Related papers: Sentence-Select: Large-Scale Language Model Data S…

Large Language Models (LLMs) and Multimodal LLMs (MLLMs) have demonstrated immense potential in autonomous driving (AD) by offering human-like reasoning and open-world generalization. However, the excessive computational overhead and high…

Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of parameters, leading to slow inferences even with adapted hardware. In this context,…

Natural Language Processing has recently made understanding human interaction easier, leading to improved sentimental analysis and behaviour prediction. However, the choice of words and vocal cues in conversations presents an underexplored…

We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given…

Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…

This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to…

Extensive efforts have been made to boost the performance in the domain of language models by introducing various attention-based transformers. However, the inclusion of linear layers with large dimensions contributes to significant…

While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific…

The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in…

Rare words remain a critical bottleneck for speech-to-text systems. While direct fine-tuning improves recognition of target words, it often incurs high cost, catastrophic forgetting, and limited scalability. To address these challenges, we…

This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings…

In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

While speech large language models (SpeechLLMs) have advanced standard automatic speech recognition (ASR), contextual biasing for named entities and rare words remains challenging, especially at scale. To address this, we propose BR-ASR: a…

While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…

Neural network language model (NNLM) plays an essential role in automatic speech recognition (ASR) systems, especially in adaptation tasks when text-only data is available. In practice, an NNLM is typically trained on a combination of data…

The integration of Language Models (LMs) has proven to be an effective way to address domain shifts in speech recognition. However, these approaches usually require a significant amount of target domain text data for the training of LMs.…

Current models for Word Sense Disambiguation (WSD) struggle to disambiguate rare senses, despite reaching human performance on global WSD metrics. This stems from a lack of data for both modeling and evaluating rare senses in existing WSD…

Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts…

Generative error correction (GER) with large language models (LLMs) has emerged as an effective post-processing approach to improve automatic speech recognition (ASR) performance. However, it often struggles with rare or domain-specific…