Size-Constrained Neural Network for Edge Speech Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automatic speech recognition (ASR) systems face challenges in deploying small-sized models on resource-constrained devices due to large model sizes and the need for training on short utterances, which is complicated by data loss during label generation for feature frames.

Innovation Solution

A method and system for automatic speech recognition in resource-constrained devices that involves receiving an audio file, transcribing it to generate an Intermediate Greedy Transcript, marking split locations, splicing the audio into segments, and training a size-constrained neural network model using these segments to recognize short bursts of words, utilizing techniques like Connectionist Temporal Classification (CTC) and Recurrent Neural Networks (RNNs).

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If deep neural network models are trained for speech recognition, then recognition accuracy is improved, but model size becomes too large to fit in cache memory of resource-constrained devices

Engineering Contradiction:
Improvespeech recognition accuracyVSAvoidmodel size
Core Design Contradiction:
Measurement precisionVSVolume of stationary object

Solution Approach 1:

The patent segments the continuous audio stream into discrete speech units (phonemes, syllables, or words) and processes them independently through the neural network. This segmentation allows the model to be trained on small, manageable units rather than requiring large contextual windows, enabling deployment on resource-constrained devices while maintaining recognition accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the temporal parameter of speech processing by focusing on short-duration speech units instead of long utterances. By modifying the time dimension parameter (processing brief sounds rather than extended speech), the model achieves accurate recognition with significantly reduced complexity and size suitable for edge devices.

Inventive Principle:
Principle #35Parameter changes

2Volume of stationary object

If the model is trained to recognize short bursts of words, then model size is reduced for resource-constrained devices, but data loss occurs during label generation for feature frames

Engineering Contradiction:
Improvemodel sizeVSAvoiddata loss during label generation
Core Design Contradiction:
Volume of stationary objectVSLoss of information

Solution Approach 1:

The patent performs preliminary alignment of speech units with their corresponding labels during the data preparation phase. By pre-synchronizing the temporal boundaries of short speech bursts with their ground truth labels, the system eliminates data loss that would otherwise occur during online label generation, ensuring accurate training data without requiring manual intervention.

Inventive Principle:
Principle #10Preliminary action

3Loss of time

If online speech recognition is implemented on resource-constrained devices, then low latency and privacy preservation are achieved, but limited memory and processing capacity constrain model size

Engineering Contradiction:
ImprovelatencyVSAvoidmodel size
Core Design Contradiction:
Loss of timeVSVolume of stationary object

Solution Approach 1:

The patent segments speech into brief units that can be processed independently and quickly, enabling low-latency recognition on resource-constrained devices. This segmentation approach allows the small model to make rapid decisions on short sound bursts without requiring extensive computation or large memory resources.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent employs a simplified model that processes only the essential features of short speech units rather than analyzing complete utterances with full contextual information. This partial processing approach reduces computational requirements and model size while maintaining sufficient accuracy for practical applications on edge devices.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4002354B1Method and system for automatic speech recognition in resource constrained devices
Publication Date: 2024.06.12 TATA CONSULTANCY SERVICES LTD
  • EP4002354B1 patent drawingFigure 1
  • EP4002354B1 patent drawingFigure 2
  • EP4002354B1 patent drawingFigure 3A

AI summary

Automatic speech recognition techniques are implemented in resource constrained devices such as edge devices in internet of things where on-device speech recognition is required for low latency and privacy preservation. Existing neural network models for speech recognition have a large size and are not suitable for deployment in such devices. The present disclosure provides an architecture of a size constrained neural network and a method of training the size constrained neural network. The architecture of the size constrained neural network provides a way of increasing or decreasing number of feature blocks to achieve an accuracy-model size trade off. The method of training the size constrained neural network comprises creating a training dataset with short utterances and training the size constrained neural network with the training dataset to learn short term dependencies in the utterances. The trained size constrained neural network model is suitable for deployment in resource constrained devices.