Related papers: Flexible Keyword Spotting based on Homogeneous Aud…

The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work…

In data dominated systems and applications, a concept of representing words in a numerical format has gained a lot of attention. There are a few approaches used to generate such a representation. An interesting issue that should be…

In recent years, there has been an increasing focus on user convenience, leading to increased interest in text-based keyword enrollment systems for keyword spotting (KWS). Since the system utilizes text input during the enrollment phase and…

We address the problem of tuning word embeddings for specific use cases and domains. We propose a new method that automatically combines multiple domain-specific embeddings, selected from a wide range of pre-trained domain-specific…

On one hand, recent advances in chatbots has led to a rising popularity in using these models for coding tasks. On the other hand, modern generative image models primarily rely on text encoders to translate semantic concepts into visual…

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…

We propose a novel framework for target speech extraction based on semantic information, called ConceptBeam. Target speech extraction means extracting the speech of a target speaker in a mixture. Typical approaches have been exploiting…

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Homograph disambiguation remains a significant challenge in grapheme-to-phoneme (G2P) conversion, especially for low-resource languages. This challenge is twofold: (1) creating balanced and comprehensive homograph datasets is…

Mapping words into a fixed-dimensional vector space is the backbone of modern NLP. While most word embedding methods successfully encode semantic information, they overlook phonetic information that is crucial for many tasks. We develop…

We propose an approach to extract speaker embeddings that are robust to speaking style variations in text-independent speaker verification. Typically, speaker embedding extraction includes training a DNN for speaker classification and using…

Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications. The most cutting-edge methods are attentional encoder-decoder frameworks that learn the alignment…

In this paper we present a data-driven, integrated approach to speaker verification, which maps a test utterance and a few reference utterances directly to a single score for verification and jointly optimizes the system's components using…

In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…

Speaker embeddings achieve promising results on many speaker verification tasks. Phonetic information, as an important component of speech, is rarely considered in the extraction of speaker embeddings. In this paper, we introduce phonetic…

Compositionally complex solid solution electrocatalysts span vast composition spaces, and even one materials system can contain more candidate compositions than can be measured exhaustively. Here we evaluate a label-free screening strategy…

Diversity in patent language is growing and makes finding synonyms for conducting patent searches more and more challenging. In addition to that, most approaches for dealing with diverse patent language are based on manual search and human…

We introduce a new approach, the ContrastiveTransformer, that produces acoustic word embeddings (AWEs) for the purpose of very low-resource keyword spotting. The ContrastiveTransformer, an encoder-only model, directly optimises the…