Related papers: Empowering Low-Resource Language ASR via Large-Sca…
Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in…
This paper presents an effective transfer learning framework for language adaptation in text-to-speech systems, with a focus on achieving language adaptation using minimal labeled and unlabeled data. While many works focus on reducing the…
Pseudo-labeling is the most adopted method for pre-training automatic speech recognition (ASR) models. However, its performance suffers from the supervised teacher model's degrading quality in low-resource setups and under domain transfer.…
Data availability and quality are major challenges in natural language processing for low-resourced languages. In particular, there is significantly less data available than for higher-resourced languages. This data is also often of low…
In this paper, we introduce Neural Information Retrieval resources for 11 widely spoken Indian Languages (Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, and Telugu) from two major Indian language…
This paper addresses performance degradation in anomalous sound detection (ASD) when neither sufficiently similar machine data nor operational state labels are available. We present an integrated pipeline that combines three complementary…
The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…
Voice conversion (VC) could be used to improve speech recognition systems in low-resource languages by using it to augment limited training data. However, VC has not been widely used for this purpose because of practical issues such as…
Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several…
Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing…
Identifying breakdowns in ongoing dialogues helps to improve communication effectiveness. Most prior work on this topic relies on human annotated data and data augmentation to learn a classification model. While quality labeled dialogue…
Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the…
India's vast linguistic diversity presents unique challenges and opportunities for technological advancement, especially in the realm of Natural Language Processing (NLP). While there has been significant progress in NLP applications for…
End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…
Recently, encoder-decoder neural models have achieved great success on text generation tasks. However, one problem of this kind of models is that their performances are usually limited by the scale of well-labeled data, which are very…
Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervised meta-training (SSMT) setting has been proposed for FSL,…
Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain…
Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on speech tasks using only small amounts of annotated data. The high number of proposed approaches…
Handwritten word recognition and spotting of low-resource scripts are difficult as sufficient training data is not available and it is often expensive for collecting data of such scripts. This paper presents a novel cross language platform…