Learning When to Trust Which Teacher for Weakly Supervised ASR
Automatic speech recognition (ASR) training can utilize multiple experts as teacher models, each trained on a specific domain or accent. Teacher models may be opaque in nature since their architecture may be not be known or their training cadence is different from that of the student ASR model. Still, the student models are updated incrementally using the pseudo-labels generated independently by the expert teachers. In this paper, we exploit supervision from multiple domain experts in training student ASR models. This training strategy is especially useful in scenarios where few or no human transcriptions are available. To that end, we propose a Smart-Weighter mechanism that selects an appropriate expert based on the input audio, and then trains the student model in an unsupervised setting. We show the efficacy of our approach using LibriSpeech and LibriLight benchmarks and find an improvement of 4 to 25\% over baselines that uniformly weight all the experts, use a single expert model, or combine experts using ROVER.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Learning to Rank from Samples of Variable Quality
Training deep neural networks requires many training samples, but in practice, training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from…
Document RankingLearning-To-RankFidelity-Weighted Learning
Training deep neural networks requires many training samples, but in practice training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from …
Ad-Hoc Information RetrievalInformation RetrievalRetrievalSeeking Flat Minima with Mean Teacher on Semi- and Weakly-Supervised Domain Generalization for Object Detection
Object detectors do not work well when domains largely differ between training and testing data. To overcome this domain gap in object detection without requiring expensive annotations, we consider two problem settings: …
Domain AdaptationDomain GeneralizationObjectobject-detection+2Learning from Samples of Variable Quality
Training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other sources of weak supervision such as crowd-sourcing. This c…
BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation
Labeling objects with pixel-wise segmentation requires a huge amount of human labor compared to bounding boxes. Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with p…
Box-supervised Instance SegmentationInstance SegmentationSegmentationSemantic Segmentation+2