相关论文: SpecAugment on Large Scale Datasets

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

We combine recent advancements in end-to-end speech recognition to non-autoregressive automatic speech recognition. We push the limits of non-autoregressive state-of-the-art results for multiple datasets: LibriSpeech, Fisher+Switchboard and…

The task of making speaker verification systems robust to adverse scenarios remain a challenging and an active area of research. We developed an unsupervised feature enhancement approach in log-filter bank domain with the end goal of…

The performance of deep neural network-based speech enhancement systems typically increases with the training dataset size. However, studies that investigated the effect of training dataset size on speech enhancement performance did not…

Deep learning-based speech enhancement (SE) models have achieved impressive performance in the past decade. Numerous advanced architectures have been designed to deliver state-of-the-art performance; however, their scalability potential…

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the…

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

Automatic speech recognition (ASR) should serve every speaker, not only the majority ``standard'' speakers of a language. In order to build inclusive ASR, mitigating the bias against speaker groups who speak in a ``non-standard'' or…

Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While…

There is a surge in interest in self-supervised learning approaches for end-to-end speech encoding in recent years as they have achieved great success. Especially, WavLM showed state-of-the-art performance on various speech processing…

Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large…

Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set…

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time…

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…

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem,…

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…

We study transfer learning in convolutional network architectures applied to the task of recognizing audio, such as environmental sound events and speech commands. Our key finding is that not only is it possible to transfer representations…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

OpenAI's Whisper Automated Speech Recognition model excels in generalizing across diverse datasets and domains. However, this broad adaptability can lead to diminished performance in tasks requiring recognition of specific vocabularies.…