Related papers: Contextual Biasing with the Knuth-Morris-Pratt Mat…

Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…

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…

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

We present a first large-scale public synthetic dataset for contextual spellchecking customization of automatic speech recognition (ASR) with focus on diverse rare and out-of-vocabulary (OOV) phrases, such as proper names or terms. The…

Recognition of uncommon words such as names and technical terminology is important to understanding conversations in context. However, the ability to recognise such words remains a challenge in modern automatic speech recognition (ASR)…

The integration of contextual embeddings into the optimization processes of large language models is an advancement in natural language processing. The Context-Aware Neural Gradient Mapping framework introduces a dynamic gradient adjustment…

Automatic Speech Recognition (ASR) models have achieved remarkable accuracy in general settings, yet their performance often degrades in domain-specific applications due to data mismatch and linguistic variability. This challenge is…

Media bias detection requires comprehensive integration of information derived from multiple news sources. Sentence-level political bias detection in news is no exception, and has proven to be a challenging task that requires an…

Accented automatic speech recognition (ASR) often degrades due to the limited availability of accented training data. Prior work has explored accent modeling in low-resource settings, but existing approaches typically require minutes to…

Automatic Speech Recognition (ASR) systems are often optimized to work best for speakers with canonical speech patterns. Unfortunately, these systems perform poorly when tested on atypical speech and heavily accented speech. It has…

In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem…

Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

It is difficult for an E2E ASR system to recognize words such as entities appearing infrequently in the training data. A widely used method to mitigate this issue is feeding contextual information into the acoustic model. Previous works…

Contextual bandit algorithms are commonly used in digital health to recommend personalized treatments. However, to ensure the effectiveness of the treatments, patients are often requested to take actions that have no immediate benefit to…

Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user's playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during…

Despite great improvements in semantic segmentation, challenges persist because of the lack of local/global contexts and the relationship between them. In this paper, we propose Contextrast, a contrastive learning-based semantic…

Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…

Effectively distinguishing the pronunciation correlations between different written texts is a significant issue in linguistic acoustics. Traditionally, such pronunciation correlations are obtained through manually designed pronunciation…

In this paper, we investigate the use of selectional restriction -- the constraints a predicate imposes on its arguments -- in a language model for speech recognition. We use an un-tagged corpus, followed by a public domain tagger and a…