1 Definition
A Data Type whose instance represents – or is rendered to be perceived – as an analogue signal with vocal characteristics.
2 Functional Requirements
A Speech Qualifier must allow the expression of the following Elements:
- Sub-Types
- Formats
- Content
- Transport
- Attributes
- Source
- Metadata
- Spatial Attributes
- Device
3 Syntax
https://schemas.mpai.community/TFA/V1.0/data/SpeechQualifier.json
4 Semantics
-
Sub-Types
- No Sub-Types
-
Formats:
-
Content
- Definition: The method used to digitally represent speech.
- Methods
- PCM
- Definition: the digital representation of speech using samples.
- Characteristics:
- Sampling Frequency: Number expressing kHz.
- Sample Precision: Number expressing bits/sample.
- Compression Formats:
- Definition: the method used to reduce the number of bits required to represent a Speech instance.
- Methods
- G711A (https://www.itu.int/rec/dologin_pub.asp?lang=f&id=T-REC-G.711-198811-I!!PDF-E&type=items)
- G711mu (https://www.itu.int/rec/dologin_pub.asp?lang=f&id=T-REC-G.711-198811-I!!PDF-E&type=items)
- MP3 (ISO/IEC 11172-3:1993)
- AAC2 (ISO/IEC 13818-7:2006)
- AAC4 (ISO/IEC 14496-3:2019)
- PCM
-
Transport
- Definition: the method used to transport Speech.
- Methods
- File
- Definition: the container of Speech.
- Containers
- WAV (https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.2088-1-201910-I!!PDF-E.pdf)
- MP4 (ISO/IEC 14496-12:2022)
- Stream
- Definition: the method to move Content across the network.
- Methods
- DASH (ISO/IEC 23009-1:2022)
- HTTP Live Streaming (https://datatracker.ietf.org/doc/html/rfc8216)
- File
-
-
Attributes
-
Source
- Definition: the type of Speech instance
- Types
- Real
- Synthetic
-
Metadata
- Definition: the descriptive Data attached to a Speech instance.
- Descriptions
- Language
- Definition: the method used to indicate the Language used by a Speech instance.
- Methods
- ISO 636-1
- ISO 636-2
- ISO 636-3
- Speaker Identity
- Definition: the method used to identify a speaker.
- Methods
- Instance Identifier ((https://mpai.community/standards/mpai-osd/v1-1/data-types/instance-identifier/)
- Content Description
- Definition: the method used to describe the content of a Speech instance in words
- Methods
- ASCII
- Unicode (ISO/IEC10646)
- Entity Internal Status
- Definition: the method used to describe the internal status such as cognitive state, emotion, and social attitude.
- Methods
- Personal Status (https://mpai.community/standards/mpai-mmc/v2-2/data-types/personal-status/)
- Language
-
Device
- Definition: elements of the device that captured the Speech instance.
- Elements
- Device ID
- Definition: an identifier of the device that captured the Speech instance
- Methods
- A string
- Device Location
- Definition: method to define the position and orientation of the device in a real or virtual space that captured the Speech instance.
- Methods
- Point of View (https://mpai.community/standards/mpai-osd/v1-1/data-types/point-of-view/)
- Sensor Characteristics
- Definition: sensor features having an impact on the captured Speech instance
- Sensor Features
- Omnidirectional
- Figure of eight
- Cardioid
- Supercardioid
- Hypercardioid
- Device ID
-