Related papers: Multilingual Speech Evaluation: Case Studies on En…

Code-mixing, the blending of linguistic elements from distinct languages to form meaningful sentences, is common in multilingual settings, yielding hybrid languages like Hinglish and Minglish. Marathi, India's third most spoken language,…

Compared to English, the amount of labeled data for Indonesian text classification tasks is very small. Recently developed multilingual language models have shown its ability to create multilingual representations effectively. This paper…

Code-Switching (CS) is a common linguistic phenomenon in multilingual communities that consists of switching between languages while speaking. This paper presents our investigations on end-to-end speech recognition for Mandarin-English CS…

Evaluation of multilingual Large Language Models (LLMs) is challenging due to a variety of factors -- the lack of benchmarks with sufficient linguistic diversity, contamination of popular benchmarks into LLM pre-training data and the lack…

Discourse particles, such as \textit{well} and \textit{kind of}, are crucial components that enable LLMs to ``speak'' more like humans. They are used to convey emotions, intentions, and interpersonal meanings. However, existing studies have…

This study investigates whether phonological features can be applied in text-to-speech systems to generate native and non-native speech in English and Mandarin. We present a mapping of ARPABET/pinyin to SAMPA/SAMPA-SC and then to…

Recent advancements in Text-to-Speech (TTS) technology have led to natural-sounding speech for English, primarily due to the availability of large-scale, high-quality web data. However, many other languages lack access to such resources,…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Despite being neighbouring countries and sharing the language of Bahasa Melayu (ISO 639-3:ZSM), cultural and language education policy differences between Singapore and Malaysia led to differences in the translation of the "annoying"…

Multilingual Large Language Models (LLMs) exhibit remarkable cross-lingual abilities, yet often exhibit a systematic bias toward the representations from other languages, resulting in semantic interference when generating content in…

Audio language models process audio inputs using textual prompts for tasks like speech recognition and audio captioning. Although built on multilingual pre-trained components, most are trained primarily on English, limiting their usability…

Multilingual large language models (MLLMs) have shown impressive capabilities across a variety of languages. However, efficacy can differ greatly between different language families, especially for those with limited linguistic resources.…

The majority of existing speech emotion recognition models are trained and evaluated on a single corpus and a single language setting. These systems do not perform as well when applied in a cross-corpus and cross-language scenario. This…

Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on English. We introduce MuRating, a scalable framework that transfers high-quality English…

In this paper we present a new dataset, with musical excepts from the three main ethnic groups in Singapore: Chinese, Malay and Indian (both Hindi and Tamil). We use this new dataset to train different classification models to distinguish…

We present a multilingual, continuous backchannel prediction model for Japanese, English, and Chinese, and use it to investigate cross-linguistic timing behavior. The model is Transformer-based and operates at the frame level, jointly…

Speech-to-speech translation combines machine translation with speech synthesis, introducing evaluation challenges not present in either task alone. How to automatically evaluate speech-to-speech translation is an open question which has…

Automatic speech recognition (ASR) systems have traditionally been evaluated using English datasets, with the word error rate (WER) serving as the predominant metric. WER's simplicity and ease of interpretation have contributed to its…

Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to mitigate this is to train or fine-tune models with more…

Emotion classification is a challenging task in NLP due to the inherent idiosyncratic and subjective nature of linguistic expression, especially with code-mixed data. Pre-trained language models (PLMs) have achieved high performance for…