1 Definition | 2 Functional Requirements | 3 Syntax |
4 Semantics | 5 Conformance Testing | 6 Performance Assessment |
1 Definition
A Data Type representing characteristic elements extracted from the input speech, specifically Pitch, Intensity, Tempo, Personal Status, and NNSpeechFeatures in a period of time.
2 Functional Requirements
Speech Descriptors may include Neural Network Descriptors.
3 Syntax
https://schemas.mpai.community/MMC/V2.3/data/SpeechDescriptors.json
4 Semantics
Label | Size | Description |
Header | N1 Bytes | Speech Descriptors Header |
– Standard – SpeechDescriptors | 9 Bytes | The characters “MMC-SPD-V” |
– Version | N2 Bytes | Major version – 1 or 2 characters |
– Dot-separator | 1 Byte | The character “.” |
– Subversion | N3 Byte | Minor version – 1 or 2 characters |
MInstanceID | N4 Bytes | ID of the Metaverse Instance. |
SpeechDescriptorsID | N5 Bytes | ID of Speech Descriptors. |
SpeechDescriptorsData | N7 Bytes | Data associated with Input Text. |
NNSpeechFeatures | N8 Bytes | The output vector of a neural-network using Speech as input. |
Duration | N9 Bytes | The Time in which the Speech Descriptors are computed. |
Pitch | N10 Bytes | Real number measuring the fundamental frequency of Speech in Hz (Hertz). |
Intensity | N11 Bytes | Real number measuring the Energy of Speech in dBs (decibel). |
Tempo | N12 Byte | Real number measuring the rate at which specified linguistic units (Phonemes, Syllables, or Words) are produced. |
Personal Status | N13 Byte | The Speech Personal Status carried by the input speech. |
5 Conformance Testing
A Data instance Conforms with MPAI-MMC V2.3 Speech Descriptors (MMC-SPD) if:
- The Data validates against the Speech Descriptors’ JSON Schema.
- All Data in the Speech Descriptors’ JSON Schema
- Have the specified type
- Validate against their JSON Schemas
- Conform with their Data Qualifiers if present.
6 Performance Assessment