相关论文: Unsilencing Colonial Archives via Automated Entity…

Recently, sign language researchers have turned to sign language interpreted TV broadcasts, comprising (i) a video of continuous signing and (ii) subtitles corresponding to the audio content, as a readily available and large-scale source of…

Automatic Speech Recognition (ASR) systems, such as Whisper, achieve high transcription accuracy but struggle with named entities and numerical data, especially when proper formatting is required. These issues increase word error rate (WER)…

This work introduces an anonymization scheme for a corpus of texts to safeguard metadata from disclosure. It specifically aims to prevent large language models from identifying metadata associated with texts, thereby avoiding their…

Voice-enabled interactions provide more human-like experiences in many popular IoT systems. Cloud-based speech analysis services extract useful information from voice input using speech recognition techniques. The voice signal is a rich…

High-quality automatic speech recognition (ASR) is essential for virtual assistants (VAs) to work well. However, ASR often performs poorly on VA requests containing named entities. In this work, we start from the observation that many ASR…

Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this…

The advancements of AI-synthesized human voices have introduced a growing threat of impersonation and disinformation. It is therefore of practical importance to developdetection methods for synthetic human voices. This work proposes a new…

Participatory approaches to artificial intelligence are increasingly documented across public, civic, and humanitarian settings, but evidence about how participation is organized remains fragmented. This paper reports on the construction of…

Automatic Speech Recognition (ASR) technologies have transformed human-computer interaction; however, low-resource languages in Africa remain significantly underrepresented in both research and practical applications. This study…

Despite its scientific, political, and practical value, comprehensive information about human languages, in all their variety and complexity, is not readily obtainable and searchable. One reason is that many language data are collected as…

Long-term Web archives comprise Web documents gathered over longer time periods and can easily reach hundreds of terabytes in size. Semantic annotations such as named entities can facilitate intelligent access to the Web archive data.…

Accurately classifying accents and assessing accentedness in non-native speakers are both challenging tasks due to the complexity and diversity of accent and dialect variations. In this study, embeddings from advanced pre-trained language…

While extensively explored in text-based tasks, Named Entity Recognition (NER) remains largely neglected in spoken language understanding. Existing resources are limited to a single, English-only dataset. This paper addresses this gap by…

Named entity recognition (NER) is a fundamental component in many applications, such as Web Search and Voice Assistants. Although deep neural networks greatly improve the performance of NER, due to the requirement of large amounts of…

Building conversational agents that can have natural and knowledge-grounded interactions with humans requires understanding user utterances. Entity Linking (EL) is an effective and widely used method for understanding natural language text…

Significant advances are being made in speech emotion recognition (SER) using deep learning models. Nonetheless, training SER systems remains challenging, requiring both time and costly resources. Like many other machine learning tasks,…

A scientific paper is traditionally prefaced by an abstract that summarizes the paper. Recently, research highlights that focus on the main findings of the paper have emerged as a complementary summary in addition to an abstract. However,…

Generative audio models are rapidly advancing in both capabilities and public utilization -- several powerful generative audio models have readily available open weights, and some tech companies have released high quality generative audio…

Speech anonymization and de-identification have garnered significant attention recently, especially in the healthcare area including telehealth consultations, patient voiceprint matching, and patient real-time monitoring. Speaker identity…

We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions. We first formulate two…