Related papers: Using Text Injection to Improve Recognition of Per…
This paper enhances dysarthric and dysphonic speech recognition by fine-tuning pretrained automatic speech recognition (ASR) models on the 2023-10-05 data package of the Speech Accessibility Project (SAP), which contains the speech of 253…
Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…
Automatic Speech Recognition (ASR) systems are used in the financial domain to enhance the caller experience by enabling natural language understanding and facilitating efficient and intuitive interactions. Increasing use of ASR systems…
Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for…
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…
Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit…
Room Impulse Responses (RIRs) enable realistic acoustic simulation, with applications ranging from multimedia production to speech data augmentation. However, acquiring high-quality real-world RIRs is labor-intensive, and data scarcity…
In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to…
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…
Protecting Personally Identifiable Information (PII), such as names, is a critical requirement in learning technologies to safeguard student and teacher privacy and maintain trust. Accurate PII detection is an essential step toward…
For d/Deaf and hard of hearing (DHH) people, captioning is an essential accessibility tool. Significant developments in artificial intelligence (AI) mean that Automatic Speech Recognition (ASR) is now a part of many popular applications.…
Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…
Explainable AI (XAI) techniques have been widely used to help explain and understand the output of deep learning models in fields such as image classification and Natural Language Processing. Interest in using XAI techniques to explain deep…
We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…
Speech enhancement for voice pickup in hearables aims to improve the user's voice by suppressing noise and interfering talkers, while maintaining own-voice quality. For single-channel methods, it is particularly challenging to distinguish…
Aiming to improve the Automatic Speech Recognition (ASR) outputs with a post-processing step, ASR error correction (EC) techniques have been widely developed due to their efficiency in using parallel text data. Previous works mainly focus…
Accurate recognition of slot values such as domain specific words or named entities by automatic speech recognition (ASR) systems forms the core of the Goal-oriented Dialogue Systems. Although it is a critical step with direct impact on…
Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on…
Evaluating automatic speech recognition (ASR) systems is a classical but difficult and still open problem, which often boils down to focusing only on the word error rate (WER). However, this metric suffers from many limitations and does not…
Programs offer compactness and structure that makes them an attractive representation for visual data. We explore how code rewriting can be used to improve systems for inferring programs from visual data. We first propose Sparse…