Dr. Andreas Stolcke of Alexa Speech organization at Amazon

Abstract:

Group fairness, or avoidance of large performance disparities for different cohorts of users, is a major concern as AI technologies find adoption in ever more application scenarios. In this talk I will present some recent work on fairness for speech-based technologies, specifically, speaker recognition and speech recognition.   For speaker recognition, I report on two algorithmic approaches to reduce performance variability across different groups.  In the first method, group-adapted fusion, we combine sub-models that are specialized for subpopulations that have very different representation (and therefore performance) in the data. The second method, adversarial reweighting, forces the model to focus on those portions of the population that are harder to recognize, without requiring a priori labels for speaker groups. For automatic speech recognition, I present methods for detecting and mitigating accuracy disparities as a function of geographic or demographic variables, principally by oversampling or adaptation based on group membership. The talk concludes with an application of synthetic speech generation (TTS) for filling in data gaps for a group of speakers with atypical speech, namely, stutter.

Related Publications:

Improving fairness in speaker verification via group-adapted fusion network

Adversarial reweighting for speaker verification fairness

Reducing geographic disparities in automatic speech recognition via elastic weight consolidation

Toward fairness in speech recognition: Discovery and mitigation of performance disparities

Stutter-TTS: Controlled synthesis and improved recognition of stuttered speech

Biography:

Andreas Stolcke is senior principal scientist in the Alexa Speech organization at Amazon. He obtained his PhD from UC Berkeley and then worked as a researcher at SRI International and Microsoft, before joining Amazon.  His research interests include computational linguistics, language modeling, speech recognition, speaker recognition and diarization, and paralinguistics, with over 300 papers and patents in these areas.  His open-source SRI Language Modeling Toolkit was widely used in academia (before becoming obsolete by virtue of deep neural network models).  Andreas is a Fellow of the IEEE and the International Speech Communication Association, and giving this talk as an IEEE Distinguished Industry Speaker.