Related papers: Word Error Rate Definitions and Algorithms for Lon…

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h…

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…

Evaluating ASR systems for Indian languages is challenging due to spelling variations, suffix splitting flexibility, and non-standard spellings in code-mixed words. Traditional Word Error Rate (WER) often presents a bleaker picture of…

Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal. In this context, the word error rate (WER) metric is the reference for evaluating…

Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particularly for the 80 million-strong global community of people…

While standard speaker diarization attempts to answer the question "who spoken when", most of relevant applications in reality are more interested in determining "who spoken what". Whether it is the conventional modularized approach or the…

Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive…

Trivial events are ubiquitous in human to human conversations, e.g., cough, laugh and sniff. Compared to regular speech, these trivial events are usually short and unclear, thus generally regarded as not speaker discriminative and so are…

Pre-trained acoustic representations such as wav2vec and DeCoAR have attained impressive word error rates (WER) for speech recognition benchmarks, particularly when labeled data is limited. But little is known about what phonetic properties…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

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.…

Scores from traditional confidence classifiers (CCs) in automatic speech recognition (ASR) systems lack universal interpretation and vary with updates to the underlying confidence or acoustic models (AMs). In this work, we build…

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…

The amount of freely available systems for automatic speech recognition (ASR) based on neural networks is growing steadily, with equally increasingly reliable predictions. However, the evaluation of trained models is typically exclusively…

Recent literature has shown that a learned front end with multi-channel audio input can outperform traditional beam-forming algorithms for automatic speech recognition (ASR). In this paper, we present our study on multi-channel acoustic…

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…

Fine-tuning pretrained ASR models for specific domains is challenging for small organizations with limited labeled data and computational resources. Here, we explore different data selection pipelines and propose a robust approach that…

Training large foundation models using self-supervised objectives on unlabeled data, followed by fine-tuning on downstream tasks, has emerged as a standard procedure. Unfortunately, the efficacy of this approach is often constrained by both…

Automatic Speech Recognition (ASR) systems are commonly evaluated using aggregate metrics such as Word Error Rate (WER), which do not capture the linguistic structure of errors. Fine-grained analysis, such as Part-of-Speech (PoS)-wise error…

This paper investigates the in-context learning abilities of the Whisper automatic speech recognition (ASR) models released by OpenAI. A novel speech-based in-context learning (SICL) approach is proposed for test-time adaptation, which can…