Related papers: Resource-Efficient Transfer Learning From Speech F…

End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…

The performance of child speech recognition is generally less satisfactory compared to adult speech due to limited amount of training data. Significant performance degradation is expected when applying an automatic speech recognition (ASR)…

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

In recent years, deep learning models have demonstrated remarkable success in various domains, such as computer vision, natural language processing, and speech recognition. However, the generalization capabilities of these models can be…

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…

Foundational vision transformer models have shown impressive few shot performance on many vision tasks. This research presents a novel investigation into the application of parameter efficient fine-tuning methods within an active learning…

Adapters are an efficient, composable alternative to full fine-tuning of pre-trained models and help scale the deployment of large ASR models to many tasks. In practice, a task ID is commonly prepended to the input during inference to route…

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…

Alongside acoustic information, linguistic features based on speech transcripts have been proven useful in Speech Emotion Recognition (SER). However, due to the scarcity of emotion labelled data and the difficulty of recognizing emotional…

Foundation models have shown superior performance for speech emotion recognition (SER). However, given the limited data in emotion corpora, finetuning all parameters of large pre-trained models for SER can be both resource-intensive and…

Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important issue associated with such approaches is that the intermediate…

Automatic Speech Recognition (ASR) systems have found their use in numerous industrial applications in very diverse domains. Since domain-specific systems perform better than their generic counterparts on in-domain evaluation, the need for…

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…

Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…

Personalizing automatic speech recognition (ASR) systems for non-normative speech, such as dysarthric and aphasic speech, is challenging. While speaker-specific fine-tuning (SS-FT) is widely used, it is typically initialized directly from a…

Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result. However, the…

Using self-supervised learning (SSL) models has significantly improved performance for downstream speech tasks, surpassing the capabilities of traditional hand-crafted features. This study investigates the amalgamation of SSL models, with…

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…

This work explores better adaptation methods to low-resource languages using an external language model (LM) under the framework of transfer learning. We first build a language-independent ASR system in a unified sequence-to-sequence (S2S)…