Voice Imitation Research Articles

Variasi Sebutan untuk Kucing dan Pemaknaannya dalam Akun Mention Confess (Menfess) @Kochengfs

Variations in the appellation of cat are created because cat is marked as something important for humans. One influential factor in the emergence of variations in the appellation is the existence of interaction spaces among cat lovers. One of them is menfess account @kochengfs. This research examines the various appellation for cat and their meanings in the menfess account @kochengfs. The purpose of this research is to describe the variation of appellations for cat and their meanings in the menfess account @kochengfs. This research is included in the qualitative descriptive research. This research uses a semiotic approach with the trichotomous relation theory from Peirce. The data source of this research comes from the mention confess (menfess) account @kochengfs with a corpus of research data in the form of 1,758 tweets taken from 17–24 February 2023. Based on the analysis, there are 214 tweets containing 37 appellations for cat. The appellations are dominated by icon signifying with a total of 24 appellations, then symbols with 12 appellations, and index only 1 appellation. Appellations with icon signifying are based on (a) body shape; (b) body hair; (c) voice imitation; (d) fur color; (e) teeth shape; and (f) physical characteristic.

基于微信小程序的泰语词汇记忆平台设计与实现

This article provides a detailed introduction to a WeChat mini program called “Thai Echoes”, which aims to provide a convenient platform for learners to memorize Thai vocabulary more effectively. We have developed this platform based on technologies such as Spring Boot, MyBatis, and Uni-app, and designed rich functional modules such as word memory, challenge games, and voice imitation to meet the needs of Thai language learners. In addition, by analyzing user learning data, it is possible to track learners’ progress and continuously optimize teaching effectiveness. This study demonstrates the potential application of WeChat mini programs in the field of foreign language learning, providing ideas for further developing educational technologies with practical value.

PENERAPAN METODE MENDONGENG UNTUK MENGEMBANGKAN KARAKTER PEDULI LINGKUNGAN PADA ANAK USIA 5-6 TAHUN

This study describes the application of storytelling methods to develop the character of caring for the environment for children aged 5-6 years in Kindergarten of the Model Laboratory of the University of Muhammadiyah Pontianak. Ex post facto research method qualitative descriptive approach. The research subjects were teachers of group B at the Model Laboratory Kindergarten, University of Muhammadiyah Pontianak. The results showed, 1. Teacher preparation for storytelling methods, the teacher had made initial preparations such as determining goals before storytelling, determining themes, determining fairy tale titles and preparing media/props, 2. The process of applying storytelling methods the teacher greeted children with something interesting, discussed thematerial. fairy tales, starting a fairy tale slowly, with the sentence "one day live", using storytelling techniques such as intonation, body movements, voice imitation, eye contact and there is interaction between teacher and child, 3. Evaluation by the teacher after the application of the storytelling method is complete . In developing the character of caring for the environment, namely by asking again the fairy tale that has been conveyed, bringing the child to conclude positive and negative values and the assessment is taken by observing the child's behavior while in the institution.

Neural Dynamics of Karaoke-Like Voice Imitation in Singing Performance

Beyond normal and non-imitative singing, the imitation of the timbre of another singer’s voice, such as in Karaoke singing, involves the demanding reproduction of voice quality features and strongly depends on singing experience and practice. We show that precise voice imitation in a highly proficient and experienced vocal imitator, even in the absence of external auditory voice feedback, largely drew on internal cortico-subcortical auditory resources to control voicing errors based on imagined voice performance. Compared to the experienced vocal imitator, singers of a control group without experience in voice imitation used only sensorimotor feedback and demanding monitoring resources for imitation in the absence of voice feedback, a neural strategy that led, however, to a significantly poorer vocal performance. Thus, only long-term vocal imitation experience allows for the additional use of internal auditory brain resources, which result from training-induced brain plasticity, and which enable accurate vocal performance even under difficult performance conditions.

Voice Disguise in Automatic Speaker Recognition

Humans are able to identify other people’s voices even in voice disguise conditions. However, we are not immune to all voice changes when trying to identify people from voice. Likewise, automatic speaker recognition systems can also be deceived by voice imitation and other types of disguise. Taking into account the voice disguise classification into the combination of two different categories (deliberate/non-deliberate and electronic/non-electronic), this survey provides a literature review on the influence of voice disguise in the automatic speaker recognition task and the robustness of these systems to such voice changes. Additionally, the survey addresses existing applications dealing with voice disguise and analyzes some issues for future research.

Short voice imitation man-in-the-middle attacks on Crypto Phones: Defeating humans and machines1

Establishing secure voice, video and text over Internet (VoIP) communications is a crucial task necessary to prevent eavesdropping and man-in-the-middle attacks. The traditional means of secure session establishment (e.g., those relying upon PKI or KDC) require a dedicated infrastructure and may im pose unwanted trust onto third-parties. “Crypto Phones” (popular instances such as PGPfone and Zfone), in contrast, provide a purely peer-to-peer user-centric secure mechanism claiming to completely address the problem of wiretapping. The secure association mechanism in Crypto Phones is based on cryptographic protocols employing Short Authenticated Strings (SAS) validated over the voice medium. The security of Crypto Phones crucially relies on the assumption that the voice channel, over which SAS is validated, provides the properties of integrity and source authentication. In this paper, we challenge this assumption, and report on automated SAS voice imitation man-in-the-middle attacks that can compromise the security of Crypto Phones in both two-party and multi-party settings, even if users pay due diligence and even if an automated software (voice biometrics systems) is used to detect voice manipulation. The first attack, called the short voice reordering attack, builds arbitrary SAS strings in a victim’s voice by reordering previously eavesdropped SAS strings spoken by the victim. The second attack, called the short voice morphing attack, builds arbitrary SAS strings in a victim’s voice from a few previously eavesdropped sentences (less than 3 minutes) spoken by the victim. We design and implement our attacks using off-the-shelf speech recognition/synthesis tools, and comprehensively evaluate them with respect to both manual detection (based on a user study with 30 participants) and automated detection via a speaker verification tool. The results demonstrate the effectiveness of our attacks against three prominent forms of SAS encodings: numbers, PGP word lists and Madlib sentences. These attacks can be used by a wiretapper to compromise the confidentiality and privacy of Crypto Phones voice, video and text communications (plus authenticity in case of text conversations).

Genetic algorithm to estimate the input parameters of Klatt and HLSyn formant-based speech synthesizers

Voice imitation basically consists in estimating a synthesizer's input parameters to mimic a target speech signal. This is a difficult inverse problem because the mapping is time-varying, non-linear and from many to one. It typically requires considerable amount of time to be done manually. This work presents the evolution of a system based on a genetic algorithm (GA) to automatically estimate the input parameters of the Klatt and HLSyn formant synthesizers using an analysis-by-synthesis process. Results are presented for natural (human-generated) speech for three male speakers. The results obtained with the GA-based system outperform those obtained with the baseline Winsnoori with respect to four objective figures of merit and a subjective test. The GA with Klatt synthesizer generated similar voices to the target and the subjective tests indicate an improvement in the quality of the synthetic voices when compared to the ones produced by the baseline.

Analysis of voice imitation by professional/non-professional impersonators based on Kullback–Leibler divergence between acoustic models

Considering the practical use of speaker verification systems, it is important to investigate the effect of spoofing attacks by professional/non-professional voice imitation. This research proposes an analysis method of voice imitation using the distances between three GMM-based acoustic models trained from cepstral features of “impostor's original voice,” “target person's voice,” and “impostor's imitated voice.” The distance measure is defined by the Kullback-Leibler (KL) divergence. The analysis uses Japanese imitated voice produced by a male professional impersonator and six male non-professional impostors. Each impostor imitated five or six target persons who have never been tried to imitate by the impostors before the experiments. The analysis results show that 1) although the non-professional imitators drastically change their voice features by the imitation, the averaged acoustical distance between the imitated and target voice is still large, 2) whereas the professional imitator approaches their voice characteristics towards the target voice; the distance between the imitated and target voice is approximately 70% of the original distance. The experiments of speaker verification using HMM-UBM-based framework show that the professional imitation certainly yields higher equal error rates than that of non-professional imitation.

Vocal Flexibility and Prosodic Strategies in a Professional Impersonator

Voice imitation of a famous personality results in detection and reproduction of some vocal features, including spectral characteristics but also prosody, speech flow, or articulatory patterns. The objective of this study was to describe vocal flexibility in one of the best French impersonators and determine his strategies. Prospective study. We have downloaded the recording of a political speech by former French President Jacques Chirac, who we have chosen for his very specific and recognizable voice. After transcription, we asked one professional impersonator and four control subjects to do several readings in their natural voice and in a spontaneous imitation task (ie, without listening to any of Chirac's recording). To facilitate the control subject's task, we made an additional recording after having them listen to the target sample. Using Praat freeware, we have compared several prosodic measurements taken on each sample: pitch, pitch range, articulatory speed, duration of pauses, and number of pauses. Results showed significant modifications in the participant's prosody and significant differences in the strategies used by the professional impersonator and the control group. The professional impersonator's imitation strategy lies in the reproduction of global characteristics and instant alignment of prosodic variations.

사람의 말을 발성하는 개의 사례 연구

본 논문은 사람의 언어를 발성하는 개의 사례를 수동성, 능동성으로 구분하여 음원특징과 발성 원인 등을 연구하였다. 사람의 말을 발성하는 기존 사례들을 분석한 결과, 일부 개는 주인 음성의 음향특성을 이해하고 그것을 자신의 발성기관을 통해 일시적인 소리모방이 가능하다. 이것은 언어적 소통의 기능이 없는 수동적 발성 사례이다. 반면 최근 보고된 /엄마/, /누나야/ 발성을 하는 개는 기존 사례들과 확연히 구별되는 특징을 보인다. 해당 개는 상황에 따라 해당 단어를 능동적으로 반복 발성하며, 주인과 기초적 소통과 교감 기능을 수행한다. 개가 사람의 말을 능동적으로 발성할 수 있는 이유는 두뇌가 우수하고 주인과의 친밀도가 매우 높은 점, 해당 발음에 따른 사람들의 적극적인 반응 등이 원인으로 판단된다. 해당 결과는 동물의 발성 가능 소리와, 언어 학습 가능성 연구에 활용될 수 있다. This paper studies characteristics and causes of sound, and many others by distinguishing passivity and activity of the cases of a dog vocalizing human's words. As a result of the previous cases of vocalization of human's words, the dog was able to understand characteristics of a host's voice and imitate the sound using his own vocal organs. This is the case of passive vocalization accompanied by temporary voice imitation without a function of communication. On the contrary, as a consequence of the recently reported case in which a dog vocalizes such words as "Um-ma" and "Nu-na-ya," it shows the vocalization pattern clearly distinguished from the prior cases. The given dog repeatedly vocalizes pertaining words in an active manner according to circumstances and plays a role of fundamental communication and interaction with its host. The reason why the dog can vocalize the man's words actively is determined to be that the dog has a high level of intelligence and intimacy with its host, that people react actively to its pertaining pronunciation, and so forth. The following results can be used for the study that investigates animals' sound with vocalization possibility and language learning feasibility.

Spontaneous Voice Gender Imitation Abilities in Adult Speakers

BackgroundThe frequency components of the human voice play a major role in signalling the gender of the speaker. A voice imitation study was conducted to investigate individuals' ability to make behavioural adjustments to fundamental frequency (F0), and formants (Fi) in order to manipulate their expression of voice gender.Methodology/Principal FindingsThirty-two native British-English adult speakers were asked to read out loud different types of text (words, sentence, passage) using their normal voice and then while sounding as ‘masculine’ and ‘feminine’ as possible. Overall, the results show that both men and women raised their F0 and Fi when feminising their voice, and lowered their F0 and Fi when masculinising their voice.Conclusions/SignificanceThese observations suggest that adult speakers are capable of spontaneous glottal and vocal tract length adjustments to express masculinity and femininity in their voice. These results point to a “gender code”, where speakers make a conventionalized use of the existing sex dimorphism to vary the expression of their gender and gender-related attributes.

Revisiting the design and implementation of GAVIS: J-GAVIS


 
 
 GAVIS (Genetic Algorithm based Voice Imitation System), [1], is a system whose purpose is to find a set of effects to imitate voice signals. The system is based on Genetic Algo- rithms and Fourier Transforms. Although GAVIS proves to be effective, some deficiencies were found, and amongst them was the execution speed of the system. It is to improve such deficiencies that a new version of the system was designed and implemented. In this paper, we present the foundations for GAVIS’ construction and a new and improved design and implementation of GAVIS (J-GAVIS) and describe its new features.
 
 

Automatic Speaker Recognition as a Measurement of Voice Imitation and Conversion

Voices can be deliberately disguised by means of human imitation or voice conversion. The question arises as to what extent they can be modified by using either of both methods. In the current paper, a set of speaker identification experiments are conducted; first, analysing some prosodic features extracted from voices of professional impersonators attempting to mimic a target voice and, second, using both intragender and crossgender converted voices in a spectral-based speaker recognition system. The results obtained in the current experiments show that the identification error rate increases when testing with imitated voices, as well as when using converted voices, especially the crossgender ones.

A case study of successful voice imitation

Our voices and speech behaviour give cues to the listener as to our identity. These cues make it possible for the listener to recognise a voice without seeing the speaker. A professional impersonator has to identify the salient and characteristic features of the target voice in order to succeed. The present phonetic study of a Swedish professional impersonator and one of his voice imitations compares the target voice, the voice imitation and the impersonator's own voice. The findings indicate that a successful impersonation is the result of the impersonator's ability to alter his voice in numerous ways.

Voice spectrograms as a function of age, voice disguise, and voice imitation.

In order to determine if speech spectrograms can be used to identify human beings, two questions must be studied: (1) does the formant structure of phonemes uttered by a certain speaker change over a long interval of time, and (2) can the formant structure be changed by disguise, or is it even possible to imitate the formant structure of another speaker? Spectrograms of utterances produced by seven speakers and recorded over periods of up to 29 years showed that the frequency position of formants and pitch of voiced sounds shift to lower frequencies with increasing age of test persons. Speech spectrograms of texts spoken in a normal and a disguised voice revealed strong variations in formant structure. Speech spectrograms of utterances of well-known people have been compared with those of imitators. The imitators succeeded in varying the formant structure and fundamental frequency of their voices, but they were not able to adapt these parameters to match or even be similar to those of imitated persons.