In this paper, based on the multilingual morphological analyzer, we researched the similar low-resource languages, Uyghur and Kazakh, short text classification. Generally, the online linguistic resources of these languages are noisy. So a preprocessing is necessary and can significantly improve the accuracy. Uyghur and Kazakh are the languages with derivational morphology, in which words are coined by stems concatenated with suffixes. Usually, terms are used as the representation of text content while excluding functional parts as stop words in these languages. By extracting stems we can collect necessary terms and exclude stop words. Morpheme segmentation tool can split text into morphemes with 95% high reliability. After preparing both word- and morpheme-based training text corpora, we apply convolutional neural network (CNN) as a feature selection and text classification algorithm to perform text classification tasks. Experimental results show that the morpheme-based approach outperformed the word-based approach. Word embedding technique is frequently used in text representation both in the framework of neural networks and as a value expression, and can map language units into a sequential vector space based on context, and it is a natural way to extract and predict out-of-vocabulary (OOV) from context information. Multilingual morphological analysis has provided a convenient way for processing tasks of low resource languages like Uyghur and Kazakh.

Language identification is the front end of multilingual speech-processing tasks. The study aims to enhance the accuracy of language identification in complex acoustic environments by proposing a multi-scale feature extraction method. This method replaces the baseline feature extraction network with a multi-scale feature extraction network (SE-Res2Net-CBAM-BILSTM) to extract multi-scale features. A multilingual cocktail party dataset was simulated, and comparative experiments were conducted with various models. The experimental results show that the proposed model achieved language identification accuracies of 97.6% for an Oriental language dataset and 75% for a multilingual cocktail party dataset Furthermore, comparative experiments show that our model outperformed three other models in the accuracy, recall, and F1 values. Finally, a comparison of different loss functions shows that the model performance was better when using focal loss.

Automatic Speaker Verification (ASV) has its benefits compared to other biometric verification methods, such as face recognition. It is convenient, low cost, and more privacy protected, so it can start being used for various practical applications. However, voice verification systems are vulnerable to unknown spoofing attacks, and need to be upgraded with the pace of forgery techniques. This paper investigates a low-cost attacking scenario in which a playback device is used to impersonate the real speaker. The replay attack only needs a recording and playback device to complete the process, so it can be one of the most widespread spoofing methods. In this paper, we explore and investigate some spectral clues in the high sampling rate recording signals, and utilize this property to effectively detect the replay attack. First, a small scale genuine-replay dataset of high sample rates are constructed using some low-cost mobile terminals; then, the signal features are investigated by comparing their spectra; machine learning models are also applied for evaluation. The experimental results verify that the high frequency spectral clue in the replay signal provides a convenient and reliable way to detect the replay attack.

In multi-lingual, multi-speaker environments (e.g., international conference scenarios), speech, language, and background sounds can overlap. In real-world scenarios, source separation techniques are needed to separate target sounds. Downstream tasks, such as ASR, speaker recognition, speech recognition, VAD, etc., can be combined with speech separation tasks to gain a better understanding. Since most of the evaluation methods for monophonic separation are either single or subjective, this paper used the downstream recognition task as an overall evaluation criterion. Thus, the performance could be directly evaluated by the metrics of the downstream task. In this paper, we investigated a two-stage training scheme that combined speech separation and language identification tasks. To analyze and optimize the separation performance of single-channel overlapping speech, the separated speech was fed to a language identification engine to evaluate its accuracy. The speech separation model was a single-channel speech separation network trained with WSJ0-2mix. For the language identification system, we used an Oriental Language Dataset and a dataset synthesized by directly mixing different proportions of speech groups. The combined effect of these two models was evaluated for various overlapping speech scenarios. When the language identification network model was based on single-person single-speech frequency spectrum features, Chinese, Japanese, Korean, Indonesian, and Vietnamese had significantly improved recognition results over the mixed audio spectrum.

Morphologically derivative languages form words by fusing stems and suffixes, stems are important to be extracted in order to make cross lingual alignment and knowledge transfer. As there are phonetic harmony and disharmony when linguistic particles are combined, both phonetic and morphological changes need to be analyzed. This paper proposes a multilingual stemming method that learns morpho-phonetic changes automatically based on character based embedding and sequential modeling. Firstly, the character feature embedding at the sentence level is used as input, and the BiLSTM model is used to obtain the forward and reverse context sequence, and the attention mechanism is added to this model for weight learning, and the global feature information is extracted to capture the stem and affix boundaries; finally CRF model is used to learn more information from sequence features to describe context information more effectively. In order to verify the effectiveness of the above model, the model in this paper is compared with the traditional model on two different data sets of three derivative languages: Uyghur, Kazakh and Kirghiz. The experimental results show that the model in this paper has the best stemming effect on multilingual sentence-level datasets, which leads to more effective stemming. In addition, the proposed model outperforms other traditional models, and fully consider the data characteristics, and has certain advantages with less human intervention.

Bilingual lexicon extraction is useful, especially for low-resource languages that can leverage from high-resource languages. The Uyghur language is a derivative language, and its language resources are scarce and noisy. Moreover, it is difficult to find a bilingual resource to utilize the linguistic knowledge of other large resource languages, such as Chinese or English. There is little related research on unsupervised extraction for the Chinese-Uyghur languages, and the existing methods mainly focus on term extraction methods based on translated parallel corpora. Accordingly, unsupervised knowledge extraction methods are effective, especially for the low-resource languages. This paper proposes a method to extract a Chinese-Uyghur bilingual dictionary by combining the inter-word relationship matrix mapped by the neural network cross-language word embedding vector. A seed dictionary is used as a weak supervision signal. A small Chinese-Uyghur parallel data resource is used to map the multilingual word vectors into a unified vector space. As the word-particles of these two languages are not well-coordinated, stems are used as the main linguistic particles. The strong inter-word semantic relationship of word vectors is used to associate Chinese-Uyghur semantic information. Two retrieval indicators, such as nearest neighbor retrieval and cross-domain similarity local scaling, are used to calculate similarity to extract bilingual dictionaries. The experimental results show that the accuracy of the Chinese-Uyghur bilingual dictionary extraction method proposed in this paper is improved to 65.06%. This method helps to improve Chinese-Uyghur machine translation, automatic knowledge extraction, and multilingual translations.