Related papers: Improved Audio Embeddings by Adjacency-Based Clust…

The goal of Audio-Visual Segmentation (AVS) is to localize and segment the sounding source objects from video frames. Research on AVS suffers from data scarcity due to the high cost of fine-grained manual annotations. Recent works attempt…

We propose a new application of embedding techniques for problem retrieval in adaptive tutoring. The objective is to retrieve problems whose mathematical concepts are similar. There are two challenges: First, like sentences, problems…

In this paper, we propose a novel representation for text documents based on aggregating word embedding vectors into document embeddings. Our approach is inspired by the Vector of Locally-Aggregated Descriptors used for image…

As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation. They capture semantic and syntactic relations among words but the…

Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…

Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the…

In this paper, we focus on the problem of content-based retrieval for audio, which aims to retrieve all semantically similar audio recordings for a given audio clip query. This problem is similar to the problem of query by example of audio,…

Efficient representation of text documents is an important building block in many NLP tasks. Research on long text categorization has shown that simple weighted averaging of word vectors for sentence representation often outperforms more…

Term clustering is important in biomedical knowledge graph construction. Using similarities between terms embedding is helpful for term clustering. State-of-the-art term embeddings leverage pretrained language models to encode terms, and…

Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be addressed by clustering the sentences in a training corpus…

Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks. However, their performances vary significantly across different tasks, implying that the word embeddings learnt by those…

Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding…

Large Lanugage Models (LLMs) are gaining increasing popularity in a variety of use cases, from language understanding and writing to assistance in application development. One of the most important aspects for optimal funcionality of LLMs…

Dual-encoder-based audio retrieval systems are commonly optimized with contrastive learning on a set of matching and mismatching audio-caption pairs. This leads to a shared embedding space in which corresponding items from the two…

Query-by-example search often uses dynamic time warping (DTW) for comparing queries and proposed matching segments. Recent work has shown that comparing speech segments by representing them as fixed-dimensional vectors --- acoustic word…

Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings. In this paper, the content-aware speaker embeddings…

Speech encodes multiple simultaneous attributes -- linguistic content, speaker identity, dialect, gender --that conventional single-vector embeddings conflate. We present a factor-partitioned embedding framework that maps each utterance…

There have been some works that learn a lexicon together with the corpus to improve the word embeddings. However, they either model the lexicon separately but update the neural networks for both the corpus and the lexicon by the same…

Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…