×
Specifically, we examine whether adversarial or multi-task learning techniques help mitigate these biases, and improve the fairness of speaker recognition ...
Mar 17, 2022 · In this paper, we systematically evaluate the biases present in speaker recognition systems with respect to gender across a range of system ...
Dec 22, 2022 · It is crucial to accurately evaluate and mitigate biases present in machine learning (ML) based speech technologies, such as speaker recognition ...
Apr 1, 2023 · In this paper, we systematically evaluate the biases present in speaker recognition systems with respect to gender across a range of system ...
In this paper, we conduct the first comprehensive survey on speech-centric trustworthy ML topics related to privacy, safety, and fairness. In addition to ...
People also ask
Mar 18, 2022 · In this paper, we systematically evaluate the biases present in speaker recognition systems with respect to gender across a range of system ...
Alvi, M., Zisserman, A., Nellåker, C., 2018. Turning a blind eye: Explicit removal of biases and variation from deep neural network embeddings.
The results showed that specific types of data augmentation applied to both native and non-native-accented speech improve non-native-accented ASR while applying ...
Missing: study strategies
We present an in-depth empirical and ana- lytical study of bias in the machine learning development workflow of speaker verification, a voice biometric and core ...
Missing: strategies | Show results with:strategies
This paper introduces a set of approaches for bias mitigation for multimodal, multi-class confidence prediction of adult speakers in a work-like setting.