Related papers: Contrastive Augmentation: An Unsupervised Learning…
A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to…
One of the challenges in developing a high quality custom keyword spotting (KWS) model is the lengthy and expensive process of collecting training data covering a wide range of languages, phrases and speaking styles. We introduce Synth4Kws…
This paper introduces a novel approach for streaming openvocabulary keyword spotting (KWS) with text-based keyword enrollment. For every input frame, the proposed method finds the optimal alignment ending at the frame using connectionist…
Keyword Spotting (KWS) is an essential component in a smart device for alerting the system when a user prompts it with a command. As these devices are typically constrained by computational and energy resources, the KWS model should be…
Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large…
End-to-end (E2E) keyword search (KWS) has emerged as an alternative and complimentary approach to conventional keyword search which depends on the output of automatic speech recognition (ASR) systems. While E2E methods greatly simplify the…
Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large models, we employ light-weight networks to comply with tight…
Self-supervised learning (SSL) for automated speech recognition in terms of its emotional content, can be heavily degraded by the presence noise, affecting the efficiency of modeling the intricate temporal and spectral informative…
Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the…
This paper introduces the system submitted by the Yidun NISP team to the video keyword wakeup challenge. We propose a mandarin keyword spotting system (KWS) with several novel and effective improvements, including a big backbone (B) model,…
Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of…
Supervised learning can improve the design of state-of-the-art solvers for combinatorial problems, but labelling large numbers of combinatorial instances is often impractical due to exponential worst-case complexity. Inspired by the recent…
Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…
Keyword spotting (KWS) and speaker verification (SV) have been studied independently although it is known that acoustic and speaker domains are complementary. In this paper, we propose a multi-task network that performs KWS and SV…
We propose using cascaded classifiers for a keyword spotting (KWS) task on narrow-band (NB), 8kHz audio acquired in non-IID environments -- a more challenging task than most state-of-the-art KWS systems face. We present a model that…
Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment. This problem will be more challenging if KWS models are further required for edge devices due to their limited memory. To alleviate…
Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…
Contrastive learning-based recommendation algorithms have significantly advanced the field of self-supervised recommendation, particularly with BPR as a representative ranking prediction task that dominates implicit collaborative filtering.…
Data augmentation plays a critical role in generating high-quality positive and negative pairs necessary for effective contrastive learning. However, common practices involve using a single augmentation policy repeatedly to generate…
This paper introduces the system submitted by the DKU-SMIIP team for the Auto-KWS 2021 Challenge. Our implementation consists of a two-stage keyword spotting system based on query-by-example spoken term detection and a speaker verification…