Related papers: Learning discriminative features in sequence train…

The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a…

While deep learning models have demonstrated robust performance in speaker recognition tasks, they primarily rely on low-level audio features learned empirically from spectrograms or raw waveforms. However, prior work has indicated that…

Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises. In this paper, we introduce a…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two…

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping…

Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…

Feature selection aims to identify the most pattern-discriminative feature subset. In prior literature, filter (e.g., backward elimination) and embedded (e.g., Lasso) methods have hyperparameters (e.g., top-K, score thresholding) and tie to…

We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

In this paper we propose the Structured Deep Neural Network (structured DNN) as a structured and deep learning framework. This approach can learn to find the best structured object (such as a label sequence) given a structured input (such…

Neural networks often learn spurious correlations when exposed to biased training data, leading to poor performance on out-of-distribution data. A biased dataset can be divided, according to biased features, into bias-aligned samples (i.e.,…

End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in…

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…

Data augmentation is conventionally used to inject robustness in Speaker Verification systems. Several recently organized challenges focus on handling novel acoustic environments. Deep learning based speech enhancement is a modern solution…

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…