ASR Decoding via Dynamic Beam Width Adjustment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Large vocabulary automatic speech recognition (ASR) systems face challenges in real-time operation on battery-operated devices due to high computational loads, leading to increased power consumption and reduced battery life, as they require significant resources to handle computational peaks during utterance processing.

Innovation Solution

The implementation of inner frame histogram pruning, which dynamically updates the beam width during decoding by eliminating tokens that fall outside the updated beam width, reducing the variability of compute needed and lowering resource usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If large vocabulary ASR systems are used to achieve high word recognition accuracy, then recognition quality is improved, but power consumption increases and battery life is reduced

Engineering Contradiction:
Improveword recognition accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The beam width is dynamically adjusted during decoding based on the histogram of token scores. The system transitions from a fixed beam width approach to a dynamic one where the beam width adapts to the distribution of token scores, allowing the system to maintain high recognition accuracy while reducing computational load and power consumption when full beam width is not necessary.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the beam width parameter during decoding based on the histogram analysis of token scores. By modifying this key parameter dynamically rather than keeping it fixed, the system can reduce computational requirements and power consumption while maintaining the necessary recognition accuracy for large vocabulary ASR.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If large vocabulary ASR systems are used to achieve high word recognition accuracy, then recognition quality is improved, but computational load increases making real-time operation difficult

Engineering Contradiction:
Improveword recognition accuracyVSAvoidreal-time processing capability
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The beam width is dynamically adjusted during decoding based on the histogram of token scores. The system transitions from a fixed beam width approach to a dynamic one where the beam width adapts to the distribution of token scores, allowing the system to maintain high recognition accuracy while reducing computational load and power consumption when full beam width is not necessary.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system applies partial action by using histogram pruning to eliminate tokens that fall outside the updated beam width. Instead of processing all tokens with full beam width, the system selectively processes only the necessary portion of tokens, reducing computational load while maintaining sufficient recognition accuracy for real-time operation.

Inventive Principle:
Principle #16Partial or excessive action

3Device complexity

If conventional beam search with fixed beam width is used, then implementation is simple, but computational peaks occur during utterance processing increasing power consumption

Engineering Contradiction:
Improvedecoder implementation complexityVSAvoidpower consumption during computational peaks
Core Design Contradiction:
Device complexityVSUse of energy by moving object

Solution Approach 1:

The beam width is dynamically adjusted during decoding based on the histogram of token scores. The system transitions from a fixed beam width approach to a dynamic one where the beam width adapts to the distribution of token scores, allowing the system to maintain high recognition accuracy while reducing computational load and power consumption when full beam width is not necessary.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs preliminary action by updating the beam width histogram before processing each token. This preliminary update allows the system to identify and eliminate tokens that would fall outside the updated beam width, preventing unnecessary computational peaks and reducing power consumption before the actual token processing occurs.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3886087B1Method and system of automatic speech recognition with highly efficient decoding
Publication Date: 2023.10.25 INTEL CORP
  • EP3886087B1 patent drawingFigure 1
  • EP3886087B1 patent drawingFigure 2
  • EP3886087B1 patent drawingFigure 3A

AI summary

A system, article, and method of automatic speech recognition with highly efficient decoding is accomplished by frequent beam width adjustment.