Related papers: Improved Regularization Techniques for End-to-End …

Subword regularization, used widely in NLP, improves model performance by reducing the dependency on exact tokenizations, augmenting the training corpus, and exposing the model to more unique contexts during training. BPE and MaxMatch, two…

Data augmentation is a widely adopted technique utilized to improve the robustness of automatic speech recognition (ASR). Employing a fixed data augmentation strategy for all training data is a common practice. However, it is important to…

Recent advances in deep learning show that end-to-end speech to text translation model is a promising approach to direct the speech translation field. In this work, we provide an overview of different end-to-end architectures, as well as…

Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of…

The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization…

In this paper, we propose a novel end-to-end neural-network-based speaker diarization method. Unlike most existing methods, our proposed method does not have separate modules for extraction and clustering of speaker representations.…

End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…

Due to the scarcity of publicly available diarization data, the model performance can be improved by training a single model with data from different domains. In this work, we propose to incorporate domain information to train a single…

Recently, end-to-end mispronunciation detection and diagnosis (MD&D) systems has become a popular alternative to greatly simplify the model-building process of conventional hybrid DNN-HMM systems by representing complicated modules with a…

Federated learning can be used to train machine learning models on the edge on local data that never leave devices, providing privacy by default. This presents a challenge pertaining to the communication and computation costs associated…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have…

We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model. Key to our approach are a strong baseline acoustic and…

Despite dropout's ubiquity in machine learning, its effectiveness as a form of data augmentation remains under-explored. We address two key questions: (i) When is dropout effective as an augmentation strategy? (ii) Is dropout uniquely…

When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic performance numbers. We…

End-to-end speaker diarization approaches have shown exceptional performance over the traditional modular approaches. To further improve the performance of the end-to-end speaker diarization for real speech recordings, recently works have…

We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset. In this scenario, overfitting is a major…

Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout's training and inference phases,…

End-to-end diarization presents an attractive alternative to standard cascaded diarization systems because a single system can handle all aspects of the task at once. Many flavors of end-to-end models have been proposed but all of them…

Data augmentation is a technique to generate new training data based on existing data. We evaluate the simple and cost-effective method of concatenating the original data examples to build new training instances. Continued training with…