Rita Singh

Title: Rita Singh: Innovator in Speech Processing Technologies

Introduction

Rita Singh is a prominent inventor based in Watertown, MA (US), known for her significant contributions to the field of speech processing. With a total of 4 patents, she has developed innovative methods that enhance the classification and segmentation of audio signals.

Latest Patents

One of her latest patents is titled "Classification in likelihood spaces." This method classifies data into multiple classes, ensuring that the data in each class has a class-conditional probability distribution. The class-conditional probability distributions of measured data are projected into a likelihood space, where they are classified according to a discriminant classifier.

Another notable patent is "Classifier-based non-linear projection for continuous speech segmentation." This method segments an audio signal into non-speech and speech segments by first extracting high-dimensional spectral features. These features are then projected non-linearly to low-dimensional features, which are averaged using a sliding window and weighted averages. A linear discriminant is applied to determine a threshold that separates the low-dimensional features, allowing for effective classification of speech segments.

Career Highlights

Rita Singh is currently employed at Mitsubishi Electric Research Laboratories, Inc., where she continues to push the boundaries of speech processing technology. Her work has been instrumental in developing advanced methods that improve the accuracy and efficiency of audio signal classification.

Collaborations

Throughout her career, Rita has collaborated with esteemed colleagues, including Bhiksha Ramakrishnan and Bhiksha Raj. These collaborations have further enriched her research and contributed to the advancement of the field.

Conclusion

Rita Singh's innovative work in speech processing technologies has made a significant impact on the industry. Her patents reflect her dedication to enhancing audio signal classification and segmentation, showcasing her as a leading inventor in her field.