Related papers: Improving Spoken Language Identification with Map-…

Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. Recently, a novel multilingual model fusion technique has been proposed where a model is trained to learn cross-lingual…

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features…

Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data scarcity problem, data augmentation is commonly used for…

MixUp is a data augmentation strategy where additional samples are generated during training by combining random pairs of training samples and their labels. However, selecting random pairs is not potentially an optimal choice. In this work,…

Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap…

Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this…

In recent years, substantial work has been done on language tagging of code-mixed data, but most of them use large amounts of data to build their models. In this article, we present three strategies to build a word level language tagger for…

In this paper, we present MixRep, a simple and effective data augmentation strategy based on mixup for low-resource ASR. MixRep interpolates the feature dimensions of hidden representations in the neural network that can be applied to both…

Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing…

Spoken language identification (LID) technologies have improved in recent years from discriminating largely distinct languages to discriminating highly similar languages or even dialects of the same language. One aspect that has been mostly…

The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise…

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

A mixed sample data augmentation strategy is proposed to enhance the performance of models on audio scene classification, sound event classification, and speech enhancement tasks. While there have been several augmentation methods shown to…

Multilingual Automatic Speech Recognition (ASR) models are typically evaluated in a setting where the ground-truth language of the speech utterance is known, however, this is often not the case for most practical settings. Automatic Spoken…

Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively leveraging the options to optimize computational cost and…

Adapting pretrained large language models (LLMs) to various downstream tasks in tens or hundreds of human languages is computationally expensive. Parameter-efficient fine-tuning (PEFT) significantly reduces the adaptation cost, by tuning…

Language identification (LID) recognizes the language of a spoken utterance automatically. According to recent studies, LID models trained with an automatic speech recognition (ASR) task perform better than those trained with a LID task…

This paper explores the potential of leveraging Large Language Models (LLMs) for data augmentation in multilingual commonsense reasoning datasets where the available training data is extremely limited. To achieve this, we utilise several…