Related papers: wav2letter++: The Fastest Open-source Speech Recog…

Strong presentation skills are valuable and sought-after in workplace and classroom environments alike. Of the possible improvements to vocal presentations, disfluencies and stutters in particular remain one of the most common and prominent…

The proliferation of scene text in both structured and unstructured environments presents significant challenges in optical character recognition (OCR), necessitating more efficient and robust text spotting solutions. This paper presents…

Last several years, GPUs are used to accelerate computations in many computer science domains. We focused on GPU accelerated Support Vector Machines (SVM) training with non-linear kernel functions. We had searched for all available GPU…

RTNeural is a neural inferencing library written in C++. RTNeural is designed to be used in systems with hard real-time constraints, with additional emphasis on speed, flexibility, size, and convenience. The motivation and design of the…

Unconstrained text recognition is an important computer vision task, featuring a wide variety of different sub-tasks, each with its own set of challenges. One of the biggest promises of deep neural networks has been the convergence and…

This study evaluates the performance of three advanced speech encoder models, Wav2Vec 2.0, XLS-R, and Whisper, in speaker identification tasks. By fine-tuning these models and analyzing their layer-wise representations using SVCCA, k-means…

In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discrete components such as…

Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity,…

Learned wavelet image and video coding approaches provide an explainable framework with a latent space corresponding to a wavelet decomposition. The wavelet image coder iWave++ achieves state-of-the-art performance and has been employed for…

There has been a growing demand for automated spoken language assessment systems in recent years. A standard pipeline for this process is to start with a speech recognition system and derive features, either hand-crafted or based on…

Modern machine learning frameworks are complex: they are typically organised in multiple layers each of which is written in a different language and they depend on a number of external libraries, but at their core they mainly consist of…

In the recent literature, "end-to-end" speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a structured output learning approach (such as CTC). In contrast…

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

This paper presents methods to accelerate recurrent neural network based language models (RNNLMs) for online speech recognition systems. Firstly, a lossy compression of the past hidden layer outputs (history vector) with caching is…

This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a million hours of publicly available speech audio in 128…

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on…

Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. However, such predetermined features are fundamentally limited,…

We introduce S++, a simple, robust, and deployable framework for training a neural network (NN) using private data from multiple sources, using secret-shared secure function evaluation. In short, consider a virtual third party to whom every…

As the complexity of state-of-the-art deep learning models increases by the month, implementation, interpretation, and traceability become ever-more-burdensome challenges for AI practitioners around the world. Several AI frameworks have…