Related papers: Improving Data Driven Inverse Text Normalization u…
Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation…
We propose data and knowledge-driven approaches for multilingual training of the automated speech recognition (ASR) system for a target language by pooling speech data from multiple source languages. Exploiting the acoustic similarities…
Batch normalization (BN) is an effective method to accelerate model training and improve the generalization performance of neural networks. In this paper, we propose an improved batch normalization technique called attentive batch…
Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model…
Dialogue State Tracking (DST) is a key part of task-oriented dialogue systems, identifying important information in conversations. However, its accuracy drops significantly in spoken dialogue environments due to named entity errors from…
Data Augmentation (DA) is frequently used to provide additional training data without extra human annotation automatically. However, data augmentation may introduce noisy data that impairs training. To guarantee the quality of augmented…
End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-translation or…
Data augmentation is commonly used to help build a robust speaker verification system, especially in limited-resource case. However, conventional data augmentation methods usually focus on the diversity of acoustic environment, leaving the…
We present a case study on developing a customized speech-to-text system for a Hungarian speaker with severe dysarthria. State-of-the-art automatic speech recognition (ASR) models struggle with zero-shot transcription of dysarthric speech,…
In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…
ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence. While optimizing the probability of all tokens in the target sequence is sensible, one may want to de-emphasize tokens…
The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning models. Therefore, we propose an intra-source style…
Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…
Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch…
Speech sounds are produced as the coordinated movement of the speaking organs. There are several available methods to model the relation of articulatory movements and the resulting speech signal. The reverse problem is often called as…
Spoken Language Understanding (SLU) converts user utterances into structured semantic representations. Data sparsity is one of the main obstacles of SLU due to the high cost of human annotation, especially when domain changes or a new…
Automatic speech recognition (ASR) systems have achieved strong performance on general transcription tasks. However, they continue to struggle with recognizing rare named entities and adapting to domain mismatches. In contrast, large…
Automatic Speech Recognition (ASR) systems have attained unprecedented performance with large speech models pre-trained based on self-supervised speech representation learning. However, these pre-trained speech models suffer from…
Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a…
We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our…