Related papers: Research on Architectures for Integrated Speech/La…
This volume contains the papers presented at the 21st International Overture Workshop, held on the 10th of March 2023. This event was the latest in a series of workshops around the Vienna Development Method (VDM), the open-source project…
Recent advances in large language models (LLMs) have attracted significant interest in extending their capabilities to multimodal scenarios, particularly for speech-to-speech conversational systems. However, existing multimodal models…
Pre-trained transformer language models (TLMs) have recently refashioned natural language processing (NLP): Most state-of-the-art NLP models now operate on top of TLMs to benefit from contextualization and knowledge induction. To explain…
The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we…
We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time. The model represents words and contexts by latent trajectories in an embedding space. At each moment in…
Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high…
The emergence of small vision-language models (sVLMs) marks a critical advancement in multimodal AI, enabling efficient processing of visual and textual data in resource-constrained environments. This survey offers a comprehensive…
Recent breakthroughs in large language models (LLM) have stirred up global attention, and the research has been accelerating non-stop since then. Philosophers and psychologists have also been researching the structure of language for…
The future of autonomous vehicles lies in the convergence of human-centric design and advanced AI capabilities. Autonomous vehicles of the future will not only transport passengers but also interact and adapt to their desires, making the…
We describe an architecture for implementing spoken natural language dialogue interfaces to semi-autonomous systems, in which the central idea is to transform the input speech signal through successive levels of representation corresponding…
This is an interim report discussing possible guidelines for the assessment and evaluation of projects developing speech and language systems. It was prepared at the request of the European Commission DG XIII by an ad hoc study group, and…
To participate in the Isometric Spoken Language Translation Task of the IWSLT 2022 evaluation, constrained condition, AppTek developed neural Transformer-based systems for English-to-German with various mechanisms of length control, ranging…
Recent works in neural machine translation have begun to explore document translation. However, translating online multi-speaker conversations is still an open problem. In this work, we propose the task of translating Bilingual…
We investigate whether \emph{LLM-based agents} can develop task-oriented communication protocols that differ from standard natural language in collaborative reasoning tasks. Our focus is on two core properties such task-oriented protocols…
While the progress of machine translation of written text has come far in the past several years thanks to the increasing availability of parallel corpora and corpora-based training technologies, automatic translation of spoken text and…
Text-to-speech synthesis (TTS) is a task to convert texts into speech. Two of the factors that have been driving TTS are the advancements of probabilistic models and latent representation learning. We propose a TTS method based on latent…
Different languages have distinct phonetic systems and vary in their prosodic features making it challenging to develop a Text-to-Speech (TTS) model that can effectively synthesise speech in multilingual settings. Furthermore, TTS…
Single-stage text-to-speech models have been actively studied recently, and their results have outperformed two-stage pipeline systems. Although the previous single-stage model has made great progress, there is room for improvement in terms…
This paper discusses the construction, fine-tuning, and deployment of BeaverTalk, a cascaded system for speech-to-text translation as part of the IWSLT 2025 simultaneous translation task. The system architecture employs a VAD segmenter for…
Since language models are used to model a wide variety of languages, it is natural to ask whether the neural architectures used for the task have inductive biases towards modeling particular types of languages. Investigation of these biases…