Related papers: Efficient Streaming LLM for Speech Recognition

We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these…

This paper describes our Triple X speech recognition system submitted to Task 1 of the Multi-Lingual Conversational Speech Language Modeling (MLC-SLM) Challenge. Our work focuses on optimizing speech recognition accuracy in multilingual…

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual…

We address the task of video chaptering, i.e., partitioning a long video timeline into semantic units and generating corresponding chapter titles. While relatively underexplored, automatic chaptering has the potential to enable efficient…

Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks. However, a critical challenge remains in that they sometimes generate factually incorrect answers. To address this, while many…

Recently, streaming end-to-end automatic speech recognition (E2E-ASR) has gained more and more attention. Many efforts have been paid to turn the non-streaming attention-based E2E-ASR system into streaming architecture. In this work, we…

The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an…

Large Vision-Language Models (LVLMs) have demonstrated strong multimodal reasoning capabilities on long and complex documents. However, their high memory footprint makes them impractical for deployment on resource-constrained edge devices.…

Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters. We study how much of this decoder capacity is actually needed for speech tasks. Across two LLM…

Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM)…

Large language models have become extremely popular recently due to their ability to achieve strong performance on a variety of tasks, such as text generation and rewriting, but their size and computation cost make them difficult to access,…

Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased…

We introduce Speech Information Retrieval (SIR), a new long-context task for Speech Large Language Models (Speech LLMs), and present SPIRAL, a 1,012-sample benchmark testing models' ability to extract critical details from approximately…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…

In real-world applications, users often require both translations and transcriptions of speech to enhance their comprehension, particularly in streaming scenarios where incremental generation is necessary. This paper introduces a streaming…

Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks. However, their applicability is still less explored in low-resource…

We propose Chunk-wise Attention Transducer (CHAT), a novel extension to RNN-T models that processes audio in fixed-size chunks while employing cross-attention within each chunk. This hybrid approach maintains RNN-T's streaming capability…

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…

Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail…