Subword-Based Speech Recognition Network Structure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech recognition systems face limitations in speed due to character-based end-to-end models and complexity with word-based models, and subword-based models suffer from training-recognition mismatches.
Innovation Solution
The implementation of a subword-based end-to-end speech recognition apparatus that uses a subword dictionary to simplify the network structure, estimate sequences of subwords, and convert them into recognizable words, minimizing mismatches between training and recognition operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a character-based end-to-end acoustic model is used, then the model can process speech signals, but the output length becomes too long and recognition speed is limited
Solution Approach 1:
The patent segments words into subwords (e.g., morphemes, syllables, or character n-grams) to create a intermediate representation. This segmentation reduces the output length compared to character-based models while maintaining better linguistic structure than word-based models. The subword units serve as building blocks that can be efficiently processed by the acoustic model.
Solution Approach 2:
The patent applies different processing strategies to different parts of the speech recognition pipeline. The acoustic model uses subword-based output for local efficiency, while a separate language model component handles global linguistic constraints. This local optimization allows speed improvement in the acoustic processing stage without sacrificing overall recognition accuracy.
2Ease of manufacture
If a word-based end-to-end acoustic model is used, then recognition can be performed, but the great number of output classes makes implementation difficult
Solution Approach 1:
The patent divides the large vocabulary into smaller subword units, reducing the number of output classes the acoustic model must handle directly. Instead of outputting thousands of word classes, the model outputs a smaller set of subword classes that can be recombined to form complete words, making implementation more manageable.
Solution Approach 2:
The patent introduces a new dimension in the output space by using subword representations. Rather than directly mapping acoustic features to word classes (one-dimensional mapping), the system maps to subword sequences that can be composed into words, effectively adding a compositional dimension to the recognition process.
3Productivity
If a subword-based end-to-end acoustic model is used, then output length is reduced, but mismatches occur between training and recognition due to unrecognized subwords
Solution Approach 1:
The patent performs preliminary preparation by creating a comprehensive subword dictionary during the training phase that anticipates all possible subword units that may appear during recognition. This preliminary action ensures that the model is trained on the same subword vocabulary it will encounter during recognition, preventing mismatches.
Solution Approach 2:
The patent implements feedback mechanisms where the system monitors for unrecognized subwords during recognition and uses this information to improve the subword dictionary and model. This feedback loop ensures continuous alignment between training and recognition capabilities, reducing mismatches over time.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A processor-implemented speech recognition method includes: extracting a speech feature from an input speech to be recognized; estimating a first sequence of first subwords corresponding to at least one portion of the input speech based on the extracted speech feature; converting the first sequence to a second sequence of at least one second subword by combining at least two of the first subwords; and recognizing the input speech by recognizing a remaining portion of the input speech based on the second sequence.