Dialectal Speech Recognition Research Articles

Augmented dialectal speech recognition for AI-based neuropsychological scale assessment in Alzheimer’s disease

Alzheimer’s disease (AD) is a prevalent and widespread neurodegenerative disorder among the older adult population worldwide. Among the numerous cognitive screening methods, neuropsychological scale assessments (NSA) are the widely utilized screening tools in clinical practice. The NSA places significant emphasis on speech-related questions, and thus the role of Automatic Speech Recognition (ASR) technology in AI-based NSA evaluations becomes particularly critical. However, the majority of ASR research pays limited attention to the study of speech recognition for various dialects. One of the primary reasons and main challenges for the scarcity of research in dialectal speech recognition is the limited availability of annotated dialectal data. Furthermore, the older adults’ unclear pronunciation leads to erroneous recognition of similar phonetic words by ASR. To overcome the challenges of limited annotated dialect data in various regions and the issues related to confusable pronunciation of older adults, we propose a dialectal collaborative encoder mechanism and a machine reading comprehension augmented model (MRCAM) that automatically corrects the texts in the NSA. The dialectal collaborative encoder mechanism utilizes layer frozenness to transfer recognition ability to the dialectal model. Meanwhile, the MRCAM model fills the gap by combining speech recognition algorithms with natural language processing (NLP) technology to recognize the dialects spoken by older adults. The experimental evaluation results indicate that the proposed augmented model achieves over 90% consistency with the physician’s judgment, providing the premise of the proposed methods for the task of automated screening for AD based on ASR.

Implementation of Data Mining for Speech Recognition Classification of Sundanese Dialect Using KNN Method with MFCC Feature Extraction

The importance of preservation and development of speech recognition technology for regional languages such as Sundanese, which have unique phonetic characteristics. Regional language speech recognition can assist in the development of local, educational, and cultural preservation applications to implement and evaluate the effectiveness of the combination of MFCC and KNN methods in classifying Sundanese dialect speech recognition. Methods used include trait extraction with MFCC, which converts voice data into numerical representations based on frequency characteristics, and classification with KNN, which groups data based on similarity to train data. The Dataset used consisted of speech recordings of Western and Southern Sundanese dialects. The results showed that the k-Nearest Neighbors (KNN) method can classify Sundanese dialect speech recognition with an accuracy of 80.00%, showing good ability in distinguishing "Western" and "southern" dialects. Mel-Frequency Cepstral Coefficients (MFCC) proved to be very effective in extracting sound features, helping KNN achieve low error rates. The combination of MFCC and KNN proved effective for speech recognition classification of Sundanese dialects, providing satisfactory results with high accuracy.

Low Resource Malay Dialect Automatic Speech Recognition Modeling Using Transfer Learning from a Standard Malay Model

Approaches to automatic speech recognition have transited from Hidden Markov Model (HMM)-based ASR to deep neural networks. The advantages of deep neural network approaches are that they can be developed quickly and perform better given large language resources. Nevertheless, dialect speech recognition is still challenging due to the limited resources. Transfer learning approaches have been proposed to improve speech recognition for low resources. In the first approach, the model is pre-trained on a large and diverse labeled dataset to learn the acoustic and language patterns from the speech signal. Then, the model parameters are updated with a new dataset, and the pre-trained model is fine-tuned on a low-resource language dataset. The fine-tuning process is usually completed by freezing the pre-trained layers and training the remaining layers of the model on the low-resource language corpus. Another approach is to use a pre-trained model to capture the compact and meaningful features as input to the encoder. Pre-training in this approach usually involves using unsupervised learning methods to train models on a corpus of large amounts of unmarked data. It enables the model to learn the general patterns and relationships between the input speech signals. This paper proposes a training recipe using transfer learning and Standard Malay models to improve automatic speech recognition for Kelantan and Sarawak Malay dialects.

An experiment of Moroccan dialect speech recognition in noisy environments using PocketSphinx

An experiment of Moroccan dialect speech recognition in noisy environments using PocketSphinx

A comparative study of machine learning-based Chinese dialect speech recognition

As the official language of China, Mandarin is used on all formal occasions. However, due to China's rich history and vast population, dialects have become the primary language spoken by many people. While not taught in school, dialects serve as unofficial languages in China and are passed down through word of mouth. In recent years, the use of dialects has significantly declined as people have adapted to using official Mandarin in all settings. However, among the elderly, dialects remain the primary language of communication. The great need to use dialects as the primary mode of communication has laid the foundation for the importance and high demand for dialect speech recognition. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, research on this topic is further analysed and compared. The results suggest that there has been a certain degree of development and progress in dialect speech recognition technology. However, further research is needed to overcome the limitations of low-resource language speech recognition.

Chinese dialect speech recognition: a comprehensive survey

As a multi-ethnic country with a large population, China is endowed with diverse dialects, which brings considerable challenges to speech recognition work. In fact, due to geographical location, population migration, and other factors, the research progress and practical application of Chinese dialect speech recognition are currently at different stages. Therefore, exploring the significant regional heterogeneities in specific recognition approaches and effects, dialect corpus, and other resources is of vital importance for Chinese speech recognition work. Based on this, we first start with the regional classification of dialects and analyze the pivotal acoustic characteristics of dialects, including specific vowels and tones patterns. Secondly, we comprehensively summarize the existing dialect phonetic corpus in China, which is of some assistance in exploring the general construction methods of dialect phonetic corpus. Moreover, we expound on the general process of dialect recognition. Several critical dialect recognition approaches are summarized and introduced in detail, especially the hybrid method of Artificial Neural Network (ANN) combined with the Hidden Markov Model(HMM), as well as the End-to-End (E2E). Thirdly, through the in-depth comparison of their principles, merits, disadvantages, and recognition performance for different dialects, the development trends and challenges in dialect recognition in the future are pointed out. Finally, some application examples of dialect speech recognition are collected and discussed.

Enhanced Dialectal Speech Recognition in Punjabi Using Pitch-Based Acoustic Modeling

Enhanced Dialectal Speech Recognition in Punjabi Using Pitch-Based Acoustic Modeling

Research on dialect speech recognition based on DenseNet-CTC

At present, most of the speech recognition research is based on a wide range of regions, and there are few studies on speech recognition of urban dialects. The mainstream speech recognition methods are mostly based on ResNet network, using ResNet network as acoustic model and N-gram as language model. In this study, DenseNet is used as the basic network, and the data set of Zigong dialect subdivided by Sichuan dialect is taken as the research object of speech recognition. DenseNet-BiGRU + CTC is constructed as the acoustic model of speech recognition, and RNN is used as the speech recognition model of language model. Experiments show that the speech recognition model using DenseNet network as the basic network has higher accuracy than the model based on ResNet. Compared with the GRU-CTC network word error rate (WER) decreased by 3 %, compared with the DPCNN-Attention-CTC speech recognition method error rate decreased by 5 %.

Sichuan dialect speech recognition with deep LSTM network

In speech recognition research, because of the variety of languages, corresponding speech recognition systems need to be constructed for different languages. Especially in a dialect speech recognition system, there are many special words and oral language features. In addition, dialect speech data is very scarce. Therefore, constructing a dialect speech recognition system is difficult. This paper constructs a speech recognition system for Sichuan dialect by combining a hidden Markov model (HMM) and a deep long short-term memory (LSTM) network. Using the HMM-LSTM architecture, we created a Sichuan dialect dataset and implemented a speech recognition system for this dataset. Compared with the deep neural network (DNN), the LSTM network can overcome the problem that the DNN only captures the context of a fixed number of information items. Moreover, to identify polyphone and special pronunciation vocabularies in Sichuan dialect accurately, we collect all the characters in the dataset and their common phoneme sequences to form a lexicon. Finally, this system yields a 11.34% character error rate on the Sichuan dialect evaluation dataset. As far as we know, it is the best performance for this corpus at present.

Representation for dialect recognition using topographic independent component analysis

In dialect speech recognition, the feature of tone in one dialect is subject to changes in pitch frequency as well as the length of tone. It is beneficial for the recognition if a representation can be derived to account for the frequency and length changes of tone in an effective and meaningful way. In this paper, we propose a method for learning such a representation from a set of unlabeled speech sentences containing the features of the dialect changed from various pitch frequencies and time length. Topographic independent component analysis (TICA) is applied for the unsupervised learning to produce an emergent result that is a topographic matrix made up of basis components. The dialect speech is topographic in the following sense: the basis components as the units of the speech are ordered in the feature matrix such that components of one dialect are grouped in one axis and changes in time windows are accounted for in the other axis. This provides a meaningful set of basis vectors that may be used to construct dialect subspaces for dialect speech recognition.