Study: AI is better at reading than listening
USC researchers discovered that current audio large language models often miss paralinguistic cues such as tone and emotion, limiting their ability to truly listen. They introduced the VoxParadox benchmark, which evaluates models on ten tasks that contrast spoken words with nonverbal audio signals. The team also proposed techniques that markedly improve the models' interpretation of how something is said, not just what is said.
- ▪The study found that audio LLMs prioritize textual content and treat acoustic cues as secondary, leading to tone‑deaf behavior.
- ▪Researchers created the VoxParadox benchmark, testing models on tasks like emotion detection, pitch identification, and speaker counting with contradictory audio cues.
- ▪New methods developed by the team significantly enhanced the models' ability to understand paralinguistic information.
- ▪Misreading emotional tone in applications such as health assessments could produce harmful AI responses.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,368 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | USC Viterbi | School of Engineering |
| Canonical URL | https://viterbischool.usc.edu/news/2026/08/can-ai-read-the-room-usc-study-finds-ai-is-better-at-reading-than-listening/ |
| Publication time | Tue, 11 Aug 2026 05:05:23 +0000 |
| Retrieval time | 2026-08-11T05:10:42.002Z |
| Last seen | 2026-08-11T05:10:42.002Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | yyVxwZjvDHb_ · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Can AI Read the Room? USC Study Finds AI Is Better at Reading Than Listening Venice Tang | August 10, 2026 Researchers identified why audio AI models miss tone, emotion and other audio cues – and developed new solutions that dramatically improve their ability to interpret speech beyond words Can AI Read the Room? (Credit: Midjourney) Today, users can do more than exchange text with artificial intelligence (AI). From holding conversations and asking questions aloud to sending voice messages, AI can now process audios and respond in real time. But can AI really listen as well as it can read? A new study led by USC researchers suggests the answer is no.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at USC Viterbi | School of Engineering.
Discussion
0 commentsMore from USC Viterbi | School of Engineering
