Related papers: Learning Fast Adaptation on Cross-Accented Speech …

The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary…

The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical…

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models. ASR…

Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities, and domain-specific special words for which little or no labeled data is available. To address…

Automatic Speech Recognition (ASR) systems have been gaining popularity in the recent years for their widespread usage in smart phones and speakers. Building ASR systems for task-specific scenarios is subject to the availability of…

This paper describes our experiments with automatically identifying native accents from speech samples of non-native English speakers using low level audio features, and n-gram features from manual transcriptions. Using a publicly available…

Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such representations may be skewed toward canonical data…

When only a limited amount of accented speech data is available, to promote multi-accent speech recognition performance, the conventional approach is accent-specific adaptation, which adapts the baseline model to multiple target accents…

Large Language Models (LLMs) are trained on corpora disproportionally weighted in favor of Standard American English. As a result, speakers of other dialects experience significantly more failures when interacting with these technologies.…

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech…

In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing…

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of…

Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…

Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks. The MAML algorithm performs well on few-shot learning…

Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent…

Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data is available for…