相关论文: Topic Model Robustness to Automatic Speech Recogni…

Prompt-based learning's efficacy across numerous natural language processing tasks has led to its integration into dense passage retrieval. Prior research has mainly focused on enhancing the semantic understanding of pre-trained language…

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to differences in acoustic…

This study addresses an image-matching problem in challenging cases, such as large scene variations or textureless scenes. To gain robustness to such situations, most previous studies have attempted to encode the global contexts of a scene…

With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in the recent days. More and more applications relying on speech synthesis technology…

Retrieval-augmented generation (RAG) systems rely on accurate document retrieval to ground large language models (LLMs) in external knowledge, yet retrieval quality often degrades in corpora where topics overlap and thematic variation is…

We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion. This is done by specifying a fixed time budget, and then automatically choosing location and size of segments for…

Systems that can associate images with their spoken audio captions are an important step towards visually grounded language learning. We describe a scalable method to automatically generate diverse audio for image captioning datasets. This…

Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introduce a human-annotated benchmark based on Czech historical documents, containing human-defined…

This paper proposes a modeling framework for dynamic topic evolution based on temporal large language models. The method first uses a large language model to obtain contextual embeddings of text and then introduces a temporal decay function…

In this paper we propose a new approach to evaluate the informativeness of transcriptions coming from Automatic Speech Recognition systems. This approach, based in the notion of informativeness, is focused on the framework of Automatic Text…

Latent Dirichlet allocation (LDA) is a popular topic modeling technique in academia but less so in industry, especially in large-scale applications involving search engine and online advertising systems. A main underlying reason is that the…

The time at which a message is communicated is a vital piece of metadata in many real-world natural language processing tasks such as Topic Detection and Tracking (TDT). TDT systems aim to cluster a corpus of news articles by event, and in…

Dialog evaluation is a challenging problem, especially for non task-oriented dialogs where conversational success is not well-defined. We propose to evaluate dialog quality using topic-based metrics that describe the ability of a…

Dense video captioning is a task of localizing interesting events from an untrimmed video and producing textual description (captions) for each localized event. Most of the previous works in dense video captioning are solely based on visual…

In this work, automatic analysis of themes contained in a large corpora of judgments from public procurement domain is performed. The employed technique is unsupervised latent Dirichlet allocation (LDA). In addition, it is proposed, to use…

We propose and evaluate an automated pipeline for discovering significant topics from legal decision texts by passing features synthesized with topic models through penalised regressions and post-selection significance tests. The method…

An initial procedure in text-as-data applications is text preprocessing. One of the typical steps, which can substantially facilitate computations, consists in removing infrequent words believed to provide limited information about the…

The rapid advancement of spoofing algorithms necessitates the development of robust detection methods capable of accurately identifying emerging fake audio. Traditional approaches, such as finetuning on new datasets containing these novel…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Learning an effective speaker representation is crucial for achieving reliable performance in speaker verification tasks. Speech signals are high-dimensional, long, and variable-length sequences containing diverse information at each…