Phonetic Approaches Research Articles

ALLOPHONIC VARIATIONS AS STYLE MARKER OF A VOICE ACTOR

This study deals with the allophones of several phonemes pronounced by a voice actor in performing a character in animation movie. It concerns with the stylistic analysis in phonetic and phonology levels that reinforce the voice actor in performance. The data are taken from the utterances spoken by Adam Sandler, the voice actor of Count Dracula in Hotel Transylvania-2. The method of data analysis is through descriptive qualitative based on stylistic and phonetic approaches. By comparing the general American accent with the voice actor’s pronunciation, it is found that the acoustic features of [5], [r], [?], [º], [n̪] and phonemes /@/ and /e/ have particular effects in reinforcing the character in the movie, mainly to bring up comical atmosphere.Keywords: stylistics, phonetics, phonemes, allophones, voice actor

A Computerized Syllable-Based Intervention for French-Speaking Children with Down Syndrome: What Effects on Reading Skills?

The aim of this research was to provide to eight children with Down Syndrome a syllable-processing software program that drew their attention to phonological and orthographic syllables. The children participated in a 10-hour training course (spread over 5 weeks) that used an experimental design with four assessment sessions, the first two of which were used to obtain a baseline in literacy skills. The effect of training was assessed just after training and two months later. A significant effect on decoding was observed at medium term after training. All children progressed in at least one domain, either in phonological skills, in decoding, or in word reading. Four children progressed in decoding and word reading. This study confirms the appropriateness of using phonetic approaches to reading instruction in order to stimulate learning to read in children with Down Syndrome. The syllable-based training facilitates the construction of associations between letters and syllables—the “syllabic bridge”—and could be a faster and easier way to learn letter-sound correspondences in French.

Performance Analysis: AI-based VIST Audio Player by Microsoft Speech API

Speech recognition has gained much attention from researchers for almost last two decades. Isolated words, connected words, and continuous speech are the main focused areas of speech recognition. Researchers have adopted many techniques to solve speech recognition challenges under the umbrella of Artificial Intelligence (AI), Pattern Recognition and Acoustic Phonetic approaches. Variation in pronunciation of words, individual accents, unwanted ambient noise, speech context, and quality of input devices are some of these challenges in speech recognition. Many Application Programming Interface (API)s are developed to overcome the issue of accuracy in a speech-to-text conversion such as Microsoft Speech API and Google Speech API. In this paper, the performance of Microsoft Speech API is analyzed against other Speech APIs mentioned in the literature on the special dataset (without background noise) prepared. A Voice Interactive Speech to Text (VIST) audio player was developed for the analysis of Microsoft Speech API. VIST audio player creates runtime subtitles of the audio files running on it; the player is responsible for speech to text conversion in real-time. Microsoft Speech API was incorporated in the application to validate and make the performance of API measurable. The experiments proved the Microsoft Speech API more accurate with respect to other APIs in the context of the prepared dataset for the VIST audio player. The accuracy rate according to the precision-recall is 96% for Microsoft Speech API, which is better than previous ones as mentioned in the literature.

Development of Artificial Intelligence and Prospects for Its Application

Aim. To analyze the concept of “artificial intelligence”, to justify the effectiveness of using artificial intelligence technologies.Tasks. To study the conceptual apparatus; to propose and justify the author’s definition of the “artificial intelligence” concept; to describe the technology of speech recognition using artificial intelligence.Methodology. The authors used such general scientific methods of cognition as comparison, deduction and induction, analysis, generalization and systematization.Results. Based on a comparative analysis of the existing conceptual apparatus, it is concluded that there is no single concept of “artificial intelligence”. Each author puts his own vision into it. In this regard, the author’s definition of the “artificial intelligence” concept is formulated. It is determined that an important area of applying artificial intelligence technologies in various fields of activity is speech recognition technology. It is shown that the first commercially successful speech recognition prototypes appeared already by the 1990s, and since the beginning of the 21st century. The great interest in “end-to-end” automatic speech recognition has become obvious. While traditional phonetic approaches have requested pronunciation, acoustic, and language model data, end-to-end models simultaneously consider all components of speech recognition, thereby facilitating the stages of self-learning and development. It is established that a significant increase in the” mental “ capabilities of computer technology and the development of new algorithms have led to new achievements in this direction. These advances are driven by the growing demand for speech recognition.Conclusions. According to the authors, artificial intelligence is a complex of computer programs that duplicate the functions of the human brain, opening up the possibility of informal learning based on big data processing, allowing to solve the problems of pattern recognition (text, image, speech) and the formation of management decisions. Currently, the active development of information and communication technologies and artificial intelligence concepts has led to a wide practical application of intelligent technologies, especially in control systems. The impact of these systems can be found in the work of mobile phones and expert systems, in forecasting and other areas. Among the obstacles to the development of this technology is the lack of accuracy in speech and voice recognition systems in the conditions of sound interference, which is always present in the external environment. However, the recent advances overcome this disadvantage.

LEXICO-SEMANTIC ASPECTS: NATIONAL APPLIED AND FINE ART TERMS

The purpose of this article is to provide an analysis of implications of using lexico-semantic approach to terminology structuring, especially for interpreting data supplied for the purpose of building specialized dictionaries. The authors pay attention to the lexical and semantic, grammatical and phonetic approaches of the applied and fine art terms, as well as the approaches of translation. It is also aimed at revealing terms from the national pragmatic meanings and in their substantial and functional interpretation, defining the pragmatic effect of speech communication in other languages. The result of this paper is the brief dictionary of Uzbek, Russian and English national terms used in applied and fine arts. The dictionary contains about 1500 terms of fine and applied art. Moreover, the creation of a dictionary can serve as a tool to bring a single meaning to terms that can carry multiple meanings in different parts of a country. Besides, it will serve as an important source for introducing art to future generation and familiarizing with masters’ achievements.

Spoken language recognition using a new conditional cascade method to combine acoustic and phonetic results

Spoken language recognition (SLR) is an identification process to detect the language of an audio file. Traditional SLR systems are mainly based on acoustic or phonetic approaches. These approaches have complementary characteristic, so fusing them may lead to improve the accuracy of final SLR system. In the phonetic-based approaches, the process of phone recognition, as its initial step, is a time consuming process, therefore it may results in a high computational cost for overall SLR system. In this paper, a new structure, named conditional cascade, is proposed to speed up the combined system of the phonetic and acoustic approaches. In the proposed structure, the phonetic approach is only used when the confidence score of the acoustic approach is not desirable. Hence, the performance of the SLR system can be improved, while its speed degradation is not significant. To calculate final confidence scores, a heuristic method is utilized based on the acoustic scores distribution for each language. The experimental results showed that the proposed conditional cascade system could decrease the classification error of target languages with an acceptable runtime.

Automatic detection of speaker state: Lexical, prosodic, and phonetic approaches to level-of-interest and intoxication classification

Traditional studies of speaker state focus primarily upon one-stage classification techniques using standard acoustic features. In this article, we investigate multiple novel features and approaches to two recent tasks in speaker state detection: level-of-interest (LOI) detection and intoxication detection. In the task of LOI prediction, we propose a novel Discriminative TFIDF feature to capture important lexical information and a novel Prosodic Event detection approach using AuToBI; we combine these with acoustic features for this task using a new multilevel multistream prediction feedback and similarity-based hierarchical fusion learning approach. Our experimental results outperform published results of all systems in the 2010 Interspeech Paralinguistic Challenge – Affect Subchallenge. In the intoxication detection task, we evaluate the performance of Prosodic Event-based, phone duration-based, phonotactic, and phonetic-spectral based approaches, finding that a combination of the phonotactic and phonetic-spectral approaches achieve significant improvement over the 2011 Interspeech Speaker State Challenge – Intoxication Subchallenge baseline. We discuss our results using these new features and approaches and their implications for future research.

Comparison of human-supervised and fully automatic formant-trajectory measurement for forensic voice comparison

Acoustic–phonetic approaches to forensic voice comparison often include analysis of vowel formants. Such methods depend on human-supervised formant extraction, which is often assumed to be reliable and relatively robust to transmission-channel effects, but requires substantial investment of human labor. Fully automatic formant trackers require less human labor but are usually not considered reliable. This study assesses the variability within and between four human experts and compares the results of human-supervised formant measurement with several fully automatic procedures, both on studio-quality recordings and transmission-channel degraded recordings. Measurements are made of the formant trajectories of /iau/ tokens in a database of recordings of 60 female speakers of Chinese. As well as directly comparing the formant-measurements results, the formant measurements are also used as input to likelihood-ratio forensic-voice-comparison systems, and the validity and reliability of each system is empiricall...

The phonetics–interaction interface in the initiation of closings in everyday English telephone calls

This paper combines interactional and phonetic approaches to examine the phonetics–interaction interface in the initiation of closings in everyday, British-English telephone conversations. Specifically, it investigates the phonetic and interactional properties of “multi-unit sequence transition turns” (such as “yes + okay then”), which are regularly employed by speakers to manoeuvre the call from some on-topic talk into the closing section. Such shifts are managed by these turns having a two-unit design in which the first unit attends to the preceding sequence and serves to close it down, and the second unit offers and makes relevant the subsequent action of call closure. In addition to commonalities in interactional function, these turns have systematic phonetic designs with various parameters such as pitch, loudness and glottalisation patterning together in different ways. The most striking phonetic regularity observed is the common occurrence of a click at the boundary between the two units. This paper contributes to our understanding of the organisation of call closings in British-English telephone interaction and demonstrates the fruitfulness of conducting context-bound, interactional and phonetic investigations hand-in-hand.

Combining linguistic and non-linguistic information in likelihood-ratio-based forensic voice comparison: A hybrid automatic-traditional system.

In the last decade, forensic voice comparison has experienced a remarkable paradigm shift [Morrison, Sci. Justice 49, 298–308 (2009)]. Both automatic and traditional phonetic approaches have been developed within the new paradigm. The main difference is that traditional approaches are typically local in both time and frequency domains, with features like formant frequencies extracted from linguistically comparable items (e.g., words or phonemes), whereas automatic approaches are typically global, with long-term spectral properties used and linguistic information treated as noise. Since neither makes use of all the information present, combining them could improve performance. A fully automatic and a partially traditional system were compared. Data were pairs of non-contemporaneous landline-telephone recordings of 60 speakers from the Japanese National Research Institute of Police Science database (net 35–40 s speech per recording). In the fully automatic system, the whole speech-active portion of the recording was analyzed using 12th order LPCCs, mean cepstral subtraction, GMM-UBM, and logistic-regression calibration. In the partially traditional system, the same procedures were applied only to tokens of [o:], [ɴ], and [ç] extracted from the recordings, with logistic-regression fusion of the results. The performance of each system and the fusion of the two were compared using the log-likelihood-ratio cost (Cllr).

Phonetics and phonology of main stress in Italian

Vowel duration is not contrastive in standard and regional varieties of Italian. However, vowels in stressed open syllables are longer than unstressed vowels or vowels in closed syllables. The increased duration is not equal in all positions. Most notably, the increased duration of a stressed open penultimate syllable is much greater than the duration of a stressed open antepenultimate syllable or a stressed final syllable, which has no noticeable duration increase. Nonetheless, phonological analyses of Italian have characterised length by a single rule (see for example Vogel 1986, Nespor & Vogel 1986) that lengthens non-final main stress vowels regardless of position. Phonetic studies, particularly Farnetani & Kori (1983, 1990) and Marotta (1985), pay closer attention to the duration of stressed vowels in different positions. Although their explanations of stressed vowel duration differ, the common theme is that duration differences are due to shortening vowels as a consequence of word compression or position (antepenultimate or penultimate syllable) in the word.While the phonetic approaches account for differences in duration due to shortening, the phonological approaches propose lengthening with no regard for actual duration differences. The phonetic and phonological approaches to stressed vowel duration in Italian appear to be diametrically opposed. This paper proposes that lengthening a stressed vowel is the correct characterisation of duration differences in Italian, but there is no single rule that lengthens stressed vowels.

Rhythmic constraints on stress timing in English

Rhythm in speech is interpreted as the hierarchical organization of temporally coordinated prosodic units. This is a departure from conventional phonetic approaches which have focused on isochrony. Speech cycling, a novel experimental vehicle for investigating rhythmic constraints, is introduced. In a speech cycling task, subjects repeat a phrase together with a periodic stimulus and the temporal distribution of onset events (beats) is examined. Two speech cycling experiments are presented which probe the degree to which the relative durations of inter-stress intervals within a series of repeated phrases are independent. The data reveal the presence of strong rhythmic constraints on stress timing which have hitherto eluded experimenters. It is argued that these constraints are evidence for a task-specific dynamical system in which prominent events (stress beats) are constrained to occur at specific, predictable, phases of an enclosing cycle. The dynamical system is characterized by entrainment between metrical levels, a principle which underlies rhythmic coordination in other activities such as locomotion. It is demonstrated that the hierarchical nesting of metrical levels arises inevitably within a repetition task, and what is more, the construction of individual prosodic units depends to some extent on the resulting rhythmic pattern. By structuring an utterance so that prominent events lie at privileged phases of a higher-level prosodic unit, rhythm is seen as an organizational principle which has its roots in the coordination of complex action and its effect in the realm of prosodic structure.

Effects of speech rate on the absolute and relative timing of apraxic and conduction aphasic sentence production

The purpose of this investigation was to provide a constructive replication of the Kent and McNeil (1987, In Phonetic approaches to speech production in aphasia and related disorders. San Diego: College-Hill Press) study of the speech timing characteristics of apraxic and conduction aphasic speakers. Acoustic analysis was used to obtain absolute utterance durations, segment durations, and vowel formant trajectories from utterances produced under control, fast, and slow rate conditions. Segment-to-whole ratios and slope values were calculated. Results support the hypothesis presented by Kent and McNeil (1987) that there is a phonetic-motoric component contributing to the speech patterns of both the apraxic and conduction aphasic speakers sampled. Theories of rate control in normal and disordered speakers are discussed.

How phonetic is a phonological feature representation? The case of labiodental fricatives

This paper examines the psychological reality of feature representations. Given the non-cognitive linguistic and the low-level phonetic approaches, it is a priori an aopen question whether the psycholinguistic representation borrows from both, from either or from neither of these. As a test case, a point of divergence between phoneticians and linguistics has selected for scrutiny. While the former consider [f] and [v] to be labiodental fricatives, the latter regard them as underlying bilabials or simply labials. To determine if [f] and [v] behave psycholinguistically like bilabial or labiodental segments, the interactions between the fricatives at issue and the other phonemes are analyzed in two large corpora of slips of the tongue in English and German. The results indicate that [f] and [v] are indistinguishable from bilabials, that is, they are as likely to substitute for other bilabials and as unlikely to replace non-bilabials in the way that [p], [m] or [w] do. Three hypotheses are put forward in an attempt to come to grips with this finding. According to the bilabialness-only and the labialness-only hypotheses there is no node for labiodentalness in the processing network. The rival account starts from the assumption that features are represented as vectors in a space coordinate system. In this concept, there is a vector for bilabialness as well as one for labiodentalness. It is claimed that these vectors are closer to each other than their actual phonetic distance would imply. There is less empirical support for the vector hypothesis than for the bilabialness-only one. It is concluded that phonetic and psycholinguistic feature representations need not match.

Random tendencies and event dependencies : Ki Punches. IEEE Trans. Reliab.R-33 (3) 202 (August 1984)

This paper combines interactional and phonetic approaches to examine the phonetics–interaction interface in the initiation of closings in everyday, British-English telephone conversations. Specifically, it investigates the phonetic and interactional properties of “multi-unit sequence transition turns” (such as “yes + okay then”), which are regularly employed by speakers to manoeuvre the call from some on-topic talk into the closing section. Such shifts are managed by these turns having a two-unit design in which the first unit attends to the preceding sequence and serves to close it down, and the second unit offers and makes relevant the subsequent action of call closure. In addition to commonalities in interactional function, these turns have systematic phonetic designs with various parameters such as pitch, loudness and glottalisation patterning together in different ways. The most striking phonetic regularity observed is the common occurrence of a click at the boundary between the two units. This paper contributes to our understanding of the organisation of call closings in British-English telephone interaction and demonstrates the fruitfulness of conducting context-bound, interactional and phonetic investigations hand-in-hand.

Generalised availability measures for a multi-unit repairable system with standby failure : P. K. Kapur, N. L. Butani and Renu Bala. Microelectron. Reliab.24 (4) 637 (1984)

This paper combines interactional and phonetic approaches to examine the phonetics–interaction interface in the initiation of closings in everyday, British-English telephone conversations. Specifically, it investigates the phonetic and interactional properties of “multi-unit sequence transition turns” (such as “yes + okay then”), which are regularly employed by speakers to manoeuvre the call from some on-topic talk into the closing section. Such shifts are managed by these turns having a two-unit design in which the first unit attends to the preceding sequence and serves to close it down, and the second unit offers and makes relevant the subsequent action of call closure. In addition to commonalities in interactional function, these turns have systematic phonetic designs with various parameters such as pitch, loudness and glottalisation patterning together in different ways. The most striking phonetic regularity observed is the common occurrence of a click at the boundary between the two units. This paper contributes to our understanding of the organisation of call closings in British-English telephone interaction and demonstrates the fruitfulness of conducting context-bound, interactional and phonetic investigations hand-in-hand.

Is the Phonetic Generalization Hypothesis in Spelling Valid?

This study was conducted to help settle a major controversy in spelling instruction concerning the phonetic generalization hypothesis. It utilized Solomon’s Four-Group Experimental Design for 2x2x2 factorial analyses-girls versus boys, pretesting versus nonpretesting, and phonetic instruction versus no phonetic treatment. Dependent variables were two spelling test scores of pupils in 106 Grades 2-6 classes: (1) spellings consistent with two phonetic generalizations taught to treatment groups and (2) spellings unrelated to the two phonetic generalizations. In order of most significant effects found, results showed girls superior to boys, pretesting better than nonpretesting, and questionable advantage for phonetic instruction over no phonetic instruction. Test-Study methods appear to be more promising than phonetic approaches. Further research is necessary to ascertain the definite value of Test-Study methods.

An experimental study in the teaching of voice and diction through the ear training, phonetic, and oral reading approaches∗

An experimental study in the teaching of voice and diction through the ear training, phonetic, and oral reading approaches∗