Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models

• URL: http://arxiv.org/abs/2203.15975v1
• Date: Wed, 30 Mar 2022 01:27:39 GMT
• Title: Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models
• Authors: Vineet Garg, Ognjen Rudovic, Pranay Dighe, Ahmed H. Abdelaziz, Erik Marchi, Saurabh Adya, Chandra Dhir, Ahmed Tewfik
• Abstract summary: We address the problem of detecting speech directed to a device that does not contain a specific wake-word. Specifically, we focus on audio coming from a touch-based invocation.
• Score: 13.456066434598155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address the problem of detecting speech directed to a device that does not contain a specific wake-word. Specifically, we focus on audio coming from a touch-based invocation. Mitigating virtual assistants (VAs) activation due to accidental button presses is critical for user experience. While the majority of approaches to false trigger mitigation (FTM) are designed to detect the presence of a target keyword, inferring user intent in absence of keyword is difficult. This also poses a challenge when creating the training/evaluation data for such systems due to inherent ambiguity in the user's data. To this end, we propose a novel FTM approach that uses weakly-labeled training data obtained with a newly introduced data sampling strategy. While this sampling strategy reduces data annotation efforts, the data labels are noisy as the data are not annotated manually. We use these data to train an acoustics-only model for the FTM task by regularizing its loss function via knowledge distillation from an ASR-based (LatticeRNN) model. This improves the model decisions, resulting in 66% gain in accuracy, as measured by equal-error-rate (EER), over the base acoustics-only model. We also show that the ensemble of the LatticeRNN and acoustic-distilled models brings further accuracy improvement of 20%.

Related papers

• Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models [84.8919069953397]
  Self-TAught Recognizer (STAR) is an unsupervised adaptation framework for speech recognition systems. We show that STAR achieves an average of 13.5% relative reduction in word error rate across 14 target domains. STAR exhibits high data efficiency that only requires less than one-hour unlabeled data.
  arXiv  Detail & Related papers  (2024-05-23T04:27:11Z)
• Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models [52.04189118767758]
  Generalization is a main issue for current audio deepfake detectors. In this paper we study the potential of large-scale pre-trained models for audio deepfake detection.
  arXiv  Detail & Related papers  (2024-05-03T15:27:11Z)
• Analyze the Robustness of Classifiers under Label Noise [5.708964539699851]
  Label noise in supervised learning, characterized by erroneous or imprecise labels, significantly impairs model performance. This research focuses on the increasingly pertinent issue of label noise's impact on practical applications.
  arXiv  Detail & Related papers  (2023-12-12T13:51:25Z)
• Combating Label Noise With A General Surrogate Model For Sample Selection [84.61367781175984]
  We propose to leverage the vision-language surrogate model CLIP to filter noisy samples automatically. We validate the effectiveness of our proposed method on both real-world and synthetic noisy datasets.
  arXiv  Detail & Related papers  (2023-10-16T14:43:27Z)
• MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection [76.97324120775475]
  Cross-domain keypoint detection methods always require accessing the source data during adaptation. This paper considers source-free domain adaptive keypoint detection, where only the well-trained source model is provided to the target domain.
  arXiv  Detail & Related papers  (2023-02-09T12:06:08Z)
• Learning to Detect Noisy Labels Using Model-Based Features [16.681748918518075]
  We propose Selection-Enhanced Noisy label Training (SENT) SENT does not rely on meta learning while having the flexibility of being data-driven. It improves performance over strong baselines under the settings of self-training and label corruption.
  arXiv  Detail & Related papers  (2022-12-28T10:12:13Z)
• On-the-fly Denoising for Data Augmentation in Natural Language Understanding [101.46848743193358]
  We propose an on-the-fly denoising technique for data augmentation that learns from soft augmented labels provided by an organic teacher model trained on the cleaner original data. Our method can be applied to general augmentation techniques and consistently improve the performance on both text classification and question-answering tasks.
  arXiv  Detail & Related papers  (2022-12-20T18:58:33Z)
• Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features [43.41573458276422]
  We introduce a novel learning-based solution, leveraging a noise detector, instanced by an LSTM network. The proposed method trains the noise detector in a supervised manner using the dataset with synthesized label noises. Results show that the proposed method precisely detects mislabeled samples on various datasets without further adaptation.
  arXiv  Detail & Related papers  (2022-12-19T09:39:30Z)
• Continual Learning for Fake Audio Detection [62.54860236190694]
  This paper proposes detecting fake without forgetting, a continual-learning-based method, to make the model learn new spoofing attacks incrementally. Experiments are conducted on the ASVspoof 2019 dataset.
  arXiv  Detail & Related papers  (2021-04-15T07:57:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.