相关论文: OmniLingo: Listening- and speaking-based language …

Large language models (LLMs) have demonstrated exceptional performance in various NLP applications. However, the majority of existing open-source LLMs are pre-trained primarily on English data and little part of other languages. This…

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…

The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tasks within a single…

Large language models (LLMs), such as ChatGPT, have demonstrated impressive performance in the text generation task, showing the ability to understand and respond to complex instructions. However, the performance of naive LLMs in speciffc…

We present Speech-MASSIVE, a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSIVE textual corpus. Speech-MASSIVE covers 12 languages from different families and inherits…

This paper presents Open Unified Speech Language Models (OpusLMs), a family of open foundational speech language models (SpeechLMs) up to 7B. Initialized from decoder-only text language models, the OpusLMs are continuously pre-trained on…

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…

We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface…

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…

In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised…

End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…

Federated Learning (FL) is a method of training machine learning models on private data distributed over a large number of possibly heterogeneous clients such as mobile phones and IoT devices. In this work, we propose a new federated…

Large language models (LLMs) have significantly advanced natural language processing, but their progress has yet to be equal across languages. While most LLMs are trained in high-resource languages like English, multilingual models…

Epsilon is an extensible platform of integrated and task-specific languages for model management. With solutions to the 2011 TTC Hello World case, this paper demonstrates some of the key features of the Epsilon Object Language (an extension…

Large Language Models (LLMs) have demonstrated remarkable language understanding and generation capabilities. However, training, deploying, and accessing these models pose notable challenges, including resource-intensive demands, extended…

Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose…

Component-based development is challenging in a distributed setting, for starters considering programming a task may involve the assembly of loosely-coupled remote components. In order for the task to be fulfilled, the supporting…

This paper presents a unified model to perform language and speaker recognition simultaneously and altogether. The model is based on a multi-task recurrent neural network where the output of one task is fed as the input of the other,…

Microservices is an emerging development paradigm where software is obtained by composing autonomous entities, called (micro)services. However, microservice systems are currently developed using general-purpose programming languages that do…

Instead of a monolithic programming language trying to cover all features of interest, some programming systems are designed by combining together simpler languages that cooperate to cover the same feature space. This can improve usability…