相关论文: Metric Learning for User-defined Keyword Spotting

Open-vocabulary keyword spotting (KWS) in continuous speech streams holds significant practical value across a wide range of real-world applications. While increasing attention has been paid to the role of different modalities in KWS, their…

We propose a practical approach based on federated learning to solve out-of-domain issues with continuously running embedded speech-based models such as wake word detectors. We conduct an extensive empirical study of the federated averaging…

In sponsored search, retrieving synonymous keywords for exact match type is important for accurately targeted advertising. Data-driven deep learning-based method has been proposed to tackle this problem. An apparent disadvantage of this…

User intent understanding is a crucial step in designing both conversational agents and search engines. Detecting or inferring user intent is challenging, since the user utterances or queries can be short, ambiguous, and contextually…

Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep…

Keyword Spotting (KWS) models on embedded devices should adapt fast to new user-defined words without forgetting previous ones. Embedded devices have limited storage and computational resources, thus, they cannot save samples or update…

Pre-trained language models such as BERT have been proved to be powerful in many natural language processing tasks. But in some text classification applications such as emotion recognition and sentiment analysis, BERT may not lead to…

The training of deep-learning-based text classification models relies heavily on a huge amount of annotation data, which is difficult to obtain. When the labeled data is scarce, models tend to struggle to achieve satisfactory performance.…

This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their…

Target-guided open-domain conversation aims to proactively and naturally guide a dialogue agent or human to achieve specific goals, topics or keywords during open-ended conversations. Existing methods mainly rely on single-turn datadriven…

Word embeddings are traditionally trained on a large corpus in an unsupervised setting, with no specific design for incorporating domain knowledge. This can lead to unsatisfactory performances when training data originate from heterogeneous…

We explore the application of deep residual learning and dilated convolutions to the keyword spotting task, using the recently-released Google Speech Commands Dataset as our benchmark. Our best residual network (ResNet) implementation…

The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…

For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this, we optimize acoustic and text encoders using deep metric…

In this work, we present a unified model that can handle both Keyword Spotting and Word Recognition with the same network architecture. The proposed network is comprised of a non-recurrent CTC branch and a Seq2Seq branch that is further…

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…

Evaluation of keyword spotting (KWS) systems that detect keywords in speech is a challenging task under realistic privacy constraints. The KWS is designed to only collect data when the keyword is present, limiting the availability of hard…

Till now, attention-based models have been used with great success in the keyword spotting problem domain. However, in light of recent advances in deep learning, the question arises whether self-attention is truly irreplaceable for…

In this paper, we study an under-explored area of language and vocabulary learning: keyword mnemonics, a technique for memorizing vocabulary through memorable associations with a target word via a verbal cue. Typically, creating verbal cues…

Global models are trained to be as generalizable as possible, with user invariance considered desirable since the models are shared across multitudes of users. As such, these models are often unable to produce personalized responses for…