---
title: "What managers' voices reveal in earnings calls"
description: "Earnings calls are a staple of finance and accounting research, read almost always as transcripts. In the AI journals, multimodal fusion is one of the biggest topics. Do voice and video carry information about firms that the words miss?"
url: https://scholar4ai.com/ideas/voices-in-earnings-calls
markdown_url: https://scholar4ai.com/ideas/voices-in-earnings-calls.md
license: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)
share_text: "What managers' voices reveal in earnings calls: Earnings calls are a staple of finance and accounting research, read almost always as transcripts. In the AI journals, multimodal fusion is one of the biggest topics."
date: "2026-10-23"
updated: "2026-10-23"
status: "seed"
tags: ["finance", "accounting", "ai"]
keywords: ["earnings conference calls", "earnings call transcripts", "multimodal fusion"]
---

# What managers' voices reveal in earnings calls

Earnings calls are a staple of finance and accounting research, read almost always as transcripts. In the AI journals, multimodal fusion is one of the biggest topics. Do voice and video carry information about firms that the words miss?

## What prompted this

Since October 2025, 50 papers in the archive carry an earnings-call keyword (20 in finance journals, 17 in accounting). None of them carries a multimodal, audio, voice, video or facial keyword. Meanwhile "multimodal fusion" appears on 502 papers, 495 of them in AI journals, and is the 11th most frequent keyword of the last 30 days. Earnings call transcripts are also among the most-mentioned data sources in finance on the [dataset ranking](/rankings/datasets).

## Questions

- Do executives' vocal cues (pitch, pauses, speech rate) predict earnings surprises, restatements or crash risk beyond what they say?
- Does the market price these cues during the call, or only later?
- Do managers learn to control them once analysts and machines listen?

## Data that could help

- Call recordings, which many firms post on their investor-relations sites, with timestamped transcripts.
- Speech-emotion models pretrained on public corpora such as IEMOCAP or RAVDESS, and intraday prices.
- A text-only baseline such as the Loughran-McDonald tone measure.

Voice analysis touches on privacy, so the study should use public recordings and report firm-level results only.

## Next step

Collect audio for one quarter of S&P 500 calls and test whether a pretrained speech-emotion score adds anything to a text-only tone measure.

## Related research activity

*The keywords this note follows, in the tracked finance, accounting, economics, management, operations research and AI journals as of 2026-10-26*

| Keyword | Papers, last 30 days | Rank | Papers per month, Oct 23 – Oct 26* | Papers, last 36 months |
|---|---:|---:|---|---:|
| earnings conference calls | 5 | #393 | 0, 2, 3, 3, 0, 1, 1, 0, 1, 2, 1, 1, 2, 0, 3, 0, 1, 2, 1, 4, 1, 2, 0, 0, 2, 1, 1, 0, 2, 3, 2, 4, 2, 3, 4, 3, 4 | 58 |
| earnings call transcripts | 1 | #2881 | 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 2, 0, 1, 0, 0, 2, 0, 0, 2, 0, 2, 0, 2, 2, 0, 1, 1 | 19 |
| [multimodal fusion](https://scholar4ai.com/keywords/multimodal-fusion.md) | 30 | #10 | 12, 12, 15, 19, 17, 26, 12, 21, 27, 14, 23, 22, 13, 19, 29, 26, 19, 31, 26, 37, 33, 32, 25, 22, 33, 39, 39, 66, 52, 47, 46, 48, 46, 47, 46, 28, 24 | 1,069 |

## Cite this page

Scholar4AI. (2026). What managers' voices reveal in earnings calls. Journal Research Rankings. Retrieved October 23, 2026, from https://scholar4ai.com/ideas/voices-in-earnings-calls

```bibtex
@misc{scholar4ai-ideas-voices-in-earnings-calls,
  author = {{Scholar4AI}},
  title = {What managers' voices reveal in earnings calls},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/ideas/voices-in-earnings-calls}},
  urldate = {2026-10-23},
  note = {Journal Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}
```

License: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/).