SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Zhen, Yang, Chao-Han Huck, Yu, Yahan, Tian, Jinchuan, Li, Sheng, Hu, Ke, Chen, Zhehuai, Watanabe, Shinji, Cheng, Fei, Chu, Chenhui, Kurohashi, Sadao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911295843860480
author Wan, Zhen
Yang, Chao-Han Huck
Yu, Yahan
Tian, Jinchuan
Li, Sheng
Hu, Ke
Chen, Zhehuai
Watanabe, Shinji
Cheng, Fei
Chu, Chenhui
Kurohashi, Sadao
author_facet Wan, Zhen
Yang, Chao-Han Huck
Yu, Yahan
Tian, Jinchuan
Li, Sheng
Hu, Ke
Chen, Zhehuai
Watanabe, Shinji
Cheng, Fei
Chu, Chenhui
Kurohashi, Sadao
contents We introduce Speech-based Intelligence Quotient (SIQ) as a new form of human cognition-inspired evaluation pipeline for voice understanding large language models, LLM Voice, designed to assess their voice understanding ability. Moving beyond popular voice understanding metrics such as word error rate (WER), SIQ examines LLM Voice across three cognitive levels motivated by Bloom's Taxonomy: (1) Remembering (i.e., WER for verbatim accuracy); (2) Understanding (i.e., similarity of LLM's interpretations); and (3) Application (i.e., QA accuracy for simulating downstream tasks). We demonstrate that SIQ not only quantifies voice understanding abilities but also provides unified comparisons between cascaded methods (e.g., ASR LLM) and end-to-end models, identifies annotation errors in existing benchmarks, and detects hallucinations in LLM Voice. Our framework represents a first-of-its-kind intelligence examination that bridges cognitive principles with voice-oriented benchmarks, while exposing overlooked challenges in multi-modal training. Our code and data will be open source to encourage future studies.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models
Wan, Zhen
Yang, Chao-Han Huck
Yu, Yahan
Tian, Jinchuan
Li, Sheng
Hu, Ke
Chen, Zhehuai
Watanabe, Shinji
Cheng, Fei
Chu, Chenhui
Kurohashi, Sadao
Computation and Language
Artificial Intelligence
Symbolic Computation
Sound
Audio and Speech Processing
We introduce Speech-based Intelligence Quotient (SIQ) as a new form of human cognition-inspired evaluation pipeline for voice understanding large language models, LLM Voice, designed to assess their voice understanding ability. Moving beyond popular voice understanding metrics such as word error rate (WER), SIQ examines LLM Voice across three cognitive levels motivated by Bloom's Taxonomy: (1) Remembering (i.e., WER for verbatim accuracy); (2) Understanding (i.e., similarity of LLM's interpretations); and (3) Application (i.e., QA accuracy for simulating downstream tasks). We demonstrate that SIQ not only quantifies voice understanding abilities but also provides unified comparisons between cascaded methods (e.g., ASR LLM) and end-to-end models, identifies annotation errors in existing benchmarks, and detects hallucinations in LLM Voice. Our framework represents a first-of-its-kind intelligence examination that bridges cognitive principles with voice-oriented benchmarks, while exposing overlooked challenges in multi-modal training. Our code and data will be open source to encourage future studies.
title SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models
topic Computation and Language
Artificial Intelligence
Symbolic Computation
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.19361