Speech-Driven End-to-End Language Discrimination towards Chinese Dialects
Summary
This paper investigates speech-driven features for fine-grained discrimination among Chinese dialects, using an end-to-end model that combines MFCC-based features with word-level embeddings via a CNN, outperforming text-driven methods.
View Cached Full Text
Cached at: 06/18/26, 05:45 AM
# Speech-Driven End-to-End Language Discrimination towards Chinese Dialects Source: [https://arxiv.org/abs/2606.18584](https://arxiv.org/abs/2606.18584) [View PDF](https://arxiv.org/pdf/2606.18584) > 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\. ## Submission history From: Fan Xu \[[view email](https://arxiv.org/show-email/7f279a82/2606.18584)\] **\[v1\]**Wed, 17 Jun 2026 01:23:58 UTC \(1,045 KB\)
Similar Articles
Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation
The paper proposes a novel framework (CDDTLDA) using transfer learning and data augmentation to improve Chinese dialects discrimination under low-resource conditions, achieving state-of-the-art results on two benchmark corpora.
DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects
DialectS2S is an end-to-end speech dialogue model for low-resource Chinese dialects, introducing a scalable data synthesis pipeline and a two-stage post-training strategy with self-aligned speech supervision. Experiments show improvements in dialect consistency, response quality, and intelligibility, with fully open-sourced models, data, and code.
Dolphin-CN-Dialect: Where Chinese Dialects Matter
Dolphin-CN-Dialect is a streaming-capable ASR model that improves dialect recognition through temperature-based sampling and redesigned tokenization, achieving competitive performance with a smaller model size.
Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment
This paper introduces CLeaD, a supervised contrastive alignment framework for cross-lingual depression detection from speech using WavLM embeddings. It reveals that previous results were inflated due to speaker identity leakage and achieves modest improvements on Mandarin speakers.
Probing in the Wild: A Case Study of Self-Supervised Speech Representations on Mandarin Sub-dialects with Unsupervised Articulatory Analysis
This paper presents a case study using unsupervised articulatory probing to examine how self-supervised speech models encode phonetic features across Mandarin sub-dialects, finding that salient features like labiality remain stable while finer spectral distinctions show dialect-dependent variation.