Go to MPAI-MMC V2.5 AI Modules

Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance

1 Functions

The Speech Translation with Descriptors (MMC‑STD) AIM receives an utterance (input speech) and a code identifying a language and produces an output speech which is a translation of the input speech in that language with the speech descriptors of the input speech:

Receives Speech Object Input Speech to be translated.
Language Selector Provides codes of the input and output languages.
Produces Translated Speech Object Synthesised translated Speech having the Descriptors of the input Speech Object.

2 Reference Model

Figure 1 depicts the Reference Model of the Speech Translation with Descriptors (MMC‑STD) AIM.

Speech Translation with Descriptors MMC-STD AIM

Figure 1 – The Speech Translation with Descriptors (MMC‑STD) AIM Reference Model

3 I/O Data

Table 1 specifies the Input and Output Data of the Speech Translation with Descriptors (MMC‑STD) AIM.

Table 1 – I/O Data of the Speech Translation with Descriptors (MMC‑STD) AIM

Input Description
Speech Object Input Speech.
Language Selector Provides codes of the input and output languages.
Output Description
Translated Speech Object Synthesised translated Speech having the Descriptors of the input Speech Object.

4 SubAIMs

4.1 Reference Model

Figure 2 depicts the Reference Model of the Speech Translation with Descriptors (MMC‑STD) Composite AIM.

Speech Translation with Descriptors MMC-STD Composite AIM

Figure 2 – The Speech Translation with Descriptors (MMC‑STD) Composite AIM

4.2 Operation

The MMC‑STD AIM receives input Speech and a Language Selector. Automatic Speech Recognition converts input Speech to Text. Entity Speech Description extracts Speech Descriptors from the input Speech. Text-to-Text Translation translates the Text into the target language. Text-to-Speech with Descriptors synthesises the translated Speech preserving the input Speech Descriptors.

4.3 Functions of SubAIMs

Table 2 gives the functions of the Speech Translation with Descriptors (MMC‑STD) SubAIMs.

Table 2 – Functions of the Speech Translation with Descriptors (MMC‑STD) SubAIMs

SubAIM Function
Automatic Speech Recognition Converts input Speech to Text.
Entity Speech Description Extracts Speech Descriptors from input Speech.
Text-to-Text Translation Translates Recognised Text into the target language.
Text-to-Speech with Descriptors Synthesises translated Speech preserving the input Speech Descriptors.

4.4 I/O Data of SubAIMs

Table 3 gives the Input and Output Data of the Speech Translation with Descriptors (MMC‑STD) SubAIMs.

Table 3 – I/O Data of the Speech Translation with Descriptors (MMC‑STD) SubAIMs

SubAIM Input Output
Automatic Speech Recognition Speech Object Recognised Text
Entity Speech Description Speech Object Speech Descriptors
Text-to-Text Translation Recognised Text
Language Selector		 Translated Text
Text-to-Speech with Descriptors Translated Text
Speech Descriptors		 Translated Speech Object

4.5 AIMs and JSON Metadata

Table 4 provides the links to the AIM specifications and JSON schemas. AIM1 indicates the Composite AIM and AIM2 its SubAIMs.

Table 4 – AIMs and JSON Metadata of the Speech Translation with Descriptors (MMC‑STD)

AIM1 AIM2 Name JSON
MMC‑STD Speech Translation with Descriptors X
MMC‑ASR Automatic Speech Recognition X
MMC‑ISD Entity Speech Description X
MMC‑TTT Text-to-Text Translation X
MMC‑TSD Text-to-Speech with Descriptors X

5 JSON Metadata

https://schemas.mpai.community/MMC/V2.5/AIMs/SpeechTranslationWithDescriptors.json

6 Profiles

No Profiles.

7 Reference Software

Under development.

8 Conformance Testing

Table 5 provides the Conformance Testing Method for the Speech Translation with Descriptors (MMC‑STD) Composite AIM. Conformance Testing of the individual SubAIMs is given by the individual AIM specifications.

If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present, and conform with the Qualifier, if present.

Table 5 – Conformance Testing Method for the Speech Translation with Descriptors (MMC‑STD) Composite AIM

Receives Speech Object Shall validate against Speech Object schema. Speech Data shall conform with Speech Qualifier.
Language Selector Shall validate against Language Selector schema.
Produces Translated Speech Object Shall validate against Speech Object schema. Speech Data shall conform with Speech Qualifier.

9 Performance Assessment

Not part of this specification.

Go to MPAI-MMC V2.5 AI Modules