Adaptive Frame Batching for Low-Latency Speech Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Neural network-based automatic speech recognition (ASR) systems experience undesirable user-perceived latency due to batch processing of audio frames, and conventional approaches increase training and deployment costs by using multiple models to address latency requirements.

Innovation Solution

Implement dynamic batch sizing and look-ahead frames in ASR processing, adjusting batch size and look-ahead frames based on generated word hypotheses and end-of-speech detection to reduce latency while maintaining recognition accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If audio frames are batched into a batch of two or more frames for joint processing, then recognition accuracy and performance are improved, but user-perceived latency increases due to waiting for all frames to be received

Engineering Contradiction:
Improverecognition accuracyVSAvoiduser-perceived latency
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The batch size is made dynamic rather than fixed. The system starts with a small initial batch size to reduce latency, then adaptively increases the batch size after generating a word hypothesis to improve recognition accuracy. This dynamic adjustment resolves the contradiction by allowing the system to prioritize speed initially, then accuracy later in the processing pipeline.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs preliminary processing with a small initial batch size before committing to larger batch processing. By generating an early word hypothesis with minimal batching, the system provides quick initial results to the user, then refines accuracy in subsequent processing stages without requiring the user to wait for complete large-batch processing.

Inventive Principle:
Principle #10Preliminary action

2Loss of time

If several physically-different models are used to satisfy different latency requirements, then latency requirements are met, but processor-related training and deployment costs multiply

Engineering Contradiction:
ImprovelatencyVSAvoidprocessor-related training and deployment costs
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

A single ASR model is designed to perform multiple functions by processing batches of varying sizes. The same model handles both low-latency scenarios (small batches) and high-accuracy scenarios (large batches), eliminating the need for multiple specialized models and reducing training and deployment costs while satisfying different latency requirements.

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

Solution Approach 2:

Instead of changing models to satisfy different latency requirements, the system changes the batch size parameter. By dynamically adjusting the batch size fed to a single model, the system can optimize for latency when needed (small batches) or for accuracy when needed (large batches), achieving the same effect as multiple models without the associated costs and complexity.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4401073B1Adaptive frame batching to reduce speech recognition latency
Publication Date: 2026.04.01 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4401073B1 patent drawingFigure 1A~1B
  • EP4401073B1 patent drawingFigure 1C~1D
  • EP4401073B1 patent drawingFigure 2

AI summary

Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size, and input of the second batch to the speech recognition network.