ASR Audio Encoder Pretraining with Synthetic Speech and Contrastive Losses

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Deep learning-based automatic speech recognition (ASR) models tend to overfit training data, leading to difficulties in generalizing to unseen data, especially when the training data is not extensive enough.

Innovation Solution

The method involves pre-training an audio encoder using a combination of contrastive self-supervised losses, supervised losses, and consistency losses, leveraging un-transcribed non-synthetic speech utterances, synthetic speech representations, and transcribed non-synthetic speech utterances to jointly learn speech and text representations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If ASR models are trained with extensive training data, then accuracy improves, but model complexity and training resources increase

Engineering Contradiction:
ImproveASR accuracyVSAvoidmodel complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies pre-training on synthetic speech data before fine-tuning on real speech data. This preliminary action allows the model to learn general speech patterns and representations from easily generated synthetic data, reducing the amount of complex real training data needed to achieve high accuracy while avoiding excessive model complexity

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent uses text-to-speech synthesis to create synthetic speech copies that mimic real speech patterns. These synthetic copies serve as proxies for real speech data, allowing the model to learn from abundant synthetic data without requiring proportionally large amounts of real speech data, thus improving accuracy without linearly increasing training resource requirements

Inventive Principle:
Principle #26Copying

2Productivity

If ASR models are trained with limited training data, then training resources are reduced, but overfitting increases and generalization ability decreases

Engineering Contradiction:
Improvetraining efficiencyVSAvoidgeneralization ability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent generates synthetic speech copies from text using TTS systems, creating augmented training data without requiring additional real speech recordings. This copying approach allows the model to train on diverse synthetic examples that improve generalization ability while maintaining training efficiency with limited real data resources

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent modifies speech data parameters by applying various transformations to synthetic speech (noise addition, pitch shifting, time stretching) to create diverse training examples. These parameter changes enable the model to learn robust representations that generalize better to unseen data while training on limited real speech data

Inventive Principle:
Principle #35Parameter changes

3Quantity of substance

If synthesized speech is used to increase training data volume, then data quantity increases, but data quality and realism may decrease

Engineering Contradiction:
Improvetraining data volumeVSAvoiddata quality
Core Design Contradiction:
Quantity of substanceVSManufacturing precision

Solution Approach 1:

The patent uses synthetic speech as a preliminary training step before fine-tuning on real speech data. This two-stage approach allows the model to first learn general patterns from abundant synthetic data, then refine its performance on high-quality real data, achieving both large effective training volume and high data quality

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates a composite training dataset combining synthetic speech and real speech data. This composite approach leverages the advantages of both data types: the abundance and diversity of synthetic data plus the authenticity and quality of real data, achieving both high quantity and high quality in the effective training set

Inventive Principle:
Principle #40Composite materials

Data Source

PatentEP4338156B1Advancing the use of text and speech in ASR pretraining with consistency and contrastive losses
Publication Date: 2025.06.04 GOOGLE LLC
  • EP4338156B1 patent drawingFigure 1
  • EP4338156B1 patent drawingFigure 2
  • EP4338156B1 patent drawingFigure 3A

AI summary

A method (600) includes receiving training data that includes unspoken text utterances (320), un-transcribed non-synthetic speech utterances (306), and transcribed non-synthetic speech utterances (304). Each unspoken text utterance is not paired with any corresponding spoken utterance of non-synthetic speech. Each un-transcribed non- synthetic speech utterance is not paired with a corresponding transcription. Each transcribed non-synthetic speech utterance is paired with a corresponding transcription (302). The method also includes generating a corresponding synthetic speech representation (332) for each unspoken textual utterance of the received training da.ta using a text-to-speech model (330). The method also includes pre-training an audio encoder (210) on the synthetic speech representations generated for the unspoken textual utterances, the un-transcribed non-synthetic speech utterances, and the transcribed non- synthetic speech utterances to teach the audio encoder to jointly learn shared speech and text representations