相关论文: Auxiliary Multimodal LSTM for Audio-visual Speech …

Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video…

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…

Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM) approach that…

Visual Speech Recognition (VSR) aims to recognize corresponding text by analyzing visual information from lip movements. Due to the high variability and weak information of lip movements, VSR tasks require effectively utilizing any…

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.…

This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems to improve transcription accuracy. The increasing sophistication of LLMs, with their in-context learning capabilities and…

Recently audio-visual speech recognition (AVSR), which better leverages video modality as additional information to extend automatic speech recognition (ASR), has shown promising results in complex acoustic environments. However, there is…

Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…

Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…

The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based…

Recent advances in multi-modal large language models (MLLMs) have opened new possibilities for unified modeling of speech, text, images, and other modalities. Building on our prior work, this paper examines the conditions and model…

Automatic Modulation Recognition (AMR) plays a crucial role in wireless communication systems. Deep learning AMR strategies have achieved tremendous success in recent years. Modulated signals exhibit long temporal dependencies, and…

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…

Benchmarks for language-guided embodied agents typically assume text-based instructions, but deployed agents will encounter spoken instructions. While Automatic Speech Recognition (ASR) models can bridge the input gap, erroneous ASR…

Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations.…

The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due to the noise, etc. In this case, the acoustic information can be less reliable.…

Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition…

End-to-end attention-based models have been shown to be competitive alternatives to conventional DNN-HMM models in the Speech Recognition Systems. In this paper, we extend existing end-to-end attention-based models that can be applied for…

Fine-tuning pretrained language models (LMs) is a popular approach to automatic speech recognition (ASR) error detection during post-processing. While error detection systems often take advantage of statistical language archetypes captured…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…