Consistency Based Unsupervised Self-training For ASR Personalisation
On-device Automatic Speech Recognition (ASR) models trained on speech data of a large population might underperform for individuals unseen during training. This is due to a domain shift between user data and the original training data, differed by user's speaking characteristics and environmental acoustic conditions. ASR personalisation is a solution that aims to exploit user data to improve model robustness. The majority of ASR personalisation methods assume labelled user data for supervision. Personalisation without any labelled data is challenging due to limited data size and poor quality of recorded audio samples. This work addresses unsupervised personalisation by developing a novel consistency based training method via pseudo-labelling. Our method achieves a relative Word Error Rate Reduction (WERR) of 17.3% on unlabelled training data and 8.1% on held-out data compared to a pre-trained model, and outperforms the current state-of-the art methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users
Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. Thi…
You can't see what you can't see: Experimental evidence for how much relevant information may be missed due to Google's Web search personalisation
The influence of Web search personalisation on professional knowledge work is an understudied area. Here we investigate how public sector officials self-assess their dependency on the Google Web search engine, whether th…
Decision MakingCan Fair Federated Learning reduce the need for Personalisation?
Federated Learning (FL) enables training ML models on edge clients without sharing data. However, the federated model's performance on local data varies, disincentivising the participation of clients who benefit little f…
Federated LearningGenetic Programming for Smart Phone Personalisation
Personalisation in smart phones requires adaptability to dynamic context based on user mobility, application usage and sensor inputs. Current personalisation approaches, which rely on static logic that is developed a pri…
Unsupervised 3D Pose Estimation with Geometric Self-Supervision
We present an unsupervised learning approach to recover 3D human pose from 2D skeletal joints extracted from a single image. Our method does not require any multi-view image data, 3D skeletons, correspondences between 2D…
3D Human Pose Estimation3D Pose EstimationPose Estimationvalid