Speech Enhancement Training for Artifact-Resistant Live Captioning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional speech enhancement systems introduce artifacts that degrade the performance of live captioning, and training with simulated data limits the model's adaptability to real-world noise conditions.

Innovation Solution

A multi-task training framework is employed to optimize speech enhancement models by using a combination of simulated and real-world noisy recordings, along with ground truth transcription labels, to generate noise-suppressed speech outputs that retain signal quality and improve live captioning performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Object-affected harmful factors

If conventional speech enhancement systems are used to remove background noise, then noise suppression is improved, but artifacts are introduced that degrade live captioning performance

Engineering Contradiction:
Improvebackground noiseVSAvoidartifacts
Core Design Contradiction:
Object-affected harmful factorsVSObject-generated harmful factors

Solution Approach 1:

The patent introduces an intermediary loss function (ASR loss) that mediates between noise suppression and artifact reduction. The ASR loss acts as a bridge, guiding the speech enhancement model to produce outputs that are not only clean but also suitable for downstream automatic speech recognition tasks, thereby reducing artifacts while maintaining noise suppression capability

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The speech enhancement model is designed to serve multiple functions simultaneously: it performs traditional noise suppression while also optimizing for live captioning performance. The multi-task training framework enables the model to fulfill both roles, making it universally applicable to different downstream tasks without requiring separate models

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

2Productivity

If simulated data is used to train speech enhancement models, then training efficiency is improved, but the model's adaptability to real-world noise conditions deteriorates

Engineering Contradiction:
Improvetraining efficiencyVSAvoidadaptability to real-world noise
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The training process uses simulated data as a preliminary step to establish a baseline model with good noise suppression capability. This preliminary training on controlled simulated data is followed by fine-tuning on real-world data, allowing the model to first learn fundamental noise removal skills efficiently, then adapt to real-world variations

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent changes the training data parameters from purely simulated to a combination of simulated and real-world data. By adjusting the data source parameter and incorporating real recordings with ground truth transcriptions, the model adapts its parameters to handle the complexity and variability of real-world noise conditions while retaining the efficiency benefits of simulated data training

Inventive Principle:
Principle #35Parameter changes

3Object-affected harmful factors

If noise suppression is applied to audio, then background noise is reduced, but transcription accuracy deteriorates

Engineering Contradiction:
Improvebackground noiseVSAvoidtranscription accuracy
Core Design Contradiction:
Object-affected harmful factorsVSMeasurement precision

Solution Approach 1:

The patent implements feedback by using the ASR model to evaluate the output of the speech enhancement model. The ASR loss computed from transcribing the enhanced audio provides feedback to the enhancement model, guiding it to adjust its parameters to produce outputs that improve transcription accuracy while maintaining noise suppression

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent merges two previously separate processes into a unified training framework: speech enhancement and automatic speech recognition. By combining these tasks and training them jointly with shared loss functions, the system ensures that noise suppression operations are coordinated with transcription requirements, preventing the degradation of transcription accuracy

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP4348634B1Systems and methods for human listening and live captioning
Publication Date: 2025.08.20 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4348634B1 patent drawingFigure 1
  • EP4348634B1 patent drawingFigure 2
  • EP4348634B1 patent drawingFigure 3

AI summary

Systems and methods are provided for generating and operating a speech enhancement model optimized for generating noise-suppressed speech outputs for improved human listening and live captioning. A computing system obtains a speech enhancement model trained on a first training dataset to generate noise-suppressed speech outputs and an automatic speech recognition model trained on a second training dataset to generate transcription labels for spoken language utterances. A third training dataset comprising a set of spoken language utterances is applied to the speech enhancement model to obtain a first noise-suppressed speech output which is applied to the automatic speech recognition model to generate a noise-suppressed transcription output for the set of spoken language utterances. Speech enhancement model parameters are updated to optimize the speech enhancement model to generate optimized noise-suppressed speech outputs based on a comparison of the noise-suppressed transcription output and ground truth transcription labels.