Search Results (30)

Cantonese automatic speech recognition (ASR) faces persistent challenges due to its nine lexical tones, extensive phonological variation, and the scarcity of professionally transcribed corpora. To address these issues, we propose a lightweight and data-efficient framework that leverages weak phonetic supervision (WPS) in conjunction with two pho-neme-aware augmentation strategies. (1) Dynamic Boundary-Aligned Phoneme Dropout progressively removes entire IPA segments according to a curriculum schedule, simulating real-world phenomena such as elision, lenition, and tonal drift while ensuring training stability. (2) Phoneme-Aware SpecAugment confines all time- and frequency-masking operations within phoneme boundaries and prioritizes high-attention regions, thereby preserving intra-phonemic contours and formant integrity. Built on the Whistle encoder—which integrates a Conformer backbone, Connectionist Temporal Classification–Conditional Random Field (CTC-CRF) alignment, and a multi-lingual phonetic space—the approach requires only a grapheme-to-phoneme lexicon and Montreal Forced Aligner outputs, without any additional manual labeling. Experiments on the Cantonese subset of Common Voice demonstrate consistent gains: Dynamic Dropout alone reduces phoneme error rate (PER) from 17.8% to 16.7% with 50 h of speech and 16.4% to 15.1% with 100 h, while the combination of the two augmentations further lowers PER to 15.9%/14.4%. These results confirm that structure-aware phoneme-level perturbations provide an effective and low-cost solution for building robust Cantonese ASR systems under low-resource conditions. Full article

Background/Objectives: Children with Autism Spectrum Disorder (ASD) often display heightened sensitivity to simple auditory stimuli, but have difficulty discriminating and integrating multiple phonological features (segmental: consonants and vowels; suprasegmental: lexical tones) at the syllable level, which negatively impacts their communication. This study aims to investigate the neural basis of segmental, suprasegmental and combinatorial speech processing challenges in Mandarin-speaking children with ASD compared with typically developing (TD) peers. Methods: Thirty children with ASD and thirty TD peers will complete a multi-feature oddball paradigm to elicit auditory ERP during passive listening. Stimuli include syllables with single (e.g., vowel only), dual (e.g., vowel + tone), and triple (consonant + vowel + tone) phonological deviations. Neural responses will be analyzed using temporal principal component analysis (t-PCA) to isolate overlapping ERP components (early/late MMN), and representational similarity analysis (RSA) to assess group differences in neural representational structure across feature conditions. Expected Outcomes: We adopt a dual-framework approach to hypothesis generation. First, from a theory-driven perspective, we integrate three complementary models, Enhanced Perceptual Functioning (EPF), Weak Central Coherence (WCC), and the Neural Complexity Hypothesis (NCH), to account for auditory processing in ASD. Specifically, we hypothesize that ASD children will show enhanced or intact neural discriminatory responses to isolated segmental deviations (e.g., vowel), but attenuated or delayed responses to suprasegmental (e.g., tone) and multi-feature deviants, with the most severe disruptions occurring in complex, multi-feature conditions. Second, from an empirically grounded, data-driven perspective, we derive our central hypothesis directly from the mismatch negativity (MMN) literature, which suggests reduced MMN amplitudes (with the exception of vowel deviants) and prolonged latencies accompanied by a diminished left-hemisphere advantage across all speech feature types in ASD, with the most pronounced effects in complex, multi-feature conditions. Significance: By testing alternative hypotheses and predictions, this exploratory study will clarify the extent to which speech processing differences in ASD reflect cognitive biases (local vs. global, per EPF/WCC/NCH) versus speech-specific neurophysiological disruptions. Findings will advance our understanding of the sensory and integrative mechanisms underlying communication difficulties in ASD, particularly in tonal language contexts, and may inform the development of linguistically tailored interventions. Full article

This study provides a detailed analysis of COVID-19-related social media discourse in Italy, using 535,886 tweets from 10 major cities between 30 August 2020 and 8 June 2021. The tweets were translated from Italian to English for analysis. A multifaceted methodology was employed: Latent Dirichlet Allocation (LDA) identified 20 key themes; sentiment analysis, using TextBlob, Flair, and TweetNLP, and emotion recognition using TweetNLP, revealed the emotional tone of the discourse, with 453 tweets unanimously positive across all algorithms. TextBlob was used for lexical analysis to rank the most salient positive and negative terms. The results indicated that positive sentiments centered on hope, safety measures, and vaccination progress, while negative sentiments focused on fear, death, and quarantine frustrations. This research offers valuable insights for public health officials, enabling tailored messaging, real-time strategy monitoring, and agile policymaking during the pandemic, with implications for future health crises. Full article

The tonal system of Cantonese is very different from that of Mandarin, which creates potential challenges for Mandarin speakers when learning Cantonese. The aim of this study was to explore second language (L2) production of Cantonese tones by advanced learners whose first language (L1) is Mandarin. Forty-one informants participated in a recording experiment to provide production data of Cantonese tones. The speech data were measured acoustically using the computer software Praat (Version 6.3.10) and were evaluated perceptually by native Cantonese speakers. The relationship between the acoustic analysis and perceptual evaluation was also explored. The acoustic and perceptual evaluations confirmed that, while the tones that the Mandarin learners of Cantonese produced were non-native-like, their production of the Cantonese T1 and T2 was good in general. Furthermore, the accuracy of the perceptual evaluations could be predicted based on the acoustic features of the L2 tones. Our findings are in line with hypotheses in current speech learning models, and demonstrate that familiar phonetic categories are easier to acquire than are unfamiliar ones. To provide a more complete picture of L2 speech acquisition, future research should investigate L2 tone acquisition using both production and perception data obtained from participants with a greater variety of L1s. Full article

Background/Objectives: In a tonal language like Chinese, phonologically contrasting tones signify word meanings at the syllable level. Although the development of lexical tone perception ability has been examined in many behavioral studies, its developmental trajectory from childhood to adulthood at the neural level remains unclear. This cross-sectional study aimed to examine the issue by measuring the mismatch negativity (MMN) response to a Chinese lexical tonal contrast in three groups. Methods: The MMN response to a flat-falling tonal contrast (Tone1 versus Tone4) were recorded from children (25 participants aged 6–8), adolescents (26 participants aged 12–14), and young adults (20 participants aged 18–24). Nonsense speech stimuli were also used by superimposing Tone1 and Tone4 on an English syllable. Results: All three groups demonstrated typical early MMN responses in both the meaningful and nonsense syllable conditions. However, the MMN amplitudes varied significantly across groups, with the child group showing smaller responses compared to the adolescent and adult groups, while the latter two groups had similar MMN amplitudes. Conclusions: Neural sensitivity to tonal contrasts is not fully mature in children and reaches a more adult-like level during adolescence, with no significant difference in sensitivity to meaningful versus nonsense syllables. These results provide new insights into the neural development of lexical tone perception in a tonal language, highlighting its maturation during adolescence in this process. Full article

Most research on dialectometry so far primarily focuses on European languages. Within these studies, analyses on the phonetic level predominantly focus on segments. A lack of studies on languages outside of Europe means that the variation in many lesser-studied languages, including tonal languages, is largely unknown. Tonal languages are languages which pitch is used as an indication in the lexical realisations in (at least some) morphemes, and over half of the world’s languages include lexical tones. Despite tones being the inseparable and unneglectable part of the majority of the world’s languages, there is only a handful of quantitative dialectometric studies on the dialectal variation in tonal languages. In this paper, we explore the phonetic and phonological variations in Yue, a lesser-studied tonal language spoken by around 80 million people in Southern China. Using a newly devised tone representation (modified Onset–Contour–Offset) combined with the Levenshtein distance, we explore the patterns of dialectal variation on the tonal level, as well as to what extent tonal variation correlates with segmental variation. Our results show that tones behave rather differently from segments, and thus, we illustrate that studying lesser-studied and tonal languages can contribute immensely to the study of dialect variation in general. Full article

In their quest to find a suitable tone of voice in an informalizing society, many companies are confronted with the choice of using T or V pronouns in their B2C communications. This paper presents an experimental study addressing the question of whether the recipients of these messages actually notice the difference between being addressed with a T form, which carries social meanings of informality and proximity, or a more distant V form, and to what extent the presence of additional informal linguistic features influences the salience of a pronoun switch. We furthermore investigate to what extent the professional socialization of participants impacts on the noticing of pronoun use. In a case study for Belgian Dutch, participants (N = 279) were presented with two versions of an information letter that they were asked to read quickly. The texts were manipulated for the use of T/V pronouns, as well as, depending on the condition, a number of additional informal linguistic features (i.e., informal punctuation, intensifiers, and English lexical items). Participants were not warned in advance about the changes between the two versions of the stimulus text. In a salience test following the presentation of the two text versions, less than 10% of participants noticed a switch in T/V form regardless of the presence of additional informal features. Similarly low rates of noticing were found for the other informal features, except for English loanwords. No differences were found depending on whether participants had a language-related professional background (e.g., language teachers, journalists, editors). We argue that the lack of noticing T/V pronouns may be due to the specifics of the Belgian Dutch system of pronominal address that has an additional highly salient colloquial pronoun of address which may obscure the difference in social meaning between the standard T and V pronouns. The discussion critically evaluates the implications of the study for the use of T/V pronouns in professional communication, musing on the complex relationship between noticing and evaluating. Full article

While existing cross-language studies on the perception of non-native tones primarily focus on naïve listeners, this study addresses an obvious gap by investigating learners from diverse language backgrounds. Specifically, it investigates Mandarin tone perception in two groups of learners from Nordic languages, Swedish (a pitch-accent language), and Danish (a non-tonal language), as well as in a group of native Chinese speakers. Analysis of their performance in tone identification task revealed a slight advantage for Swedish learners, implying the influence of their pitch accent background in learning Mandarin tones. However, both Swedish and Danish learners who excelled in the tone identification task exhibited similar perception of within-category tonal variations but differed from native Chinese speakers. Additionally, the study found that the presence of length contrast, a prosodic feature in the learners’ native languages, significantly influences their perception of Mandarin tones. Full article

This explorative study examines intonation contours in neutral and non-neutral statements of Paraguayan Spanish, a variety shaped by extensive contact with Guarani, a co-official language of Paraguay. Paraguayan Spanish displays both lexical and syntactic borrowings from Guarani, along with innovative intonation patterns not found in other Spanish varieties. Previous but still limited research on yes/no and wh-questions in this variety suggests the emergence of a unique intonational system, possibly of a hybrid nature, in both Spanish monolinguals and Spanish–Guarani bilinguals. To date, no comprehensive description of intonation patterns in Paraguayan Spanish statements exists. The present study addresses this gap by analyzing data obtained through a Discourse Completion Task, covering broad-focus statements, contrastive focus, exclamatives, and statements of the obvious. Data were collected in 2014 from two monolingual speakers, eleven bilingual Spanish-dominant speakers, and eight bilingual Guarani-dominant speakers. The intonation is formalized using the Autosegmental–Metrical model of intonational phonology and the Spanish Tones and Break Indices labeling system. The findings reveal three main realizations of nuclear accents (L+H*, H+L*, and innovative >H+L*) in neutral and non-neutral declarative sentences, lengthening of syllables, diverse syntactical strategies, and lexical borrowings. The study contributes to the understanding of a lesser-studied Spanish variety and offers insights into theoretical aspects of contact linguistics. Full article

The visual cues of lexical tones are more implicit and much less investigated than consonants and vowels, and it is still unclear what facial areas contribute to facial tones identification. This study investigated Chinese and English speakers’ eye movements when they were asked to identify audiovisual Mandarin lexical tones. The Chinese and English speakers were presented with an audiovisual clip of Mandarin monosyllables (for instance, /ă/, /à/, /ĭ/, /ì/) and were asked to identify whether the syllables were a dipping tone (/ă/, / ĭ/) or a falling tone (/ à/, /ì/). These audiovisual syllables were presented in clear, noisy and silent (absence of audio signal) conditions. An eye-tracker recorded the participants’ eye movements. Results showed that the participants gazed more at the mouth than the eyes. In addition, when acoustic conditions became adverse, both the Chinese and English speakers increased their gaze duration at the mouth rather than at the eyes. The findings suggested that the mouth is the primary area that listeners utilise in their perception of audiovisual lexical tones. The similar eye movements between the Chinese and English speakers imply that the mouth acts as a perceptual cue that provides articulatory information, as opposed to social and pragmatic information. Full article

How people recognize linguistic and emotional prosody in different listening conditions is essential for understanding the complex interplay between social context, cognition, and communication. The perception of both lexical tones and emotional prosody depends on prosodic features including pitch, intensity, duration, and voice quality. However, it is unclear which aspect of prosody is perceptually more salient and resistant to noise. This study aimed to investigate the relative perceptual salience of emotional prosody and lexical tone recognition in quiet and in the presence of multi-talker babble noise. Forty young adults randomly sampled from a pool of native Mandarin Chinese with normal hearing listened to monosyllables either with or without background babble noise and completed two identification tasks, one for emotion recognition and the other for lexical tone recognition. Accuracy and speed were recorded and analyzed using generalized linear mixed-effects models. Compared with emotional prosody, lexical tones were more perceptually salient in multi-talker babble noise. Native Mandarin Chinese participants identified lexical tones more accurately and quickly than vocal emotions at the same signal-to-noise ratio. Acoustic and cognitive dissimilarities between linguistic prosody and emotional prosody may have led to the phenomenon, which calls for further explorations into the underlying psychobiological and neurophysiological mechanisms. Full article

The production of L2 lexical tone has proven difficult for learners of tonal languages, leading to the testing of different tone training techniques. To test the validity of these techniques, it is first necessary to capture the differences between L1 and L2 tone datasets. The current study explores three analyses designed to compare L1 and L2 tone: (1) using a single deviation score, (2) using deviation score calculations for specific regions of tone productions, and (3) applying a complexity-invariant distance measure to the two time series datasets. These three analyses were tested using datasets sampled from a previous study testing the effects of a visual feedback paradigm on the production of L2 Mandarin tone. Results suggest the first two analyses, although useful for providing an overall evaluation of how L2 speakers’ pretest versus posttest productions compare to L1 speakers, lose critical information about tone, namely pitch height, contour, and the timing of the production. The third analysis, applying the complexity-invariant distance measure to the datasets, can provide the pertinent information lost from the first two analyses in a more robust manner. Full article

This study describes the segmental and suprasegmental phonology of Adur Niesu, a Loloish (or Ngwi) language spoken mainly in Liangshan, Sichuan, southwest China. Phonemically, there are 41 consonants, 10 monophthongs and 1 diphthong in Adur Niesu. All Adur syllables are open. Its segmental changes mainly happen to the vowels, featuring high vowel fricativization, vowel lowering, vowel centralization, vowel assimilation and vowel fusion. It is common for Adur Niesu syllables to be reduced in continuous speech, with floating tones left. There are three main types of syllable reduction: complete reduction including the segment and tone, partial reduction with a floating tone left, and partial reduction with the initial consonant left. Adur Niesu employs tones as an important means for lexical contrast, namely, high-level tone 55, mid-level tone 33, and low-falling tone 21. There is also a sandhi tone 44. There are two types of tonal alternation: tone sandhi and tone change. Tone sandhi occurs at both word and phrasal levels, and is conditioned by the phonetic environment, while tone change occurs due to the morphosyntactic environment. Finally, some seeming tonal alternation is the result of a floating tone after syllable reduction. Full article

From the perspective of areal linguistics, this paper examines the similarities in tonal behavior between Sinitic and Kam-Tai, the two most populous language groups in Lingnan. By relying on some frameworks for investigating tone systems, i.e., tone-box theories, which largely involve the evolution of tones, the following duplicating patterns and paths of diffusion of areal features are identified. (1) The secondary tonal split conditioned by vowel length on checked syllables, as well as the secondary tonal split of the upper-register tones conditioned by the laryngeal features of initial consonants, both originated in Kam-Tai languages and have diffused into some neighboring Sinitic languages. (2) The pattern of the secondary tonal split of the lower-register tones conditioned by laryngeal features of the initial consonants originated in northern authoritative Sinitic languages and spread widely among different subgroups of Sinitic languages; its diffusion into the Kam-Tai languages is limited to the lexical category of loanwords. (3) The upper-register tones associated with sonorant initials found in Lingnan Sinitic languages are suggested to be of a Kam-Tai origin trait. Further, their underlying areal typological rules are also summarized, concentrating on different upper limits for the possible secondary tonal split in the Sinitic and Kam-Tai languages, which were determined by the historically distinct laryngeal features of the initial consonants of the two language groups. Full article

This paper presents a detailed description of the phonology of the Rongpa variety of Choyul, an understudied Tibeto-Burman language spoken in Lithang (理塘) County, Dkarmdzes (甘孜) Tibetan Autonomous Prefecture of Sichuan Province, China. Based on firsthand fieldwork data, this paper lays out Rongpa phonology with details, examining its syllable canon, initial and rhyme systems, and word prosody. Peculiar characteristics of this phonological system are as follows: First, Rongpa has a substantial phonemic inventory, which comprises 43 consonants, 13 vowels, and 2 tones. 84 consonant clusters are observed to serve as the initial of a syllable. Secondly, the phonemic contrast between plain and uvularized vowels is attested. In addition, regressive vowel harmony on uvularization, height, and lip-roundedness can be clearly observed in various constructions including prefixed verb stems. Finally, regarding word prosody, two tones in monosyllabic words, /H/ and /L/, are observed to distinguish lexical meanings, and disyllabic words exhibit four surface pitch patterns. Pitch patterns in verb morphology are also examined. The findings and analyses as presented in this paper could form a foundation for future research on Rongpa Choyul. Full article