Phonetic Database Research Articles

Comparing pre-linguistic normalization models against US English listeners’ vowel perception

One of the central computational challenges for speech perception is that talkers differ in pronunciation--i.e., how they map linguistic categories and meanings onto the acoustic signal. Yet, listeners typically overcome these difficulties within minutes (Clarke & Garrett, 2004; Xie et al., 2018). The mechanisms that underlie these adaptive abilities remain unclear. One influential hypothesis holds that listeners achieve robust speech perception across talkers through low-level pre-linguistic normalization. We investigate the role of normalization in the perception of L1-US English vowels. We train ideal observers (IOs) on unnormalized or normalized acoustic cues using a phonetic database of 8 /h-VOWEL-d/ words of US English (N = 1240 recordings from 16 talkers, Xie & Jaeger, 2020). All IOs had 0 DFs in predicting perception—i.e., their predictions are completely determined by pronunciation statistics. We compare the IOs’ predictions against L1-US English listeners’ 8-way categorization responses for /h-VOWEL-d/ words in a web-based experiment. We find that (1) pre-linguistic normalization substantially improves the fit to human responses from 74% to 90% of best-possible performance (chance = 12.5%); (2) the best-performing normalization accounts centered and/or scaled formants by talker; and (3) general purpose normalization (C-CuRE, McMurray & Jongman, 2011) performed as well as vowel-specific normalization.

Analysis of the Artistic Elements of Broadcast Hosting Based on Media Speech Corpus

Whether it is speech synthesis research or speech recognition research, it depends on the construction of excellent speech corpus at the back end to some extent. The phonetic corpus includes three forms: text database, phonetic database and acoustic parameter database. Based on phonetic facts, it serves the basic research of language and the processing of language modernization technology through the functions of natural phonetic collection, phonetic annotation, retrieval and statistics. The purpose of the construction of the media corpus is to serve the research of the audio language of the media, especially the prosody research of the host language. Broadcasting and hosting is an important part of radio and television, and the diversity and richness of modern radio and television programs also put forward new requirements for broadcasting and hosting. Broadcasting determines the basic style, purpose and orientation of radio and television news programs. In the media industry, the status of broadcasting and hosting art is gradually highlighted. Under the background of media convergence, broadcasting and hosting art needs to be developed in more advanced technical fields, and the media voice corpus is an important product created by the development of science and technology.

On the Monophthong Features of Cangzhou Dialect (Hebei Province) based on Acoustic Data Analysis in the Big Data Era

With reference to the acoustic data of seven first-level vowels in Mandarin Chinese, this paper examines the vowel characteristics of the 16 dialects in Cangzhou, Hebei, and summarizes the local and overall characteristics of the Monophthongs in the Cangzhou dialect based on a large amount of acoustic data. Through comparative analysis of the distribution of Monophthongs of various dialects in Cangzhou and their differences and similarities with Mandarin, we hope to enrich the dialect phonetic database and provide a reference basis for data support for the promotion of Mandarin Chinese.

Compiling of Phonetic Database Structure

The voice corpus of language is the essential part of the linguistic resources, and it contains the phonetic database. A phonetic database is a structured collection of software-delivered speech fragments. Nowadays, phonetic database or voice corpus became like a new element in speech technologies, and much investigation has taken place according to this event. The investigators' interest in voice corpus is related to the development of a speech recognition system. Today it is enough to experience in preparation of a phonetic database. Equipped with unique information on the preparation and usage of everyday speech corpus, the development level of speech technologies and the increasing power of computer technologies allow for the investigation of various language materials, largescale, and statistical phonetic research. These developed directions of linguistics were investigated in this article. Speech corpora are a valuable source of information for phonological research and the study of sound patterns. The study of speech corpora is in its infancy compared to other field studies in linguistics. Existing speech corpora form the part of the world's languages and do not fully represent all the dialects and speech forms by phonological aspect. The article analyses the history, structure, and importance of developing speech corpses, a branch of corpus linguistics and has developed in recent years. The article also lists the main features to be considered in the design of the speech corpus.

Optimizing Arabic Speech Distinctive Phonetic Features and Phoneme Recognition Using Genetic Algorithm

Distinctive phonetic features have an important role in Arabic speech phoneme recognition. In a given language, distinctive phonetic features are extrapolated from acoustic features using different methods. However, exploiting lengthy acoustic features vector in the sake of phoneme recognition has a huge cost in terms of computational complexity, which in turn, affects real time applications. The aim of this work is to consider methods to reduce the size of features vector employed for distinctive phonetic feature and phoneme recognition. The objective is to select the relevant input features that contribute to the speech recognition process. This, in turn, will lead to a reduced computational complexity of recognition algorithm, and an improved recognition accuracy. In the proposed approach, genetic algorithm is used to perform optimal features selection. Therefore, a baseline model based on feedforward neural networks is first built. This model is used to benchmark the results of proposed features selection method with a method that employs all elements of a features vector. Experimental results, utilizing the King Abdulaziz City for Science and Technology Arabic Phonetic Database, show that the average genetic algorithm based phoneme overall recognition accuracy is maintained slightly higher than that of recognition method employing the full-fledge features vector. The genetic algorithm based distinctive phonetic features recognition method has achieved a 50% reduction in the dimension of the input vector while obtaining a recognition accuracy of 90%. Moreover, the results of the proposed method is validated using Wilcoxon signed rank test.

Construct a phonetic database and develop a phonetic transcription in Gujarati language

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

The Phonetic Alphabet of the Chechen Language as a Basis of a Speech-Synthesis System

This paper describes the principles for developing the AZBAT phonetic alphabet, which was created by analogy with the DARPAbet phonetic alphabet of the English language and is oriented to creating the speech corpus and system for synthesis of Chechen speech. The experience of developers of other phonetic alphabets and databases was used; account was also taken of the features of pronunciation and graphics, rules of compatibility, and variability of phonemes, which had been described in the works of well-known Chechen philologists. The classification of vowels and consonant phonemes is given, according to which each phoneme has the attributes that are necessary to implement the program code. The designed system for synthesis of Chechen speech is assigned a basic set of acoustic phonetic elements that consists of diphones and allophones. This set will be complied with to build an acoustic phonetic database that is the basis of a system for automatic synthesis of Chechen speech.

Information-theoretic analysis of efficiency of the phonetic encoding–decoding method in automatic speech recognition

A words phonetic decoding method in automatic speech recognition is considered. The properties of Kullback–Leibler divergence are used to synthesize the estimation of the distribution of divergence between minimum speech units (e.g., single phonemes) inside a single class. It is demonstrated that the minimum variance of the intraphonemic divergence is reached when the phonetic database is tuned to the voice of a single speaker. The estimations are proven by experimental results on the recognition of vowel sounds and isolated words of Russian language.

System Determining Pronunciation Correctness of Japanese Words

A system determining pronunciation correctness of Japanese words is presented. The system is composed of six separate modules: signal segmentation, transcription interpretation, synthesis, comparison, error interpretation and phonetic database. The system uses two input sources: speech signal and its Latin transcription. The system is designed to deal specifically with Japanese language, due to the language's specificity in terms of speech. Based on the input, a timeline pointing out the locations of vowels is calculated, followed by determining the locations of all the moras (syllable timings). The signal, segmented in such a way, is then compared with a signal synthesized using a phonetic database and the transcription data. As a result the differences are pointed out and interpreted.

Phonetic encoding method in the isolated words recognition problem

A phonetic approach to the problem of automatic recognition of isolated words is investigated. The phonetic encoding method whereby each word from a vocabulary is associated with the code sequence of stable phonemes is proposed. The information-theoretical estimate of vocabulary confusability, the calculations of which rely on the phonetic database of a speaker and the communications channel SNR, is synthesized using the Kullback-Leibler divergence properties. In the experimental study of the proposed method, the mutual influence between the recognition quality and the proposed estimate of confusability is demonstrated by solving the problem of recognition of words in the Russian speech. It is established that the introduced requirement to isolated syllable pronunciation makes it possible to attain the 90–95% accuracy of recognition for vocabularies containing 2000 words.

Evidence for Direct Geographic Influences on Linguistic Sounds: The Case of Ejectives

We present evidence that the geographic context in which a language is spoken may directly impact its phonological form. We examined the geographic coordinates and elevations of 567 language locations represented in a worldwide phonetic database. Languages with phonemic ejective consonants were found to occur closer to inhabitable regions of high elevation, when contrasted to languages without this class of sounds. In addition, the mean and median elevations of the locations of languages with ejectives were found to be comparatively high. The patterns uncovered surface on all major world landmasses, and are not the result of the influence of particular language families. They reflect a significant and positive worldwide correlation between elevation and the likelihood that a language employs ejective phonemes. In addition to documenting this correlation in detail, we offer two plausible motivations for its existence. We suggest that ejective sounds might be facilitated at higher elevations due to the associated decrease in ambient air pressure, which reduces the physiological effort required for the compression of air in the pharyngeal cavity–a unique articulatory component of ejective sounds. In addition, we hypothesize that ejective sounds may help to mitigate rates of water vapor loss through exhaled air. These explications demonstrate how a reduction of ambient air density could promote the usage of ejective phonemes in a given language. Our results reveal the direct influence of a geographic factor on the basic sound inventories of human languages.

Turing Test-Based Evaluation of an Experimental System for Generation of Casual English Sentences from Regular English Input

This paper proposes an experimental system for generating slang-style casual English sentences from regular English input using a phonetic database approach, primarily as an AI task, with real-life applications such as social media marketing. An original database consisting of multiple candidates of casual English phonemes was constructed, and linguistic analysis of Twitter data used to establish the optimum frequency of slang tokens per sentence. The human-likeness and legibility of output sentences of the experimental system were evaluated using an experiment based on the classical definition of the Turing test, in which fifty human evaluators attempted to distinguish sentences produced by the system from genuine humanauthored sentences. The experiment results demonstrated that the gap in human-likeness scores between the “human” and “machine” sentences was small, and that some “machine” sentences actually outperformed several of the “human sentences.” The “machine” sentences’ average score of 3.1 on a 5-point scale, where 3 indicated complete uncertainty of whether the sentences were human-authored or machine-authored, can be considered a pass of the Turing test in the established definition. In this paper, we describe the potential approaches to the task, the construction of the phonetic database and the proposed system, and discuss the evaluation results.

Hybrid models based on biological approaches for speech recognition

This paper aims to adapt the Clonal Selection Algorithm (CSA) which is usually used to explain the basic features of artificial immune systems to the learning of Neural Networks, instead of Back Propagation. The CSA was first applied to a real world problem (IRIS database) then compared with an artificial immune network. CSA performance was contrasted with other versions of genetic algorithms such as: Differential Evolution (DE), Multiple Populations Genetic Algorithms (MPGA). The tested application in the simulation studies were IRIS (vegetal database) and TIMIT (phonetic database). The results obtained show that DE convergence speeds were faster than the ones of multiple population genetic algorithm and genetic algorithms, therefore DE algorithm seems to be a promising approach to engineering optimization problems. On the other hand, CSA demonstrated good performance at the level of pattern recognition, since the recognition rate was equal to 99.11% for IRIS database and 76.11% for TIMIT. Finally, the MPGA succeeded in generalizing all phonetic classes in a homogeneous way: 60% for the vowels and 63% for the fricatives, 68% for the plosives.

Voice and Aspiration of Stops in Turkish

According to the descriptive grammars of Turkish (Kornfilt 1997, Swift 1963, Lewis 1967, among others) and underspecification-based analysis of Turkish (Inkelas 1995), stops have a two-way contrast: voiced unaspirated vs. voiceless aspirated. Moreover, voiced stops are described as fully voiced in all positions. By contrast, it is argued in this paper that Turkish has a three-way contrast of stops, which is a combination of [spread glottis] and [voice] contrasts. More specifically, Turkish stops contrast as voiceless aspirated vs. voiceless unaspirated vs. voiced. Support for the claim comes from an acoustic-phonetic experimental study of Turkish. In this study a native male speaker of Turkish was recorded and analyzed acoustically with a speech analysis software package (Wavesurfer). In addition, a list of words read by a native female speaker of Turkish from the University of Victoria Phonetic Database was analyzed. The acoustic analysis of the data shows that Turkish has voiceless aspirated stops in all positions in a word. Voiced stops are found in intervocalic position, word-finally and in consonant clusters. Moreover, the data reveal voiceless unaspirated stops in word-initial position and in consonant clusters. In order to account for the data, an OT analysis of the three-way contrast of stops is proposed. This analysis entails that *sg and *voice are low-ranking in Turkish. Once this three-way contrast is acknowledged, a straightforward alternative to the underspecification analysis of Inkelas (1995) is possible.

Review of Pickering & Rosner (1993): Oxford Acoustic Phonetic Database on Compact Disc

Review of Pickering & Rosner (1993): Oxford Acoustic Phonetic Database on Compact Disc

Voice across America: Toward robust speaker-independent speech recognition for telecommunications applications

The demand for telecommunications applications of automatic speech recognition has exploded in recent years. This area seems a natural candidate for speech recognition systems, since it embraces a tremendous variety of applications that rely entirely on audio signals and serial interfaces. However, the telecommunications environment strains the capabilities of current technology, given its broad range of uncontrollable variables, from speaker characteristics to telephone handsets and line quality. Current recognition systems have attained impressive performance levels on relatively controlled tasks, such as speaker-independent continuous digit recognition on laboratory databases comprising a few hundred speakers [l-3]. To comprehend the additional challenges of the telecommunications environment, we must study the effects on recognition of handset and channel characteristics, speaker accent, speaking style, and lexicon, as well as the interactions among these factors. No small amount of data will suffice to model these conditions. Simultaneous with the explosion of telecommunications applications has been the introduction of powerful statistical modeling techniques, known as hidden Markov models (HMMs), to speech recognition [4,5]. These computationally intensive algorithms introduce a large number of degrees of freedom into the speech recognition problem and hence exhibit slow convergence properties. As a consequence, they require orders of magnitude more training data than the previous generation of deterministic techniques. Many databases collected in the mid-l%Os, such as the DARPA Resource Management database [6] and the TIMIT Acoustic Phonetic database [7], while ambitious programs in their own right, have proven to consistently underrepresent important dimensions in HMM recognition systems due to their limited coverage. The Voice Across America (VAA) database being collected at Texas Instruments is designed to satisfy the data requirements of this next generation of speech recognition systems. Our goal is to collect data over standard long-distance telephone lines from 100,000 speakers representing a demographically and geographically balanced sample of the contiguous United States. This database will provide the foundation for a thorough investigation of factors affecting speaker-independent continuous speech recognition for American English. Similar projects are being planned for other countries, and will form the basis for research into recognition of Japanese, British English, and European languages. As of now, we have completed two phases of the VAAproject for a total of 50,000 utterances from nearly 3700 speakers. This paper describes the methods and motivation for VAA data collection and validation procedures, the current contents of the database, and the results of exploratory research on a 1088-speaker subset of the database. Our initial results underscore the need for an extensive database: even 1088 speakers-a large database by traditional standards-are insufficient to adequately represent the many dimensions of interest. One of our purposes here is to share the insights we have gained into telephone-based data collection, in the belief that the VAA model is likely to become the standard method of collecting data over the tele-

Spectral characteristics of English stops in prestressed position

Spectral characteristics of English stops in prestressed position, both in singleton and in clusters, are examined in detail using a data base designed for controlled acoustic phonetic research [Victor W. Zue, “Acoustic phonetic data base for the study of selected English consonants, consonant clusters, and vowels,” J. Acoust. Soc. Am. 57, S34(A) (1975)]. The study being presented here is based on the analysis of some 1200 stops spoken by three male speakers. Results on the spectral characteristics of the stops at the release, during the transient, and following the onset of voicing will be presented as a function of (1) the voicing characteristics of the stop; (2) the place of articulation of the stop; and (3) the phonetic context (i.e., the influence of the following vowel or sonorant). Results on inter‐ and intraspeaker variability will also be discussed.

Duration of English stops in prestressed position

Durational characteristics of English stops in prestressed position, both in singleton and in clusters, are examined in detail using a data base designed for controlled acoustic phonetic research. [Victor W. Zue, “Acoustic phonetic data base for the study of selected English Constants, consonant clusters, and vowels,” J. Acoust. Soc. Am. 57, S34(A) (1975)]. The study being presented here is based on the analysis of some 1200 stops spoke by 3 male speakers. Results indicate systematic variations of closure, voice-onset time, frication, and aspiration durations as a function of: (1) the voicing characteristics of the stop; (2) the place of articulation of the stop; and (3) the phonetic environment (i.e., the influence of the following vowel for singleton stops, and the influence of the preceding fricative and/or the following sonorant for clusters). Results on inter- and intraspeaker variability will also be discussed.

Acoustic phonetic data base for the study of selected English consonants, consonant clusters, and vowels

Improved understanding of the acoustics of speech events and recent advances in speech analysis techniques, combined with the availability of large and fast computers, have enabled speech researchers to examine and interpret a large corpus of acoustic data. These reasons provided motivation for constructing an acoustic phonetic data base where the acoustic characteristics of speech sounds can be studied in a detailed and systematic way. The data base includes a substantial number of nonsense CVC utterances (embedded in a carrier sentence) produced by several speakers. The consonants and the vowel are systematically varied. Using the acoustic analysis system that has been implemented, analog recordings can be digitized and processed (via DFT or linear prediction) in real time. The waveform, spectra, and hand-marked phonetic labels are stored on digital tapes for later referencing. During the presentation of this paper, the display and data analysis capabilities of the data-base will be demonstrated. Results on the relative durations of frication and aspiration of voiceless plosives, and results on rapid spectral changes at the release of stops will be presented.