Related papers: Federated Heterogeneous Language Model Optimizatio…

Due to the rising awareness of privacy protection and the voluminous scale of speech data, it is becoming infeasible for Automatic Speech Recognition (ASR) system developers to train the acoustic model with complete data as before. For…

This paper presents a novel hybrid Automatic Speech Recognition (ASR) system designed specifically for resource-constrained robots. The proposed approach combines Hidden Markov Models (HMMs) with deep learning models and leverages socket…

Automatic Speech Recognition (ASR) has advanced with Speech Foundation Models (SFMs), yet performance degrades on dysarthric speech due to variability and limited data. This study as part of the submission to the Speech Accessibility…

We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate…

Retrieval-Augmented Generation (RAG) systems leverage Large Language Models (LLMs) to generate accurate and reliable responses that are grounded in retrieved context. However, LLMs often generate inconsistent outputs for semantically…

This study analyzes the performance of domain-specific Large Language Models (LLMs) for the medical field by integrating Retrieval-Augmented Generation (RAG) systems within a federated learning framework. Leveraging the inherent advantages…

This article describes a density ratio approach to integrating external Language Models (LMs) into end-to-end models for Automatic Speech Recognition (ASR). Applied to a Recurrent Neural Network Transducer (RNN-T) ASR model trained on a…

Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large…

This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems to improve transcription accuracy. The increasing sophistication of LLMs, with their in-context learning capabilities and…

Recently, model merging methods have demonstrated powerful strengths in combining abilities on various tasks from multiple Large Language Models (LLMs). While previous model merging methods mainly focus on merging homogeneous models with…

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…

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…

The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However, these methods only utilize the enhanced feature as the…

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce…

With the growing availability of smart devices and cloud services, personal speech assistance systems are increasingly used on a daily basis. Most devices redirect the voice recordings to a central server, which uses them for upgrading the…

Commonly used automatic speech recognition (ASR) systems can be classified into frame-synchronous and label-synchronous categories, based on whether the speech is decoded on a per-frame or per-label basis. Frame-synchronous systems, such as…

While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts 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…

We propose "Generative Fusion Decoding" (GFD), a novel shallow fusion framework designed to integrate large language models (LLMs) into cross-modal text recognition systems for automatic speech recognition (ASR) and optical character…