Chinese Speech Research Articles

Speech competence and speech performance

AbstractThis study examined Chinese-as-a-second-language (L2 Chinese) learners’ speech production ability from a dual perspective: speech competence and speech performance. A total of 118 valid L2 Chinese learners finished two developed tests in this study, namely, the Chinese speech competence test and the Chinese speech performance test. The results suggested that L2 Chinese learners’ speech competence and speech performance, as a twofold rendering of their L2 speech production ability, not only showed a significant positive correlation with a large effect size (Pearson’sr = .598) but also significantly predicted each other with a large effect size (Cohenf2 = .555). However, such large effect sizes of the correlation and the prediction between speech competence and speech performance were not supported among the upper-intermediate L2 Chinese learners. This suggested that the development between speech competence and speech performance may be more unbalanced among the upper-intermediate L2 Chinese learners compared with their advanced counterparts. The study adds evidence to the call for a multidimensional evaluation of L2 speech production ability. It is hoped that the dual approach (i.e., speech competence and speech performance) proposed in the present study may contribute to a more comprehensive evaluation of learners’ L2 Chinese speech production ability. Consequently, classroom-based teaching can be tailored to facilitate a more balanced development of L2 Chinese learners’ speech competence and speech performance.

“Were Buddhist Scriptures in China Translated for Chinese?”: A New Investigation into the Development of Early Buddhist Chinese from the Perspective of the Buddhist Speech Community

Modern scholarship focuses on the lexical or syntactical features of Buddhist Chinese used in Chinese translations of Buddhist scriptures; however, the origins of the language have attracted relatively little attention. Our article explores the issue from the perspective of the speech community, and we argue that the community’s ethnicity played an important role in the pre-fourth-century development of Buddhist Chinese. Buddhist scriptures were mainly introduced to inland China via the Western Regions and the Han people were not officially allowed to be monks. In addition to the translated scripture’s readership, considerable numbers of scripture transmitters and translators were not Han Chinese, and Han Chinese translation assistants were mainly grassroots literati. We combined an analysis of language learning with an examination of the universal features of translated languages and views on translation, and we argue that the early Buddhist community generally could not write and did not need to read refined literary Chinese. The lifting of a ban on Han peoples converting to Buddhism from the fourth century onwards accelerated the development of Han Buddhist communities, and dramatically promoted the localization of Buddhism and scriptures, which marked a new era of translation and translated language. Our investigation into the framework of the Buddhist Chinese speech community provides new perspectives compared with philological studies on the Buddhist language and explains the early historical development of Buddhist Chinese.

Analysis of Rehabilitation Occupational Therapy Techniques Based on Instrumental Music Chinese Tonal Language Spectrogram Analysis.

This paper provides an in-depth analysis of timbre-speech spectrograms in instrumental music, designs a model analysis of rehabilitation occupational therapy techniques based on the analysis of timbre-speech spectrograms in instrumental music, and tests the models for comparison. Starting from the mechanism of human articulation, this paper models the process of human expression as a time-varying linear system consisting of excitation, vocal tract, and radiation models. The system's overall architecture is designed according to the characteristics of Chinese speech and everyday speech rehabilitation theory (HSL theory). The dual judgment of temporal threshold and short-time average energy realized the phonetic length training. Tone and clear tone training were achieved by linear predictive coding technique (LPC) and autocorrelation function. Using the DTW technique, isolated word speech recognition was achieved by extracting Mel-scale Frequency Cepstral Coefficients (MFCC) parameters of speech signals. The system designs corresponding training scenes for each training module according to the extracted speech parameters, combines the multimedia speech spectrogram motion situation with the speech parameters, and finally presents the training content as a speech spectrogram, and evaluates the training results through human-machine interaction to stimulate the interest of rehabilitation therapy and realize the speech rehabilitation training of patients. After analyzing the pre- and post-test data, it was found that the p-values of all three groups were <0.05, which was judged to be significantly different. Also, all subjects changed their behavioral data during the treatment. Therefore, it was concluded that the music therapy technique could improve the patients' active gaze communication ability, verbal command ability, and active question-answering ability after summarizing the data, i.e., the hypothesis of this experiment is valid. Therefore, it is believed that the technique of timbre-speech spectrogram analysis in instrumental music can achieve the effect of rehabilitation therapy to a certain extent.

An improved CycleGAN-based emotional voice conversion model by augmenting temporal dependency with a transformer

Emotional voice conversion (EVC) is a task that converts an utterance’s emotional features into a target one while retaining semantic information and speaker identity. Recently, some researchers leverage deep learning methods to improve the performance of EVC, such as deep neural network (DNN), sequence-to-sequence model (seq2seq), long-short-term memory network (LSTM), and convolutional neural network (CNN), as well as their combinations with an attention mechanism. However, their methods always suffer from some instability problems (e.g., mispronunciations and skipped phonemes) because these models fail to capture temporal intra-relationships among a wide range of frames, resulting in unnatural speech and discontinuous emotional expression. To enhance the ability to capture intra-relations among frames by augmenting the temporal dependency of models, we explored the power of a transformer in this study. Specifically, we proposed a CycleGAN-based model with the transformer and investigated its ability in the EVC task. In the training procedure, we adopted curriculum learning to gradually increase the frame length to ensure that the model can monitor from short segments throughout the entire speech. The proposed method was evaluated on a Japanese emotional speech dataset and Emotional Speech Dataset (ESD, contains English and Chinese speech). Then, it was compared to widely used EVC baselines (ACVAE, CycleGAN) involving objective and subjective evaluations. The results indicate that our proposed model can convert emotion with higher emotional similarity, quality, and naturalness. • A CycleTransGAN is proposed to improve its performance on the emotional voice conversion (EVC) task. • Curriculum learning was adopted to gradually increase the input length during training. • A fine-grained level discriminator was designed to enhance the model’s ability to convert emotional voices. • The proposed method was evaluated on a Japanese emotional speech dataset and Emotional Speech Dataset (ESD, containing English and Chinese speech). • The transformer enhanced the model’s temporal dependency with a wider range, which improved the quality of converted speech.

Analysis of Differences between Russian and Chinese Speech Etiquette in a Business Banquet

The object of the study is the Russian and Chinese speech etiquette at the table. The author examines in detail such aspects of the topic as differences in seating arrangements, use of dinner set and meal system between China and Russia at business banquets, and also lists the relevant rules of etiquette and at the same time indicates the specific reasons for the differences. Special attention is paid to the analysis of the reasons for these differences by comparing the seating arrangements, use of dinner set and meal system at business banquets between Russia and China, and practical recommendations are given for future business banquets between Russia and China. The special conclusions of the study are religious ideology, geography, history and culture have a very important influence on table manners in Russia and China. The author's special contribution to the research of the topic is the analysis and comparison of speech etiquette at the table in business communication between Russians and Chinese, which helps the staff of both countries to better understand each other in economic and trade cooperation. The novelty of this article lies in pointing out not only the differences between Russian and Chinese business banquets, but also the factors influencing these differences.

Acquisition of English Corpus Machine Translation Based on Speech Recognition Technology

In the present information age, with the rapid development of computer software and hardware technology and the mature manufacturing system of English-speaking enterprises, it is no longer impossible to use statistics for machine translation. The level and quality of machine translation are expected to meet human expectations. This explains the meaning and realization value of the acquisition of English corpus machine translation, introduces the basic principles of speech recognition technology, and combines the characteristics of the English language on the basis of the original Chinese speech recognition system, adopts the technical means of speech recognition, and leads to in-depth research. In the new era of machine translation acquisition of English corpus, we use the combination of LabVIEW and MATLAB to complete the collection, editing, feature extraction, and speech recognition of speech signals and use VQ pattern matching technology to realize the English recognition of a large number of short vocabulary and individuals. In the application part, we applied the classic LabVIEW technology to the speech recognition technology, which actually realized the idea of “software instead of hardware” and achieved better translation results. Experiments show that the accuracy rate of English machine translation can be as high as 94% when using speech recognition technology. According to the results, it takes about 0.2 seconds to complete machine translation for a 30-second speech, which is basically okay to achieve the effect of real-time translation.

How do L1 Chinese raters process the L2 Chinese speech signal at the sentence level with respect to accentedness, comprehensibility and intelligibility?

Abstract Set within the context of teaching and learning Chinese at two secondary schools in the North of England and adopting a case study research design, the aim of this study was to develop research-informed insights into the nature of the pronunciation challenges facing beginner learners of Chinese. Data collection activities included recording the spoken Chinese of 20 L2 learners during a read-aloud task and a question-answer activity. Forty L1 raters were subsequently interviewed as they rated and transcribed the learners’ randomized speech samples. Distinguishing between the key constructs of accentedness, comprehensibility and intelligibility, it was found that heavily accented tones did not necessarily lead to lower levels of comprehensibility and intelligibility. Furthermore, many intelligibility breakdowns – i.e. when raters failed to correctly transcribe the learners’ intended utterances – could be traced to problems with individual words which usually implicated segmental sounds as well as tone. Findings are interpreted in terms of indicating a need for more nuanced classroom priorities aimed at the promotion of intelligible speech as opposed to an unrealistic focus on developing a native-like accent.

A field method of studying the tropes in compliments to female representatives in the speech of Chinese youth

This paper is devoted to the lexical-semantic characteristics of lexical units of feminine compliments with the use of tropes in modern Chinese speech of young people youth. “Trope” is understood as a word or a phrase that is used in a way that is different from its usual meaning. This paper uses the semantic field method, divided feminine compliments in Chinese youth speech into 6 lexical-semantic groups. Particular attention is paid to the original objects of tropes in LSG in order to analyze the model of tropes (in particular, metaphor and metonymy). In addition, the paper compared similar lexical units with the use of tropes in Chinese and Russian youth speech. The novelty of the research lies in the fact that this paper built up a semantic field of positive characteristics of the female gender in Chinese youth speech, made an attempt to identify lexical-semantic characteristics of tropes in youth speech. As a result of the study, the following conclusions are made: 1) Tropes are important methods of developing the meaning of words / phrases, which are observed with high frequency in youngs speech. 2) The formation of tropes is closely connected with segments of reality around youth, which reflect the peculiar worldview of youth, subcultures and pop-cultures they are interested in, as well as the development of society as a whole.

The Role of Phonological Awareness, Pinyin Letter Knowledge, and Visual Perception Skills in Kindergarteners' Chinese Character Reading.

Word identification models assume that words are identified by at least two sources of information and analysis; one is phonological, and the other is visual. The present study investigated the influence of phonological awareness, Pinyin letter knowledge, and visual perception skills on Chinese character recognition after controlling for vocabulary, rapid naming, and verbal short-term memory in 80 Mandarin-speaking kindergarten children. Children were tested on phonological awareness (syllable awareness, onset-end rhyme awareness, and tone awareness), Pinyin letter naming, and visual perception (visual discrimination and visual-spatial relationships). The results showed that variance in Chinese character recognition could be explained by syllable awareness and tone awareness, but not by visual perception skills or Pinyin letter knowledge. Analyses further indicated that Pinyin letter knowledge moderated the relationship between tone awareness and Chinese character recognition. A focus on tone awareness and syllable awareness in the kindergarten may help Chinese children to accomplish the transition from phonological awareness to early literacy, while Pinyin letter knowledge can help children to make the connection between Chinese speech and writing.

Audiogram of Chinese Phonemes: Construction and Evaluation

Introduction: In aural rehabilitation, speech bananas are often used as a counseling tool to visually indicate one’s auditory access to speech sounds. We constructed a Chinese-based speech banana to provide Chinese-speaking users with a more appropriate distribution of Chinese speech sounds on an audiogram. Method: The location of each phoneme was defined by its frequency and intensity. To evaluate the clinical validity of the proposed speech banana, 15 Chinese-speaking hearing aid users were recruited; the predictability of the present speech banana was examined in terms of sensitivity and specificity based on their aided sound-field narrow-band noise thresholds and speech recognition thresholds. Results: The data revealed high specificity rates of 94.2% below 8,000 Hz and high sensitivity of 96.8% above 8,000 Hz. Specificity measures the percentage of perceptible sounds correctly identified as such by the Chinese speech banana (CSB); sensitivity measures the percentage of imperceptible sounds that are correctly identified as such by the CSB. Discussion/Conclusion: The CSB represents a potentially valid counseling tool to identify phonemes that have poor perceptual quality and indicate auditory access gaps.

Deep-Learning-Based Automated Classification of Chinese Speech Sound Disorders.

This article describes a system for analyzing acoustic data to assist in the diagnosis and classification of children’s speech sound disorders (SSDs) using a computer. The analysis concentrated on identifying and categorizing four distinct types of Chinese SSDs. The study collected and generated a speech corpus containing 2540 stopping, backing, final consonant deletion process (FCDP), and affrication samples from 90 children aged 3–6 years with normal or pathological articulatory features. Each recording was accompanied by a detailed diagnostic annotation by two speech–language pathologists (SLPs). Classification of the speech samples was accomplished using three well-established neural network models for image classification. The feature maps were created using three sets of MFCC (Mel-frequency cepstral coefficients) parameters extracted from speech sounds and aggregated into a three-dimensional data structure as model input. We employed six techniques for data augmentation to augment the available dataset while avoiding overfitting. The experiments examine the usability of four different categories of Chinese phrases and characters. Experiments with different data subsets demonstrate the system’s ability to accurately detect the analyzed pronunciation disorders. The best multi-class classification using a single Chinese phrase achieves an accuracy of 74.4 percent.

Estimation of the Underlying F0 Range of a Speaker from the Spectral Features of a Brief Speech Input

From a very brief speech, human listeners can estimate the pitch range of the speaker and normalize pitch perception. Spectral features which inherently involve both articulatory and phonatory characteristics were speculated to play roles in this process, but few were reported to directly correlate with speaker’s F0 range. To mimic this human auditory capability and validate the speculation, in a preliminary study we proposed an LSTM-based method to estimate speaker’s F0 range from a 300 ms-long speech input, which turned out to outperform the conventional method. By two more experiments, this study further improved the method and verified its validity in estimating the speaker-specific underlying F0 range. After incorporating a novel measurement of F0 range and a multi-task training approach, Experiment 1 showed that the refined model gave more accurate estimates than the initial model. Based on a Japanese-Chinese bilingual parallel speech corpus, Experiment 2 found that the F0 ranges estimated with the model from the Chinese speech and the model from the Japanese speech produced by the same set of speakers had no significant difference, whereas the conventional method showed significant difference. The results indicate that the proposed spectrum-based method captures the speaker-specific underlying F0 range which is independent of the linguistic content.

Research on Chinese Speech Emotion Recognition Based on Deep Neural Network and Acoustic Features.

In recent years, the use of Artificial Intelligence for emotion recognition has attracted much attention. The industrial applicability of emotion recognition is quite comprehensive and has good development potential. This research uses voice emotion recognition technology to apply it to Chinese speech emotion recognition. The main purpose of this research is to transform gradually popularized smart home voice assistants or AI system service robots from a touch-sensitive interface to a voice operation. This research proposed a specifically designed Deep Neural Network (DNN) model to develop a Chinese speech emotion recognition system. In this research, 29 acoustic characteristics in acoustic theory are used as the training attributes of the proposed model. This research also proposes a variety of audio adjustment methods to amplify datasets and enhance training accuracy, including waveform adjustment, pitch adjustment, and pre-emphasize. This study achieved an average emotion recognition accuracy of 88.9% in the CASIA Chinese sentiment corpus. The results show that the deep learning model and audio adjustment method proposed in this study can effectively identify the emotions of Chinese short sentences and can be applied to Chinese voice assistants or integrated with other dialogue applications.

What Are the Characteristics of User Texts and Behaviors in Chinese Depression Posts?

Social media platforms provide unique insights into mental health issues, but a large number of related studies have focused on English text information. The purpose of this paper is to identify the posting content and posting behaviors of users with depression on Chinese social media. These clues may suggest signs of depression. We created two data sets consisting of 130 users with diagnosed depression and 320 other users that were randomly selected. By comparing and analyzing the two data sets, we can observe more closely how users reveal their signs of depression on Chinese social platforms. The results show that the distribution of some Chinese speech users with depression is significantly different from that of other users. Emotional sadness, fear and disgust are more common in the depression class. For personal pronouns, negative words and interrogative words, there are also great differences between the two data sets. Using topic modeling, we found that patients mainly discussed seven topics: negative emotion fluctuation, disease treatment and somatic responses, sleep disorders, sense of worthlessness, suicidal extreme behavior, seeking emotional support and interpersonal communication. The depression class post negative polarity posts much more frequently than other users. The frequency and characteristics of posts also reveal certain characteristics, such as sleep problems and reduced self-disclosure. In this study, we used Chinese microblog data to conduct a detailed analysis of the users showing depression signs, which helps to identify more patients with depression. At the same time, the study can provide a further theoretical basis for cross-cultural research of different language groups in the field of psychology.

중국어 연설문의 수사학적 특징과 번역양상 연구 — 수사법 ‘배비’를 중심으로 —

This study analyzed the rhetorical features of a speech in Chinese and classified its Korean translation methods of political discourse. The rhetorical devices from President Xi Jinping's speech at Seoul National University in 2014 were selected. As a linguistic tool that employs a particular type of words, phrases, sentences to persuade the audience, 'parallelism' was found the most common rhetorical device. Parallelism is the repetition of two or more elements of sentences with the same grammatical structure. In this study, parallelism of Xi's Chinese speech was categorized into three types: parallelism of four-character structure; parallelism of quotes such as poems and proverbs; parallelism sentences to emphasize the topic of paragraphs. In addition, this paper found four common methods for translating parallelism: first, adding Chinese characters to Korean translations; second, translating word-for-word; third, abridging repeated words and lines; fourth, expanding the implicitly meaning throughout interpreting messages of parallelism.

A contrastive study on the production of double vowels in Mandarin

Abstract The concept of ‘global village’ has linked all countries in the world as a whole. The exchanges and cooperation between different countries in politics, economy, culture, and education are becoming more and more frequent. To master a language, the study of its pronunciation is crucial. Based on the above considerations, this paper uses the Chinese pronunciation corpus of 30 learners and 10 Chinese native speakers as basic data to discuss the pronunciation patterns of learners’ mandarin diphthongs and their similarities to standard pronunciations. In this paper, by using the theory and methods of experimental phonetics, comparative analysis and error analysis, we exam and analyse the acoustic features of different levels of learners in the learning process, and the pronunciation and bias of learners’ mandarin diphthongs are obtained. From the experimental results, it can be seen that all three groups of learners have some difficulties in pronunciation of mandarin diphthongs. In particular, the learners have the greatest differences to standard pronunciations when pronouncing the diphthongs [ua] and [uo]. And some important rules and conclusions are summarised through experiments. This provides an important reference for learners to solve the problems of diphthongs pronunciation in Chinese speech synthesis and recognition.

Some methodological techniques for teaching oral speech in Chinese

This article is devoted to identifying difficulties with mastering oral speech among university students at the initial stage of learning Chinese. The author of the article sets himself the task not only to identify the purpose of teaching oral speech, but also to offer techniques to help overcome the difficulties associated with certain motivational problems, such as: the manifestation of shyness, fear of making a mistake, insufficient knowledge of lexical units, misunderstanding of the speech task. The author shares his opinion on the effectiveness of generally accepted methods of teaching oral speech of the Chinese language and offers practical tools aimed at expanding the lexical stock, developing communication skills, working out the studied material and using it in conversational practice. The hypothesis of this article is expressed in the assumption that the difficulties of learning oral speech are overcome by increasing the vocabulary, developing the skills of simple monologue and dialogic speech, as well as creating a comfortable educational environment. Based on the experience of conducting an oral Chinese course, frequent problems of university students are: inability to use additional sources, fear of unfamiliar vocabulary. Thus, it is advisable to use exercises aimed at solving these problems, namely: independent work of students, compiling their own lexical lists, working out topics of concern to them, encouraging students to communicate outside the classroom and using mobile offers or websites to train lexical units, through communication with native speakers.

The Influence of Cognitive, Affective, and Sociocultural Individual Differences on L2 Chinese Speech Performance: A Multiple Indicators Multiple Causes Approach.

Informed by Segalowitz's (Cognitive bases of second language fluency, Routledge, 2010) L2 speech production model and MacIntyre et al.'s (Mod Lang J 82(4):545-562, 1998. https://doi.org/10.1111/j.1540-4781.1998.tb05543.x ) L2 willingness to communicate model, this study sought to understand the influence of cognitive, affective and sociocultural individual differences on advanced learners' L2 Chinese speech performance. A total of 240 advanced L2 Chinese learners in China participated in the study. The participants' perceptions of the impact of cognitive, affective, and sociocultural factors on their L2 Chinese speech performance were measured by an adapted questionnaire. A speaking test, following the Hanyu Shuiping Kouyu Kaoshi (HSKK, an international standardized L2 Chinese speaking proficiency test for non-native speakers), was employed to evaluate the participants' L2 Chinese speech performance. The results of multiple indicators multiple causes (MIMIC) analysis show that (1) cognitive factors such as cognitive fluency, expression practice strategy, and assistance strategy, (2) affective factors such as speaking self-efficacy, speaking anxiety, and speaking motivation, and (3) sociocultural factors such as attitudes toward target language class and attitudes toward target language culture jointly influence advanced L2 Chinese learners' speech performance. Results and implications of the present study are discussed for enhancinglearners' L2 Chinese speech performance.

Multiple Scene Sentiment Analysis Based on Chinese Speech and Text

&lt;p&gt;This paper proposes a multi-scene sentiment analysis model for Chinese speech and text based on CNN-BiGRU-CTC + ERNIE-BiLSTM. The model is applied to the intelligent customer service scenario. While conducting voice interaction, intelligent customer service can obtain the user’s current emotion, to give a more humane answer and improve the user experience. All the training data sets in this paper adopted public data sets such as Aishell-1 and NLPCC 2014, etc.We have been able to achieve a testing accuracy of about 94.5%. The accuracy is improved by 5.24% compared to the latest speech sentiment analysis model that uses audio as a feature. The advantage of this paper is that it adopts the ERNIE language pre-training model to conduct sentiment analysis on speech signals, which still has a good classification accuracy in the case of individual wrong words in speech recognition. &lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

Active auditory learning in infants born preterm

In this volume of The Journal, Richard et al report a study demonstrating auditory learning of sounds in a foreign language by infants born preterm during their hospitalization in the neonatal intensive care unit (NICU). By sucking on a specialized pacifier, infants of English-speaking parents were able to actively elicit lullabies and speech in French or Mandarin Chinese. After 20 of these sessions, infants hearing either language showed differential electrophysiologic responses to speech sounds in these languages with no effects on their responses to English language speech sounds.