Related papers: A Theory of Unsupervised Speech Recognition
Linguistic anomalies detectable in spontaneous speech have shown promise for various clinical applications including screening for dementia and other forms of cognitive impairment. The feasibility of deploying automated tools that can…
Unsupervised single-channel overlapped speech recognition is one of the hardest problems in automatic speech recognition (ASR). Permutation invariant training (PIT) is a state of the art model-based approach, which applies a single neural…
Automatic Speech Recognition (ASR) systems now mediate countless human-technology interactions, yet research on their fairness implications remains surprisingly limited. This paper examines ASR bias through a philosophical lens, arguing…
Recent breakthroughs in Automatic Speech Recognition (ASR) have enabled fully automated Alzheimer's Disease (AD) detection using ASR transcripts. Nonetheless, the impact of ASR errors on AD detection remains poorly understood. This paper…
In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR). An ASR model with decent performance can be realized by fine-tuning an SSL model with…
Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…
Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…
In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…
With the wide use of Automatic Speech Recognition (ASR) in applications such as human machine interaction, simultaneous interpretation, audio transcription, etc., its security protection becomes increasingly important. Although recent…
Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by…
This paper presents a novel algorithm for building an automatic speech recognition (ASR) model with imperfect training data. Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the…
Self-supervised learning (SSL) speech models, which can serve as powerful upstream models to extract meaningful speech representations, have achieved unprecedented success in speech representation learning. However, their effectiveness on…
Many studies have shown automatic speech processing (ASR) systems have unequal performance across speakergroups (SG's). However, the manner in which such studies arrive at this conclusion is inconsistent. To pave the wayfor more reliable…
Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions. However, errors from the automatic speech recognizer (ASR) usually hurt the understanding performance. In reality, ASR…
In Indian Languages , native speakers are able to understand new words formed by either combining or modifying root words with tense and / or gender. Due to data insufficiency, Automatic Speech Recognition system (ASR) may not accommodate…
Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial…
This research investigates the transferability of Automatic Speech Recognition (ASR)-robust Natural Language Understanding (NLU) models from controlled experimental conditions to practical, real-world applications. Focused on smart home…
Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some…
State-of-the-art large-scale universal speech models (USMs) show a decent automatic speech recognition (ASR) performance across multiple domains and languages. However, it remains a challenge for these models to recognize overlapped speech,…
At the present time, computers are employed to solve complex tasks and problems ranging from simple calculations to intensive digital image processing and intricate algorithmic optimization problems to computationally-demanding weather…