Related papers: H_eval: A new hybrid evaluation metric for automat…

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Automatic Speech Recognition (ASR) systems suffer significant performance degradation in noisy environments, a challenge that is especially severe for low-resource languages such as Persian. Even state-of-the-art models such as Whisper…

Automatic Speech Recognition (ASR) systems in the clinical domain face significant challenges, notably the need to recognise specialised medical vocabulary accurately and meet stringent precision requirements. We introduce United-MedASR, a…

Code-switching (CS), defined as the mixing of languages in conversations, has become a worldwide phenomenon. The prevalence of CS has been recently met with a growing demand and interest to build CS ASR systems. In this paper, we present…

Recent developments in natural language processing (NLP) have highlighted the need for substantial amounts of data for models to capture textual information accurately. This raises concerns regarding the computational resources and time…

Automatic Speech Recognition (ASR) systems have achieved remarkable performance on widely used benchmarks such as LibriSpeech and Fleurs. However, these benchmarks do not adequately reflect the complexities of real-world conversational…

Simultaneous speech-to-text translation systems must balance translation quality with latency. Although quality evaluation is well established, latency measurement remains a challenge. Existing metrics produce inconsistent results,…

Most current state-of-the art systems for generating English text from Abstract Meaning Representation (AMR) have been evaluated only using automated metrics, such as BLEU, which are known to be problematic for natural language generation.…

Automatic Speech Recognition (ASR) in medical contexts has the potential to save time, cut costs, increase report accuracy, and reduce physician burnout. However, the healthcare industry has been slower to adopt this technology, in part due…

Offline handwriting recognition (HWR) has improved significantly with the advent of deep learning architectures in recent years. Nevertheless, it remains a challenging problem and practical applications often rely on post-processing…

Automatic Speech Recognition (ASR) is increasingly used in applications involving child speech, such as language learning and literacy acquisition. However, the effectiveness of such applications is limited by high ASR error rates. The…

Preschool evaluation is crucial because it gives teachers and parents influential knowledge about children's growth and development. The COVID-19 pandemic has highlighted the necessity of online assessment for preschool children. One of the…

Although great progresses have been made in automatic speech recognition (ASR), significant performance degradation is still observed when recognizing multi-talker mixed speech. In this paper, we propose and evaluate several architectures…

While the last decade has witnessed significant advancements in Automatic Speech Recognition (ASR) systems, performance of these systems for individuals with speech disabilities remains inadequate, partly due to limited public training…

This paper presents a novel hybrid Automatic Speech Recognition (ASR) system designed specifically for resource-constrained robots. The proposed approach combines Hidden Markov Models (HMMs) with deep learning models and leverages socket…

Segmentation for continuous Automatic Speech Recognition (ASR) has traditionally used silence timeouts or voice activity detectors (VADs), which are both limited to acoustic features. This segmentation is often overly aggressive, given that…

End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training, as well as heavyweight computation for inference. Of course, this impedes…

DER is the primary metric to evaluate diarization performance while facing a dilemma: the errors in short utterances or segments tend to be overwhelmed by longer ones. Short segments, e.g., `yes' or `no,' still have semantic information.…

A new label smoothing method that makes use of prior knowledge of a language at human level, homophone, is proposed in this paper for automatic speech recognition (ASR). Compared with its forerunners, the proposed method uses pronunciation…

This paper proposes a new approach to perform unsupervised fine-tuning and self-training using unlabeled speech data for recurrent neural network (RNN)-Transducer (RNN-T) end-to-end (E2E) automatic speech recognition (ASR) systems.…