Related papers: Automatic Speech Recognition for Humanitarian Appl…

We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-time on a Nexus 5 Android smartphone. We employ a quantized…

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of…

This technical report describes the methods and results of a three-week sprint to produce deployable speech recognition models for 31 under-served languages of the Common Voice project. We outline the preprocessing steps, hyperparameter…

We use dynamic time warping (DTW) as supervision for training a convolutional neural network (CNN) based keyword spotting system using a small set of spoken isolated keywords. The aim is to allow rapid deployment of a keyword spotting…

In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features…

Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models' (LLMs) exceptional long-context…

In the FAME! project, we aim to develop an automatic speech recognition (ASR) system for Frisian-Dutch code-switching (CS) speech extracted from the archives of a local broadcaster with the ultimate goal of building a spoken document…

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…

Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs). However, large RNNs limit practical deployment in hearing aid hardware (HW) form-factors, which are battery…

Automatic Speech Recognition (ASR) technologies have transformed human-computer interaction; however, low-resource languages in Africa remain significantly underrepresented in both research and practical applications. This study…

Automated detection of voice disorders with computational methods is a recent research area in the medical domain since it requires a rigorous endoscopy for the accurate diagnosis. Efficient screening methods are required for the diagnosis…

We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up…

In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized…

Language models (LMs) based on Long Short Term Memory (LSTM) have shown good gains in many automatic speech recognition tasks. In this paper, we extend an LSTM by adding highway networks inside an LSTM and use the resulting Highway LSTM…

Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search. While universal phone recognition is natural to consider when no…

Speech intelligibility can be degraded due to multiple factors, such as noisy environments, technical difficulties or biological conditions. This work is focused on the development of an automatic non-intrusive system for predicting the…

Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important to extend the pure text based methods to incorporate other…

Language models are the foundation of current neural network-based models for natural language understanding and generation. However, research on the intrinsic performance of language models on African languages has been extremely limited,…