Saved in:
Bibliographic Details
Main Authors: Mishra, Ayushi, Bai, Yang, Narayanasamy, Priyadarshan, Garg, Nakul, Roy, Nirupam
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.08907
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913807250489344
author Mishra, Ayushi
Bai, Yang
Narayanasamy, Priyadarshan
Garg, Nakul
Roy, Nirupam
author_facet Mishra, Ayushi
Bai, Yang
Narayanasamy, Priyadarshan
Garg, Nakul
Roy, Nirupam
contents Integrating spatial context into large language models (LLMs) has the potential to revolutionize human-computer interaction, particularly in wearable devices. In this work, we present a novel system architecture that incorporates spatial speech understanding into LLMs, enabling contextually aware and adaptive applications for wearable technologies. Our approach leverages microstructure-based spatial sensing to extract precise Direction of Arrival (DoA) information using a monaural microphone. To address the lack of existing dataset for microstructure-assisted speech recordings, we synthetically create a dataset called OmniTalk by using the LibriSpeech dataset. This spatial information is fused with linguistic embeddings from OpenAI's Whisper model, allowing each modality to learn complementary contextual representations. The fused embeddings are aligned with the input space of LLaMA-3.2 3B model and fine-tuned with lightweight adaptation technique LoRA to optimize for on-device processing. SING supports spatially-aware automatic speech recognition (ASR), achieving a mean error of $25.72^\circ$-a substantial improvement compared to the 88.52$^\circ$ median error in existing work-with a word error rate (WER) of 5.3. SING also supports soundscaping, for example, inference how many people were talking and their directions, with up to 5 people and a median DoA error of 16$^\circ$. Our system demonstrates superior performance in spatial speech understanding while addressing the challenges of power efficiency, privacy, and hardware constraints, paving the way for advanced applications in augmented reality, accessibility, and immersive experiences.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08907
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatial Audio Processing with Large Language Model on Wearable Devices
Mishra, Ayushi
Bai, Yang
Narayanasamy, Priyadarshan
Garg, Nakul
Roy, Nirupam
Sound
Computation and Language
Audio and Speech Processing
Integrating spatial context into large language models (LLMs) has the potential to revolutionize human-computer interaction, particularly in wearable devices. In this work, we present a novel system architecture that incorporates spatial speech understanding into LLMs, enabling contextually aware and adaptive applications for wearable technologies. Our approach leverages microstructure-based spatial sensing to extract precise Direction of Arrival (DoA) information using a monaural microphone. To address the lack of existing dataset for microstructure-assisted speech recordings, we synthetically create a dataset called OmniTalk by using the LibriSpeech dataset. This spatial information is fused with linguistic embeddings from OpenAI's Whisper model, allowing each modality to learn complementary contextual representations. The fused embeddings are aligned with the input space of LLaMA-3.2 3B model and fine-tuned with lightweight adaptation technique LoRA to optimize for on-device processing. SING supports spatially-aware automatic speech recognition (ASR), achieving a mean error of $25.72^\circ$-a substantial improvement compared to the 88.52$^\circ$ median error in existing work-with a word error rate (WER) of 5.3. SING also supports soundscaping, for example, inference how many people were talking and their directions, with up to 5 people and a median DoA error of 16$^\circ$. Our system demonstrates superior performance in spatial speech understanding while addressing the challenges of power efficiency, privacy, and hardware constraints, paving the way for advanced applications in augmented reality, accessibility, and immersive experiences.
title Spatial Audio Processing with Large Language Model on Wearable Devices
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2504.08907