Speech Scientist

Suzhou, China
Main Location
Redmond, WA, United States
Open jobs

Beijing, one of the most vibrant cities in the world. Come to experience the Chinese culture, explosive growth, great shopping and amazing food. The city is very international and easy to live in. Suzhou, one of the most beautiful cities in China. It is renowned for its beautiful tone bridges, pagodas and meticulously designed gardens, about 100 km northwest of Shanghai. Responsibilities Do you want to change the way the world interacts with computers? Do you want to be part of a team that pushes the Natural User Experience to the next level? Do you dream that one day, our world will be populated by robots that will help to do our jobs? Do you want to challenge yourself by innovating in an area that is new to Microsoft yet is an important strategic bet? Do you want to make Microsoft products not only accessible, but highly-functional?   As both computational horsepower and storage capacity reach unprecedented levels, the human race is getting closer and closer to that dream of the natural user interface. Each day we are stepping closer toward being able to interact with computers the same way we interact with another human being. Speech Synthesis (Text-To-Speech) is a key part of that vision. The TTS team’s mission is to build the most human-sounding voices for as many languages in the world as possible, and to create world

Responsibilities

Responsibilities:  

The TTS team is looking for a motivated, self-driven software development engineer/scientist to drive the development of our speech synthesis engines. Responsibilities include

1. Advance the state of the art of TTS technology.

2. Improve the speech synthesis quality in terms of naturalness, expressiveness and intelligence.

3. Provides good guidance on core speech synthesis algorithm investigations.  

4. Work on collaborations with Microsoft Research in the research frontier.

5. Drive the speech synthesis technology roadmap for Microsoft.

Qualifications

Qualifications:

 

1. MSc or PhD in CS/EE (with focus in one or more of Speech Applications) or equivalent experience.

2. Minimum of 3 years experiences working in speech domain.

3. Effective communication skills and ability to work in a collaborative environment.

4. Full understanding of the tradeoffs for decisions made in speech synthesis.

5. Deep Understanding of current speech synthesis research in at least one area (ex: Parametric Speech Synthesis – HMM, DNN, LSTM, etc., Unit concatenation speech synthesis, Voice Adaptation, Prosody Modeling etc.).

6. Ability to use multiple orthogonal processes to diagnosis voice quality issues.

7. Ability to reproduce high performance results in voice quality improvement on a consistent basis.

8. Ability to make major modifications speech tools and algorithms to support projects and substantial impact on product success.

9. Software development skills, aptitude for process design.

10. Ability to program in scripting languages.

 

Microsoft is an equal opportunity employer and supports workforce diversity.

Help us maintain the quality of jobs posted on PowerToFly. Let us know if this job is closed.
Mission
We're a community of women leveraging our connections into top companies to help underrepresented women get the roles they've always deserved. Simultaneously, we work to build truly inclusive hiring processes and environments where women can thrive and not just survive.
Are you hiring? Join our platform for diversifiying your team