for avenues to leverage industry practices like - open source-, crowd sourcing, etc.

- Be Honeywell's evangelist for Voice solutions internally and externally.

Qualifications :

- Bachelor's or Masters degree in Engineering

- Should have experience in building end-to-end systems for conversational & dialog-oriented speech applications and command and control applications.

- Around 10+ years of relevant experience in end-end Speech/Voice domain which includes hardware and software design, development and deployment of voice applications at customer locations.

- Should have experience in the following areas of speech enhancement: Voice activity detection; De-reverberation; Echo cancellation, multi-mic noise reduction, non-linear processing and control.

- Should be well versed with speech related technologies - speech recognition, speaker recognition, language recognition and natural language processing and natural language understanding.

- Experience in one or more of machine learning in an audio context - deep learning, neural networks, Bayesian, SVM. Should also have strong Matlab, C/C++, Python skills.

- A strong understanding of speech technologies for embedded devices, knowledge of voice-based user interfaces, and good understanding of embedded speech engines like Sensory/Rubidium/CMU Sphinx.

- Expert knowledge of embedded speech operating systems.

- Good experience in building acoustic & language models with multiple speech corpus

- Excellent experience in programming languages like C/C++/Java.

- Working knowledge of QNX, Embedded Linux, and/or Android.

- Strong attention to detail.

- Exemplary verbal and written communication skills.