Related papers: Which Data Matter? Embedding-Based Data Selection …

In this paper, we investigate domain adaptation for low-resource Automatic Speech Recognition (ASR) of target-domain data, when a well-trained ASR model trained with a large dataset is available. We argue that in the encoder-decoder…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to scale and diversity, the role of the data distribution is less…

In this work we evaluate the utility of synthetic data for training automatic speech recognition (ASR). We use the ASR training data to train a text-to-speech (TTS) system similar to FastSpeech-2. With this TTS we reproduce the original…

Semi-supervised learning (SSL) is an active area of research which aims to utilize unlabelled data in order to improve the accuracy of speech recognition systems. The current study proposes a methodology for integration of two key ideas: 1)…

Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no…

This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model. We trained a neural network,…

Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating…

Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data. While recently developed end-to-end methods largely simplify the modeling pipelines, they still suffer from the data…

Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to…

Building inclusive speech recognition systems is a crucial step towards developing technologies that speakers of all language varieties can use. Therefore, ASR systems must work for everybody independently of the way they speak. To…

Self-supervised learning (SSL) has been able to leverage unlabeled data to boost the performance of automatic speech recognition (ASR) models when we have access to only a small amount of transcribed speech data. However, this raises the…

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…

The recent success of Automatic Speech Recognition (ASR) is largely attributed to the ever-growing amount of training data. However, this trend has made model training prohibitively costly and imposed computational demands. While data…

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by…

Error correction (EC) based on large language models is an emerging technology to enhance the performance of automatic speech recognition (ASR) systems. Generally, training data for EC are collected by automatically pairing a large set of…

Data selection is critical for enhancing the performance of language models, particularly when aligning training datasets with a desired target distribution. This study explores the effects of different data selection methods and feature…

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…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…