Related papers: Qualitative Evaluation of Language Model Rescoring…

Error correction (EC) models play a crucial role in refining Automatic Speech Recognition (ASR) transcriptions, enhancing the readability and quality of transcriptions. Without requiring access to the underlying code or model weights, EC…

Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advances, ASR models like Whisper struggle with non-normative…

This paper addresses automatic quality assessment of spoken language translation (SLT). This relatively new task is defined and formalized as a sequence labeling problem where each word in the SLT hypothesis is tagged as good or bad…

Automatic Speech Recognition (ASR) systems have been evolving quickly and reaching human parity in certain cases. The systems usually perform pretty well on reading style and clean speech, however, most of the available systems suffer from…

Traditional ASR metrics like WER and CER fail to capture intelligibility, especially for dysarthric and dysphonic speech, where semantic alignment matters more than exact word matches. ASR systems struggle with these speech types, often…

Automatic Speech Recognition (ASR) systems generalize poorly on accented speech. The phonetic and linguistic variability of accents present hard challenges for ASR systems today in both data collection and modeling strategies. The resulting…

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…

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced.…

The ubiquitous presence of machine learning systems in our lives necessitates research into their vulnerabilities and appropriate countermeasures. In particular, we investigate the effectiveness of adversarial attacks and defenses against…

Speech emotion recognition~(SER) refers to the technique of inferring the emotional state of an individual from speech signals. SERs continue to garner interest due to their wide applicability. Although the domain is mainly founded on…

The integration of natural language processing (NLP) technologies into educational applications has shown promising results, particularly in the language learning domain. Recently, many spoken open-domain chatbots have been used as speaking…

With the strong representational power of large language models (LLMs), generative error correction (GER) for automatic speech recognition (ASR) aims to provide semantic and phonetic refinements to address ASR errors. This work explores how…

In this article, we present an approach for non native automatic speech recognition (ASR). We propose two methods to adapt existing ASR systems to the non-native accents. The first method is based on the modification of acoustic models…

Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems. In this work, we propose Masked Audio Text Encoder (MATE), a multi-modal masked language model rescorer which…

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…

This article concerns comparative studies on the Automatic Speech Recognition (ASR) model incorporated with the Large Language Model (LLM) used for medical interviews. The proposed solution is tested on polish language benchmarks and…

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

Code-switching, the alternation of languages within a single discourse, presents a significant challenge for Automatic Speech Recognition. Despite the unique nature of the task, performance is commonly measured with established metrics such…

Nowadays, research in speech technologies has gotten a lot out thanks to recently created public domain corpora that contain thousands of recording hours. These large amounts of data are very helpful for training the new complex models…

Alzheimer's Disease is the most common form of dementia. Automatic detection from speech could help to identify symptoms at early stages, so that preventive actions can be carried out. This research is a contribution to the ADReSSo…