相关论文: Mixture of LoRA Experts with Multi-Modal and Multi…

This work investigates retrieval augmented generation as an efficient strategy for automatic context discovery in context-aware Automatic Speech Recognition (ASR) system, in order to improve transcription accuracy in the presence of rare or…

Generative large language models (LLMs) exhibit impressive capabilities, which can be further augmented by integrating a pre-trained vision model into the original LLM to create a multimodal LLM (MLLM). However, this integration often…

Multi-hop question answering (MHQA) requires integrating knowledge scattered across multiple passages to derive the correct answer. Traditional retrieval-augmented generation (RAG) methods primarily focus on coarse-grained textual semantic…

This paper develops an ensemble method for fine-tuning a language model to multiple datasets. Existing methods, such as quantized LoRA (QLoRA), are efficient when adapting to a single dataset. When training on multiple datasets of different…

Integrating audio encoders with LLMs through connectors has enabled these models to process and comprehend audio modalities, significantly enhancing speech-to-text tasks, including automatic speech recognition (ASR) and automatic speech…

Large Language Models (LLMs) demonstrate remarkable capabilities, yet struggle with hallucination and outdated knowledge when tasked with complex knowledge reasoning, resulting in factually incorrect outputs. Previous studies have attempted…

Retrieval-augmented generation (RAG) has shown impressive capability in providing reliable answer predictions and addressing hallucination problems. A typical RAG implementation uses powerful retrieval models to extract external information…

Recently, large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task.…

Speech separation aims to separate multiple speech sources from a speech mixture. Although speech separation is well-solved on some existing English speech separation benchmarks, it is worthy of more investigation on the generalizability of…

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack…

Large Multimodal Models (LMMs) have demonstrated exceptional performance across a wide range of domains. This paper explores their potential in pronunciation assessment tasks, with a particular focus on evaluating the capabilities of the…

Adapting pre-trained text Large Language Models (LLMs) into Speech Language Models (Speech LMs) via continual pretraining on speech data is promising, but often degrades the original text capabilities. We propose Multimodal Depth Upscaling,…

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…

Speech emotion recognition (SER) systems can exhibit gender-related performance disparities, but how such bias manifests in multilingual speech LLMs across languages and modalities is unclear. We introduce a novel multilingual, multimodal…

Continuous sign language recognition (SLR) deals with unaligned video-text pair and uses the word error rate (WER), i.e., edit distance, as the main evaluation metric. Since it is not differentiable, we usually instead optimize the learning…

Automatic Speech Recognition (ASR) plays a crucial role in human-machine interaction and serves as an interface for a wide range of applications. Traditionally, ASR performance has been evaluated using Word Error Rate (WER), a metric that…

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…

While recent large language models (LLMs) improve on various question answering (QA) datasets, it remains difficult for a single model to generalize across question types that require distinct reasoning abilities. We provide empirical…

Multimodal Large Language Models (MLLMs) have shown remarkable performance in high-resource languages. However, their effectiveness diminishes significantly in the contexts of low-resource languages. Current multilingual enhancement methods…

Emotion Recognition in Conversations (ERC) presents unique challenges, requiring models to capture the temporal flow of multi-turn dialogues and to effectively integrate cues from multiple modalities. We propose Mixture of Speech-Text…