Related papers: Learning Acoustic Word Embeddings with Temporal Co…

We present a novel learning method for word embeddings designed for relation classification. Our word embeddings are trained by predicting words between noun pairs using lexical relation-specific features on a large unlabeled corpus. This…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

Audio captioning is the task of automatically creating a textual description for the contents of a general audio signal. Typical audio captioning methods rely on deep neural networks (DNNs), where the target of the DNN is to map the input…

Query-by-example spoken term detection (QbE-STD) searches for matching words or phrases in an audio dataset using a sample spoken query. When annotated data is limited or unavailable, QbE-STD is often done using template matching methods…

Contextualised word embeddings generated from Neural Language Models (NLMs), such as BERT, represent a word with a vector that considers the semantics of the target word as well its context. On the other hand, static word embeddings such as…

Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was…

We explore why deep convolutional neural networks (CNNs) with small two-dimensional kernels, primarily used for modeling spatial relations in images, are also effective in speech recognition. We analyze the representations learned by deep…

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…

In this paper we introduce a method for visually analyzing contextualized embeddings produced by deep neural network-based language models. Our approach is inspired by linguistic probes for natural language processing, where tasks are…

Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…

In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either extract or synthesize temporal information (e.g.,…

We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space to enable knowledge and resource transfer across languages. Beyond word alignment, we…

Embedding-based neural retrieval is a prevalent approach to address the semantic gap problem which often arises in product search on tail queries. In contrast, popular queries typically lack context and have a broad intent where additional…

Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs $…

Pre-trained language models have been widely exploited to learn dense representations of documents and queries for information retrieval. While previous efforts have primarily focused on improving effectiveness and user satisfaction,…

Query-by-example spoken term detection (QbE-STD) is typically constrained by transcribed data scarcity and language specificity. This paper introduces a novel, language-agnostic QbE-STD model leveraging image processing techniques and…

A novel sentence embedding method built upon semantic subspace analysis, called semantic subspace sentence embedding (S3E), is proposed in this work. Given the fact that word embeddings can capture semantic relationship while semantically…

Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic features with clear physical meaning, these embeddings lack…

Our objective is video retrieval based on natural language queries. In addition, we consider the analogous problem of retrieving sentences or generating descriptions given an input video. Recent work has addressed the problem by embedding…

In this paper, we study zero-shot learning in audio classification via semantic embeddings extracted from textual labels and sentence descriptions of sound classes. Our goal is to obtain a classifier that is capable of recognizing audio…