相关论文: Parameter-efficient Adaptation of Multilingual Mul…

In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many…

Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challenging due to data scarcity and efficiency constraints.…

Automatic speech recognition for low-resource languages remains fundamentally constrained by the scarcity of labeled data and computational resources required by state-of-the-art models. We present a systematic investigation into…

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…

The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-of-the-art ASR. Despite LLMs being trained with an extensive…

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly established a bottleneck (BN) layer by pre-training on a…

Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR architectures connect a speech encoder to a large language model via a projection module,…

In this paper, we propose a self-training approach for automatic speech recognition (ASR) for low-resource settings. While self-training approaches have been extensively developed and evaluated for high-resource languages such as English,…

End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources. We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory,…

Large-scale multilingual ASR models like Whisper excel in high-resource settings but face challenges in low-resource scenarios, such as rare languages and code-switching (CS), due to computational costs and catastrophic forgetting. We…

Automatic Speech Recognition (ASR) models demonstrate outstanding performance on high-resource languages but face significant challenges when applied to low-resource languages due to limited training data and insufficient cross-lingual…

This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to…

This paper proposes a novel, resource-efficient approach to Visual Speech Recognition (VSR) leveraging speech representations produced by any trained Automatic Speech Recognition (ASR) model. Moving away from the resource-intensive trends…

Multilingual Automated Speech Recognition (ASR) systems allow for the joint training of data-rich and data-scarce languages in a single model. This enables data and parameter sharing across languages, which is especially beneficial for the…

Self-supervised pre-training of a speech foundation model, followed by supervised fine-tuning, has shown impressive quality improvements on automatic speech recognition (ASR) tasks. Fine-tuning separate foundation models for many downstream…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Parameter-efficient fine-tuning (PEFT) for personalizing automatic speech recognition (ASR) has recently shown promise for adapting general population models to atypical speech. However, these approaches assume a priori knowledge of the…

Automatic speech recognition (ASR) performance has improved drastically in recent years, mainly enabled by self-supervised learning (SSL) based acoustic models such as wav2vec2 and large-scale multi-lingual training like Whisper. A huge…

Automatic speech recognition (ASR) systems remain brittle on dysarthric and other atypical speech. Recent audio-language models raise the possibility of improving performance by conditioning on additional clinical context at inference time,…