相关论文: "Sorry, I Didn't Catch That": How Speech Models Mi…

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to disfluency, filter words, and other errata…

Large language models (LLMs) have achieved top results in recent machine translation evaluations, but they are also known to be sensitive to errors and perturbations in their prompts. We systematically evaluate how both humanly plausible…

Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved…

The increasing reliability of automatic speech recognition has proliferated its everyday use. However, for research purposes, it is often unclear which model one should choose for a task, particularly if there is a requirement for speed as…

Writing, as an omnipresent form of human communication, permeates nearly every aspect of contemporary life. Consequently, inaccuracies or errors in written communication can lead to profound consequences, ranging from financial losses to…

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…

High-quality human transcription is essential for training and improving Automatic Speech Recognition (ASR) models. Recent study~\cite{libricrowd} has found that every 1% worse transcription Word Error Rate (WER) increases approximately 2%…

Speech foundation models, such as OpenAI's Whisper, become the state of the art in speech understanding due to their strong accuracy and generalizability. Yet, their applications are mostly limited to processing pre-recorded speech, whereas…

Automatic Speech Recognition (ASR) systems, such as Whisper, achieve high transcription accuracy but struggle with named entities and numerical data, especially when proper formatting is required. These issues increase word error rate (WER)…

Recent advances in automatic speech recognition (ASR) and speech enhancement have led to a widespread assumption that improving perceptual audio quality should directly benefit recognition accuracy. In this work, we rigorously examine…

Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation. While audio anti-spoofing systems are critical for detecting such threats, prior…

Sanskrit, one of humanity's most ancient languages, has a vast collection of books and manuscripts on diverse topics that have been accumulated over millennia. However, its digital content (audio and text), which is vital for the training…

Automatic speech recognition and voice identification systems are being deployed in a wide array of applications, from providing control mechanisms to devices lacking traditional interfaces, to the automatic transcription of conversations…

Modern automatic speech recognition (ASR) systems have been observed to function better for certain speaker groups (SGs) than others, despite recent gains in overall performance. One potential impediment to progress towards fairer ASR is a…

We investigate the effect of speaker localization on the performance of speech recognition systems in a multispeaker, multichannel environment. Given the speaker location information, speech separation is performed in three stages. In the…

For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to…

Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with…

Reading comprehension has been widely studied. One of the most representative reading comprehension tasks is Stanford Question Answering Dataset (SQuAD), on which machine is already comparable with human. On the other hand, accessing large…

The paper revives an older approach to acoustic modeling that borrows from n-gram language modeling in an attempt to scale up both the amount of training data and model size (as measured by the number of parameters in the model), to…

Automatic Speech Recognition (ASR) systems have proliferated over the recent years to the point that free platforms such as YouTube now provide speech recognition services. Given the wide selection of ASR systems, we contribute to the field…