Speech Translation Pipeline Using an Intermediate Language

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing translation and transcription systems face challenges in efficiency, latency, and computational resource management due to the need for numerous direct translation models between language pairs and the complexity of handling nuanced linguistic contexts.

Innovation Solution

A token-based translation and transcription system using an intermediate language and differently-sized look-ahead encoders to reduce the number of translation models required and enhance processing efficiency, with smaller encoders for transcription and larger encoders for translation to capture broader contextual information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If direct translation models are used for each language pair, then translation accuracy may be maintained, but the number of required models and computational resources increase significantly

Engineering Contradiction:
Improvetranslation accuracyVSAvoidnumber of translation models
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediate language (e.g., English) as a mediator between source and target languages. Instead of creating direct translation models for every language pair, the system translates from the source language to the intermediate language, then from the intermediate language to the target language. This reduces the number of required models from O(n²) to O(2n), where n is the number of languages, while maintaining translation quality through the use of a standardized intermediate representation.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The intermediate language serves as a universal intermediary that can handle translations between any language pair. A single intermediate language model can be used for all source languages, and a single target language model can handle all target languages, making the system multi-functional and scalable without requiring language-specific model pairs.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If larger encoders are used to capture broader contextual information, then translation accuracy improves, but computational resources and processing time increase

Engineering Contradiction:
Improvetranslation accuracyVSAvoidcomputational resources
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies different encoder sizes to different functional requirements within the system. Smaller, more efficient encoders are used for transcription tasks where speed is critical, while larger encoders with broader contextual windows are used specifically for translation tasks where accuracy and contextual understanding are paramount. This local differentiation optimizes resource allocation based on task-specific needs.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system segments the translation process into distinct stages (transcription to intermediate language, then intermediate language to target language) with different encoder configurations for each stage. This allows the system to use computationally intensive large encoders only where necessary (in the translation stage) while using lighter encoders for the transcription stage, reducing overall computational burden.

Inventive Principle:
Principle #1Segmentation

3Adaptability or versatility

If more translation models are deployed to handle diverse language pairs, then language coverage improves, but system scalability and maintenance become more difficult

Engineering Contradiction:
Improvelanguage coverageVSAvoidsystem scalability
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The intermediate language acts as a universal interface that enables the system to handle any language pair through a standardized two-stage process. New languages can be added by training only two new models (source to intermediate, and intermediate to target) rather than requiring models for every possible language pair, dramatically improving scalability and reducing maintenance complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The standardized intermediate language serves as a mediator that decouples source and target language models, allowing independent development and deployment. This intermediary layer simplifies system architecture and makes the system highly adaptable to new language pairs while maintaining consistent translation quality through the standardized intermediate representation.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4704079A1System and method for consecutive speech-to-text and text-to-text translation
Publication Date: 2026.03.04 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4704079A1 patent drawingFigure 1
  • EP4704079A1 patent drawingFigure 2
  • EP4704079A1 patent drawingFigure 3A~3D

AI summary

A computer-implemented method, computer program product and computing system for: receiving speech in a source language to define source language speech; performing a first token-based translation of the source language speech into text of an intermediate language to define intermediate language text; and performing a second token-based translation from the intermediate language text into text of a target language to define target language text.