Related papers: Efficient Utilization of Large Pre-Trained Models …
In the design of customer relationship management (CRM) systems, accurately identifying customer types and offering personalized services are key to enhancing customer satisfaction and loyalty. However, this process faces the challenge of…
We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for…
Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…
We address the problem of efficient acoustic-model refinement (continuous retraining) using semi-supervised and active learning for a low resource Indian language, wherein the low resource constraints are having i) a small labeled corpus…
Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search. While universal phone recognition is natural to consider when no…
While Automatic Speech Recognition (ASR) models have shown significant advances with the introduction of unsupervised or self-supervised training techniques, these improvements are still only limited to a subsection of languages and…
Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of…
Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…
Unsupervised pretraining, which learns a useful representation using a large amount of unlabeled data to facilitate the learning of downstream tasks, is a critical component of modern large-scale machine learning systems. Despite its…
Unsupervised visual representation learning offers the opportunity to leverage large corpora of unlabeled trajectories to form useful visual representations, which can benefit the training of reinforcement learning (RL) algorithms. However,…
Automatic speech recognition (ASR) models are normally trained to operate over single utterances, with a short duration of less than 30 seconds. This choice has been made in part due to computational constraints, but also reflects a common,…
In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…
In recent years, automatic speech recognition (ASR) systems have significantly improved, especially in languages with a vast amount of transcribed speech data. However, ASR systems tend to perform poorly for low-resource languages with…
Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as…
Developing a practical speech recognizer for a low resource language is challenging, not only because of the (potentially unknown) properties of the language, but also because test data may not be from the same domain as the available…
Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…
Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and…
Modern speech recognition systems exhibits rapid performance degradation under domain shift. This issue is especially prevalent in data-scarce settings, such as low-resource languages, where diversity of training data is limited. In this…
Much recent work on Spoken Language Understanding (SLU) is limited in at least one of three ways: models were trained on oracle text input and neglected ASR errors, models were trained to predict only intents without the slot values, or…
Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including…