The reviewed record of science sign in
Pith

arxiv: 2306.12015 · v1 · pith:WWNMMEJG · submitted 2023-06-21 · eess.AS · cs.SD

Federated Self-Learning with Weak Supervision for Speech Recognition

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WWNMMEJGrecord.jsonopen to challenge →

classification eess.AS cs.SD
keywords learningmodelsself-learningsignalsapproachconversationalfederatedmodel
0
0 comments X
read the original abstract

Automatic speech recognition (ASR) models with low-footprint are increasingly being deployed on edge devices for conversational agents, which enhances privacy. We study the problem of federated continual incremental learning for recurrent neural network-transducer (RNN-T) ASR models in the privacy-enhancing scheme of learning on-device, without access to ground truth human transcripts or machine transcriptions from a stronger ASR model. In particular, we study the performance of a self-learning based scheme, with a paired teacher model updated through an exponential moving average of ASR models. Further, we propose using possibly noisy weak-supervision signals such as feedback scores and natural language understanding semantics determined from user behavior across multiple turns in a session of interactions with the conversational agent. These signals are leveraged in a multi-task policy-gradient training approach to improve the performance of self-learning for ASR. Finally, we show how catastrophic forgetting can be mitigated by combining on-device learning with a memory-replay approach using selected historical datasets. These innovations allow for 10% relative improvement in WER on new use cases with minimal degradation on other test sets in the absence of strong-supervision signals such as ground-truth transcriptions.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.