Speech-Driven End-to-End Language Discrimination towards Chinese Dialects

2026-06-16

AI Summary

This study addresses the limited performance of conventional text-driven approaches in distinguishing closely related language varieties, such as Chinese dialects, by proposing a speech-driven, end-to-end dialect identification framework. The method integrates MFCC acoustic features with word embedding–based semantic information and leverages a hybrid architecture combining CNNs, HMM-DNN acoustic modeling, and an attention mechanism to automatically extract discriminative dialect-specific lexical cues. As the first systematic investigation validating the efficacy of speech features for Chinese dialect identification, the proposed framework significantly outperforms state-of-the-art methods on two standard Chinese dialect corpora, demonstrating the superiority of a speech-driven strategy that jointly exploits acoustic and semantic information for fine-grained dialect recognition.

Abstract

Language discrimination among similar languages, varieties, and dialects is a challenging natural language processing task. The traditional text-driven focus leads to poor results. In this paper, we explore the effectiveness of speech-driven features towards language discrimination among Chinese dialects. First, we systematically explore the appropriateness of speech-driven MFCC features towards CNN-based language discrimination. Then, we design an end-to-end speech recognition model based on HMM-DNN to predict Chinese dialect words. We adopt attention to extract the discriminative words related to different Chinese dialects. Finally, through a CNN, we combine the word-level embedding and the MFCC-based features. Evaluation of two benchmark Chinese dialect corpora shows the appropriateness and effectiveness of the proposed speech-driven approach to fine-grained Chinese dialect discrimination compared to the state-of-the-art methods.

Problem

• language discrimination
• Chinese dialects
• speech-driven features
• natural language processing
• dialect identification

Innovation

• speech-driven
• end-to-end
• language discrimination
• Chinese dialects
• attention mechanism