Skip to content

Docs/improve audio filtering docs #120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Docs/improve audio filtering docs #120

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 12 additions & 10 deletions docs/speech-to-text/features/audio-filtering.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
description: "Learn how to utilize Audio Filtering to remove background speech"
description: "Learn how to utilize audio filtering to remove background speech"
keywords:
[
speechmatics,
Expand All @@ -15,19 +15,19 @@ keywords:
import Tabs from "@theme/Tabs";
import TabItem from "@theme/TabItem";

# Audio Filtering
# Audio filtering

Audio Filtering pre-processes input audio to remove low-volume background speech which might otherwise be detected and transcribed.
Audio filtering pre-processes input audio to remove low-volume background speech which might otherwise be detected and transcribed.

:::info
This can be useful, for example, in a call center to avoid transcribing other agents' speech from the background.
This can be useful, for example, in a call center to avoid transcribing other agents' background speech.
:::

If you're new to Speechmatics, start by exploring our guides on [Transcribing a File](/speech-to-text/batch/quickstart) or [Transcribing in Real-Time](/speech-to-text/realtime/quickstart).
If you're new to Speechmatics, start by exploring our guides on [transcribing a file](/speech-to-text/batch/quickstart) or [transcribing in real-time](/speech-to-text/realtime/quickstart).

## Example

To activate Audio Filtering, include the following configuration:
To activate audio filtering, include the following configuration:

```json
{
Expand All @@ -41,13 +41,15 @@ To activate Audio Filtering, include the following configuration:
}
}
```
This will avoid processing any audio which is below the `3.4` volume threshold. For technical details on how this threshold is used see [here](#technical-details)
This will avoid processing any audio which is below the `3.4` volume threshold. For technical details on how this threshold is calculated and used, see [here](#technical-details)

`volume_threshold` supports a range of `0 - 100` where `0` does not filter any audio and `100` removes all audio.

## Volume Labelling
In realtime mode, the threshold can be adjusted dynamically with the [SetRecognitionConfig](/api-ref/realtime-transcription-websocket#setrecognitionconfig) message.

If Audio Filtering is configured, words will be labelled with their volume like this (range for `volume_threshold` is `0-100`):
## Volume labelling

If audio filtering is configured, words will be labelled with their volume like this (the range for `volume_threshold` is `0-100`):

```json
{
Expand All @@ -69,7 +71,7 @@ These values can be used as a guide to setting the volume threshold, but we reco

To obtain volume labelling without filtering any audio, supply an empty config object (`{}`) or set the `volume_threshold` to `0.0`.

## Technical Details
## Technical details

Once the audio is in a raw format (16kHz 16bit mono), it is split into 0.01s chunks. For each chunk, the root mean square amplitude of the signal is calculated, and scaled to the range `0 - 100`. If the volume is less than the supplied cut-off, the chunk will be replaced with silence.

Expand Down