相关论文: Speech-MASSIVE: A Multilingual Speech Dataset for …

Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable comprehensive speech-based interactions. However, most advanced…

Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the…

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is…

End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained…

Figures of Speech (FoS) consist of multi-word phrases that are deeply intertwined with culture. While Neural Machine Translation (NMT) performs relatively well with the figurative expressions of high-resource languages, it often faces…

The SAFE Challenge evaluates synthetic speech detection across three tasks: unmodified audio, processed audio with compression artifacts, and laundered audio designed to evade detection. We systematically explore self-supervised learning…

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker…

Singlish, a Creole language rooted in English, is a key focus in linguistic research within multilingual and multicultural contexts. However, its spoken form remains underexplored, limiting insights into its linguistic structure and…

This study introduces CLASP (Contrastive Language-Speech Pretraining), a multilingual, multimodal representation tailored for audio-text information retrieval. CLASP leverages the synergy between spoken content and textual data. During…

Speech is one of the most effective means of communication and is full of information that helps the transmission of utterer's thoughts. However, mainly due to the cumbersome processing of acoustic features, phoneme or word posterior…

Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a…

The development of Large Speech-Language Models (LSLMs) has been slowed by fragmented architectures and a lack of transparency, hindering the systematic comparison and reproducibility of research. Unlike in the vision-language domain, the…

Simultaneous speech-to-speech translation (SimulS2S) is essential for real-time multilingual communication, with increasing integration into meeting and streaming platforms. Despite this, SimulS2S remains underexplored in research, where…

Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional…

Spoken language understanding (SLU) is a task aiming to extract high-level semantics from spoken utterances. Previous works have investigated the use of speech self-supervised models and textual pre-trained models, which have shown…

We release to the community six large-scale sense-annotated datasets in multiple language to pave the way for supervised multilingual Word Sense Disambiguation. Our datasets cover all the nouns in the English WordNet and their translations…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

High-quality Text-to-Speech (TTS) model training requires extensive and diverse text and speech data. It is challenging to procure such data from real sources due to issues of domain specificity, licensing, and scalability. Large language…

Amidst the rapid advances of large language models (LLMs), most LLMs still struggle with mixed-language inputs, limited Codeswitching (CSW) datasets, and evaluation biases, which hinder their deployment in multilingual societies. This…

Describes an audio dataset of spoken words designed to help train and evaluate keyword spotting systems. Discusses why this task is an interesting challenge, and why it requires a specialized dataset that is different from conventional…