Related papers: Delayed Fusion: Integrating Large Language Models …

Fine-tuning pretrained language models (LMs) is a popular approach to automatic speech recognition (ASR) error detection during post-processing. While error detection systems often take advantage of statistical language archetypes captured…

We propose to utilize an instruction-tuned large language model (LLM) for guiding the text generation process in automatic speech recognition (ASR). Modern large language models (LLMs) are adept at performing various text generation tasks…

Text-only adaptation of an end-to-end (E2E) model remains a challenging task for automatic speech recognition (ASR). Language model (LM) fusion-based approaches require an additional external LM during inference, significantly increasing…

In this study, we investigate the integration of a large language model (LLM) with an automatic speech recognition (ASR) system, specifically focusing on enhancing rare word recognition performance. Using a 190,000-hour dataset primarily…

Transformer-based end-to-end (E2E) automatic speech recognition (ASR) systems have recently gained wide popularity, and are shown to outperform E2E models based on recurrent structures on a number of ASR tasks. However, like other E2E…

ASR model deployment environment is ever-changing, and the incoming speech can be switched across different domains during a session. This brings a challenge for effective domain adaptation when only target domain text data is available,…

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

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…

This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS).…

Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…

End-to-end (E2E) automatic speech recognition (ASR) systems have revolutionized the field by integrating all components into a single neural network, with attention-based encoder-decoder models achieving state-of-the-art performance.…

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…

In recent years, the evolution of end-to-end (E2E) automatic speech recognition (ASR) models has been remarkable, largely due to advances in deep learning architectures like transformer. On top of E2E systems, researchers have achieved…

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…

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…

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,…

Speech Large Language Models (Speech LLMs) have emerged as a crucial paradigm in recent years, extending the capabilities of traditional LLMs to speech tasks such as automatic speech recognition (ASR) and spoken dialogue modeling. However,…

Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs…

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the…

Large Language Models (LLMs) often excel in specific domains but fall short in others due to the limitations of their training. Thus, enabling LLMs to solve problems collaboratively by integrating their complementary knowledge promises to…