相关论文: Unsupervised data selection for Speech Recognition…

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…

Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods are reminiscent of the well-known word2vec embedding…

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…

Speech models may be affected by performance imbalance in different population subgroups, raising concerns about fair treatment across these groups. Prior attempts to mitigate unfairness either focus on user-defined subgroups, potentially…

Keyword Spotting plays a critical role in enabling hands-free interaction for battery-powered edge devices. Few-Shot Keyword Spotting (FS-KWS) addresses the scalability and adaptability challenges of traditional systems by enabling…

Varying data augmentation policies and regularization over the course of optimization has led to performance improvements over using fixed values. We show that population based training is a useful tool to continuously search those…

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…

Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are…

Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one AWE approach is to use unsupervised autoencoder-based recurrent…

Word error rate (WER) is a metric used to evaluate the quality of transcriptions produced by Automatic Speech Recognition (ASR) systems. In many applications, it is of interest to estimate WER given a pair of a speech utterance and a…

Several supermodular losses have been shown to improve the perceptual quality of image segmentation in a discriminative framework such as a structured output support vector machine (SVM). These loss functions do not necessarily have the…

The trimming scheme with a prefixed cutoff portion is known as a method of improving the robustness of statistical models such as multivariate Gaussian mixture models (MG- MMs) in small scale tests by alleviating the impacts of outliers.…

Recent contrastive methods show significant improvement in self-supervised learning in several domains. In particular, contrastive methods are most effective where data augmentation can be easily constructed e.g. in computer vision.…

Complex data mining has wide application value in many fields, especially in the feature extraction and classification tasks of unlabeled data. This paper proposes an algorithm based on self-supervised learning and verifies its…

Most of the existing neural-based models for keyword spotting (KWS) in smart devices require thousands of training samples to learn a decent audio representation. However, with the rising demand for smart devices to become more…

In this study, we proposed a novel semi-supervised training method that uses unlabeled data with a class distribution that is completely different from the target data or data without a target label. To this end, we introduce a contrastive…

We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabeled audio of the Libri-Light dataset. More precisely, we carry…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Hybrid Autoregressive Transducer (HAT) is a recently proposed end-to-end acoustic model that extends the standard Recurrent Neural Network Transducer (RNN-T) for the purpose of the external language model (LM) fusion. In HAT, the blank…

Advances in self-supervised learning have significantly reduced the amount of transcribed audio required for training. However, the majority of work in this area is focused on read speech. We explore limited supervision in the domain of…