Related papers: Improving Data Driven Inverse Text Normalization u…

Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…

In speech-applications such as text-to-speech (TTS) or automatic speech recognition (ASR), \emph{text normalization} refers to the task of converting from a \emph{written} representation into a representation of how the text is to be…

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.…

Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…

Building a high quality automatic speech recognition (ASR) system with limited training data has been a challenging task particularly for a narrow target population. Open-sourced ASR systems, trained on sufficient data from adults, are…

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

Building Automatic Speech Recognition (ASR) systems for code-switched speech has recently gained renewed attention due to the widespread use of speech technologies in multilingual communities worldwide. End-to-end ASR systems are a natural…

Automatic lyrics transcription (ALT), which can be regarded as automatic speech recognition (ASR) on singing voice, is an interesting and practical topic in academia and industry. ALT has not been well developed mainly due to the dearth of…

Speech enhancement using neural networks is recently receiving large attention in research and being integrated in commercial devices and applications. In this work, we investigate data augmentation techniques for supervised deep…

The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an…

Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference. In this paper, we demonstrate that n-gram LM can be…

This paper studies the task of speech reconstruction from ultrasound tongue images and optical lip videos recorded in a silent speaking mode, where people only activate their intra-oral and extra-oral articulators without producing sound.…

Neural machine translation (NMT) has recently gained widespread attention because of its high translation accuracy. However, it shows poor performance in the translation of long sentences, which is a major issue in low-resource languages.…

Offline Handwritten Text Recognition (HTR) systems play a crucial role in applications such as historical document digitization, automatic form processing, and biometric authentication. However, their performance is often hindered by the…

Synthetic data generated by text-to-speech (TTS) systems can be used to improve automatic speech recognition (ASR) systems in low-resource or domain mismatch tasks. It has been shown that TTS-generated outputs still do not have the same…

Data augmentation is a widely used technique in machine learning to improve model performance. However, existing data augmentation techniques in natural language understanding (NLU) may not fully capture the complexity of natural language…

Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT)…

In this paper, we propose a novel implicit semantic data augmentation (ISDA) approach to complement traditional augmentation techniques like flipping, translation or rotation. Our work is motivated by the intriguing property that deep…

Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be…

Recent research using pre-trained transformer models suggests that just 10 minutes of transcribed speech may be enough to fine-tune such a model for automatic speech recognition (ASR) -- at least if we can also leverage vast amounts of text…