Related papers: Research on Architectures for Integrated Speech/La…

Text-to-image generation has attracted significant interest from researchers and practitioners in recent years due to its widespread and diverse applications across various industries. Despite the progress made in the domain of vision and…

Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers. In this paper, we tackle…

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former,…

The ability of large language models (LLMs) to engage in credible dialogues with humans, taking into account the training data and the context of the conversation, has raised discussions about their ability to exhibit intrinsic motivations,…

Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…

This paper presents the open-system submission by the In2x research team for the WMT25 General Machine Translation Shared Task. Our submission focuses on Japanese-related translation tasks, aiming to explore a generalizable paradigm for…

Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in…

Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture…

Research on deep learning-powered voice conversion (VC) in speech-to-speech scenarios is getting increasingly popular. Although many of the works in the field of voice conversion share a common global pipeline, there is a considerable…

Speech understanding is essential for interpreting the diverse forms of information embedded in spoken language, including linguistic, paralinguistic, and non-linguistic cues that are vital for effective human-computer interaction. The…

One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process. In an effort to move toward automated evaluation of…

In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging transfer learning across…

The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers…

Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response…

This paper presents statistical language and translation models based on collections of small finite state machines we call ``head automata''. The models are intended to capture the lexical sensitivity of N-gram models and direct…

The Spoken Language Translator is a prototype for practically useful systems capable of translating continuous spoken language within restricted domains. The prototype system translates air travel (ATIS) queries from spoken English to…

Documenting the construction of an NMT (Neural Machine Translation) system for En/Ja based on the Transformer architecture leveraging the OpenNMT framework. A systematic exploration of corpora pre-processing, hyperparameter tuning and model…

In this paper, we propose a novel deep neural network architecture, Speech2Vec, for learning fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to…

With the rapid growth of large language models (LLMs), a wide range of methods have been developed to distribute computation and memory across hardware devices for efficient training and inference. While existing surveys provide descriptive…