Joint Speech Recognition Training for Noisy Multi-Speaker Audio

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional speech recognition technologies suffer from low accuracy in challenging conditions, such as interference from other speakers or music, due to the lack of effective integration of speech separation, enhancement, and recognition models.

Innovation Solution

A joint training method is employed to fuse loss functions from speech separation and enhancement models with a robust representation model and a speech recognition model, using intermediate neural networks to bridge the gap between human-oriented and machine-oriented speech processing tasks, enabling end-to-end training and improving recognition accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If speech separation and enhancement are performed separately from speech recognition, then the processing pipeline is simpler and more modular, but the speech recognition accuracy is low in challenging conditions

Engineering Contradiction:
Improvespeech recognition accuracyVSAvoidmodel integration complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges speech separation, speech enhancement, and speech recognition models into a unified end-to-end trainable system. The separated models are integrated such that they share common representations and can be jointly optimized through a single loss function, thereby improving recognition accuracy while maintaining reasonable system complexity through shared computational layers.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent creates a multi-functional system where the speech processing model serves multiple purposes: it performs speech separation, speech enhancement, and speech recognition simultaneously. The shared neural network layers extract features that are useful for all three tasks, making the system more efficient and accurate compared to separate specialized models.

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

2Reliability

If conventional separate models are used for speech separation and recognition, then the system is easier to implement, but the word error rate is high under noise conditions

Engineering Contradiction:
Improverecognition accuracy in noiseVSAvoidsystem implementation ease
Core Design Contradiction:
ReliabilityVSEase of manufacture

Solution Approach 1:

The patent combines multiple speech processing functions into a single integrated model that can be implemented end-to-end. This merging approach improves noise robustness by allowing the model to learn correlations between separation, enhancement, and recognition tasks, while the unified implementation simplifies deployment compared to coordinating multiple separate models.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces intermediate representations and shared feature extraction layers that act as mediators between the input speech signal and the final recognition output. These intermediate layers enable the model to progressively refine the speech representation, improving robustness to noise while maintaining a straightforward sequential implementation structure.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If speech separation and enhancement are performed first, then the speech signal is cleaner, but the overall system accuracy remains limited without joint optimization

Engineering Contradiction:
Improvespeech signal qualityVSAvoidrecognition accuracy
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent ensures continuous optimization throughout the entire speech processing pipeline by enabling end-to-end training. The loss function propagates gradients continuously from the recognition output back through the enhancement and separation stages, allowing the model to continuously refine all intermediate representations to maximize final recognition accuracy rather than optimizing each stage independently.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The patent implements feedback mechanisms through backpropagation where the recognition loss is fed back to adjust the parameters of the speech separation and enhancement components. This feedback loop allows the model to learn how different separation and enhancement strategies affect final recognition accuracy, thereby optimizing the entire pipeline for the ultimate goal of accurate speech recognition.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4006898B1Voice recognition method, device, and computer-readable storage medium
Publication Date: 2026.02.25 TENCENT TECHNOLOGY (SHENZHEN) CO LTD
  • EP4006898B1 patent drawingFigure 1~2
  • EP4006898B1 patent drawingFigure 3~4
  • EP4006898B1 patent drawingFigure 5~6

AI summary

Provided are a voice recognition method, device, and computer-readable storage medium, said method comprising: obtaining a first loss function of a voice separation enhancement model and a second loss function of a voice recognition model (S202); performing back-propagation on the basis of the second loss function to train an intermediate model bridged between the voice separation enhancement model and the voice recognition model, to obtain a robust representation model (S204); combining the first loss function and the second loss function to obtain a target loss function (S206); performing joint training of the voice separation enhancement model, the robust representation model, and the voice recognition model on the basis of the target loss function, and ending training when a preset convergence condition is satisfied (S208).