Related papers: Leveraging supplementary text data to kick-start a…

The development of resource-constrained approaches to automatic speech recognition (ASR) is of great interest due to its broad applicability to many low-resource languages for which there is scant usable data. Existing approaches to many…

Nearly half of the world's languages are endangered. Speech technologies such as Automatic Speech Recognition (ASR) are central to revival efforts, yet most languages remain unsupported because standard pipelines expect utterance-level…

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.…

With 4.5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition. We propose data selection techniques to…

In recent years, the performance of automatic speech recognition (ASR) systems has made considerable progress. Unfortunately, for people with speech impairments, such as people treated for oral cancer (OC), ASR performance is still lagging…

It is estimated that around 70 million people worldwide are affected by a speech disorder called stuttering. With recent advances in Automatic Speech Recognition (ASR), voice assistants are increasingly useful in our everyday lives. Many…

This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w.r.t. to the language model. This takes advantage of the fact that if the language model will reliably and accurately predict a token…

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive. Applying speech enhancement on Automatic Speech…

End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…

Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

Automatic Speech Recognition (ASR) systems struggle with child speech due to its distinct acoustic and linguistic variability and limited availability of child speech datasets, leading to high transcription error rates. While ASR error…

Recent progress in speech recognition has relied on models trained on vast amounts of labeled data. However, classroom Automatic Speech Recognition (ASR) faces the real-world challenge of abundant weak transcripts paired with only a small…

Large language models have proven themselves highly flexible, able to solve a wide range of generative tasks, such as abstractive summarization and open-ended question answering. In this paper we extend the capabilities of LLMs by directly…

Despite recent advancements in deep learning technologies, Child Speech Recognition remains a challenging task. Current Automatic Speech Recognition (ASR) models require substantial amounts of annotated data for training, which is scarce.…

One of the central skills that language learners need to practice is speaking the language. Currently, students in school do not get enough speaking opportunities and lack conversational practice. Recent advances in speech technology and…

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…

Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…