Related papers: Modular Adaptation of Multilingual Encoders to Wri…

Encoder models trained for the embedding of sentences or short documents have proven useful for tasks such as semantic search and topic modeling. In this paper, we present a version of the SwissBERT encoder model that we specifically…

This work investigates the performance of Voice Adaptation models for Swiss German dialects, i.e., translating Standard German text to Swiss German dialect speech. For this, we preprocess a large dataset of Swiss podcasts, which we…

The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland but seldom written. We collected a significant number of…

The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To alleviate this, we present $\textit{Franken-Adapter}$, a modular…

State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific…

This paper describes the winning approach in the Shared Task 3 at SwissText 2021 on Swiss German Speech to Standard German Text, a public competition on dialect recognition and translation. Swiss German refers to the multitude of Alemannic…

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality…

Swiss German is a dialect continuum whose natively acquired dialects significantly differ from the formal variety of the language. These dialects are mostly used for verbal communication and do not have standard orthography. This has led to…

Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate remarkable performance on general datasets, they can…

In this work, we studied the synthesis of Swiss German speech using different Text-to-Speech (TTS) models. We evaluated the TTS models on three corpora, and we found, that VITS models performed best, hence, using them for further testing.…

It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take…

Multilingual sentence encoders (MSEs) are commonly obtained by training multilingual language models to map sentences from different languages into a shared semantic space. As such, they are subject to curse of multilinguality, a loss of…

This paper investigates the challenges in building Swiss German speech translation systems, specifically focusing on the impact of dialect diversity and differences between Swiss German and Standard German. Swiss German is a spoken language…

We present SwissBERT, a masked language model created specifically for processing Switzerland-related text. SwissBERT is a pre-trained model that we adapted to news articles written in the national languages of Switzerland -- German,…

Despite rapid progress in large language models (LLMs), their performance on a vast majority of languages remains unsatisfactory. In this paper, we study building language-specific LLMs by adapting monolingual and multilingual LLMs. We…

As pre-trained models automate many code intelligence tasks, a widely used paradigm is to fine-tune a model on the task dataset for each programming language. A recent study reported that multilingual fine-tuning benefits a range of tasks…

Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this…

Integrating audio encoders with LLMs through connectors has enabled these models to process and comprehend audio modalities, significantly enhancing speech-to-text tasks, including automatic speech recognition (ASR) and automatic speech…

This paper investigates the optimal use of the multilingual encoder model mDeBERTa for tasks in three Germanic languages -- German, Swedish, and Icelandic -- representing varying levels of presence and likely data quality in mDeBERTas…

Multilingual automatic lyrics transcription (ALT) is a challenging task due to the limited availability of labelled data and the challenges introduced by singing, compared to multilingual automatic speech recognition. Although some…