SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Chunyu, Liu, Bingyu, Cui, Zhichao, Shi, Junhan, Qi, Anbin, Zhang, Tian-hao, Zhou, Dinghao, Lu, Lewei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911311030386688
author Sun, Chunyu
Liu, Bingyu
Cui, Zhichao
Shi, Junhan
Qi, Anbin
Zhang, Tian-hao
Zhou, Dinghao
Lu, Lewei
author_facet Sun, Chunyu
Liu, Bingyu
Cui, Zhichao
Shi, Junhan
Qi, Anbin
Zhang, Tian-hao
Zhou, Dinghao
Lu, Lewei
contents 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 (SLLMs), these methods are limited to a two-stage process, where automatic speech recognition (ASR) is combined with text-based retrieval. This sequential architecture suffers from high latency and error propagation. To address these limitations, we propose a unified embedding framework that eliminates the need for intermediate text representations. Specifically, the framework includes separate speech and text encoders, followed by a shared scaling layer that maps both modalities into a common embedding space. Our model reduces pipeline latency by 50\% while achieving higher retrieval accuracy compared to traditional two-stage methods. We also provide a theoretical analysis of the challenges inherent in end-to-end speech retrieval and introduce architectural principles for effective speech-to-document matching. Extensive experiments demonstrate the robustness of our approach across diverse acoustic conditions and speaker variations, paving the way for a new paradigm in multimodal SLLMs retrieval systems.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02603
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation
Sun, Chunyu
Liu, Bingyu
Cui, Zhichao
Shi, Junhan
Qi, Anbin
Zhang, Tian-hao
Zhou, Dinghao
Lu, Lewei
Audio and Speech Processing
Computation and Language
Sound
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 (SLLMs), these methods are limited to a two-stage process, where automatic speech recognition (ASR) is combined with text-based retrieval. This sequential architecture suffers from high latency and error propagation. To address these limitations, we propose a unified embedding framework that eliminates the need for intermediate text representations. Specifically, the framework includes separate speech and text encoders, followed by a shared scaling layer that maps both modalities into a common embedding space. Our model reduces pipeline latency by 50\% while achieving higher retrieval accuracy compared to traditional two-stage methods. We also provide a theoretical analysis of the challenges inherent in end-to-end speech retrieval and introduce architectural principles for effective speech-to-document matching. Extensive experiments demonstrate the robustness of our approach across diverse acoustic conditions and speaker variations, paving the way for a new paradigm in multimodal SLLMs retrieval systems.
title SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation
topic Audio and Speech Processing
Computation and Language
Sound
url https://arxiv.org/abs/2502.02603