Related papers: Improving speech recognition models with small sam…

In this paper, we investigate domain adaptation for low-resource Automatic Speech Recognition (ASR) of target-domain data, when a well-trained ASR model trained with a large dataset is available. We argue that in the encoder-decoder…

Air traffic management and specifically air-traffic control (ATC) rely mostly on voice communications between Air Traffic Controllers (ATCos) and pilots. In most cases, these voice communications follow a well-defined grammar that could be…

As human-machine voice interfaces provide easy access to increasingly intelligent machines, many state-of-the-art automatic speech recognition (ASR) systems are proposed. However, commercial ASR systems usually have poor performance on…

Recent advancements in deep learning (DL) have posed a significant challenge for automatic speech recognition (ASR). ASR relies on extensive training datasets, including confidential ones, and demands substantial computational and storage…

Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…

We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio. We find that the combination of…

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…

Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with…

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…

Despite huge improvements in automatic speech recognition (ASR) employing neural networks, ASR systems still suffer from a lack of robustness and generalizability issues due to domain shifting. This is mainly because principal corpus design…

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…

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Automatic speech recognition (ASR) allows transcribing the communications between air traffic controllers (ATCOs) and aircraft pilots. The transcriptions are used later to extract ATC named entities, e.g., aircraft callsigns. One common…

Building a high quality automatic speech recognition (ASR) system with limited training data has been a challenging task particularly for a narrow target population. Open-sourced ASR systems, trained on sufficient data from adults, are…

It is an effective way that improves the performance of the existing Automatic Speech Recognition (ASR) systems by retraining with more and more new training data in the target domain. Recently, Deep Neural Network (DNN) has become a…

Previously, a machine speech chain, which is based on sequence-to-sequence deep learning, was proposed to mimic speech perception and production behavior. Such chains separately processed listening and speaking by automatic speech…

Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…

Unsupervised cross-lingual speech representation learning (XLSR) has recently shown promising results in speech recognition by leveraging vast amounts of unlabeled data across multiple languages. However, standard XLSR model suffers from…

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks…