Modeling prosody for language identification on read and spontaneous speech

This paper describes two experiments aimed at exploring the relationship between linguistic aspects and perceived proficiency in read and spontaneous speech. 5,000 utterances of read speech by 50 non-native speakers of Korean in Experiment 1, and of 6,000 spontaneous speech utterances in Experiment 2 were scored for proficiency by native human raters and were analyzed by factors known to be related to perceived proficiency. The results show that the factors investigated in this study can be employed to predict proficiency ratings, and the predictive power of fluency and pitch and accent accuracy is strong for both read and spontaneous speech. We also observe that while proficiency ratings of read speech are mainly related to segmental accuracy, those of spontaneous speech appear to be more related to pitch and accent accuracy. Moreover, proficiency in read speech does not always equate to the proficiency in spontaneous speech, and vice versa, with Pearson’s per-speaker correlation score of 0.535.

The recognition of read and spontaneous speech in local vernacular: The case of Zurich German

This paper reports various investigations on recognizing spontaneous presentation speech in connection with the “Spontaneous Speech” national project started in 1999. Presentation speech uttered by 10 male speakers of approximately 4.5 hours duration has been recognized. Experimental results show that acoustic and language modeling based on an actual spontaneous speech corpus is far more effective than conventional modeling based on read speech. The recognition accuracy has a wide speaker-tospeaker variability according to the speaking rate, the number of fillers, the number of repairs, etc. It was confirmed that unsupervised speaker adaptation of acoustic models was effective to improve the recognition accuracy. The recognition accuracy for spontaneous speech is, however, still rather low, and there remains a large number of research issues.

This paper addresses the issue of producing synthetic speech for an interpreted dialogue where the attitudinal colouring of an original utterance is to be preserved; it describes differences in speaking style between read and spontaneous speech from the viewpoint of synthesis research and discusses the design of a synthesis system incorporating labels to encode the prosodic and segmental variation simultaneously. Spontaneous speech confronts us with phenomena that were not encountered in corpora of prepared or read speech, and to account for these we have to identify increasingly higher-level factors of discourse structure and speaker involvement. The paper makes three specific claims: (a) that it is better to label the distinctive characteristics of speech through higher-level context dependencies, and to select units for synthesis from appropriate contexts, rather than attempt to predict and modify fine phonetic detail; (b) that the labelling of segmental and prosodic characteristics can be done adequately for speech synthesis using automatic techniques, leaving the human labeller free to identify higher-level discourse-related aspects of the speech; and (c) that instead of minimizing the size of the source database of speech units, we should rather be concerned to maximize its variety and to efficiently select from it the units that most closely express the characteristics of the target speech. The CHATR resynthesis toolkit performs many of these tasks.

Sequence labeling to detect stuttering events in read speech

Discriminative keyword spotting

The Acoustic Voice Quality Index (AVQI) is a widely adopted tool for assessing dysphonia, incorporating sustained vowel and continuous speech samples to enhance ecological validity. Despite its broad use, the reliability of AVQI measurements, particularly in digital health applications, remains underexplored. This study aims to review the literature on AVQI's development and validation from the perspective of internal consistency of acoustic measurements, and to assess the amount of speech required to reliably determine the AVQI of a voice recording. Two sub-studies are described. Study 1: A narrative review was conducted using Google Scholar and Scopus to identify studies mentioning “AVQI” and “reliability”. Key methodological details were extracted from studies reporting AVQI measurements, summarized, and discussed in terms of how the internal consistency of acoustic measurements was ensured across studies where AVQI had been validated or applied. Study 2: Recordings of read and spontaneous speech as well as sustained vowels produced by 54 native Swedish speakers (22 female, 32 male; age range: 46–78 years) were assessed in terms of the amount of speech required to obtain a reliable acoustic measurement of the speakers' voices. Simulations were performed using read and spontaneous speech materials of varying lengths. The variability in AVQI and its sub-measures was analyzed relative to the length (in words or in seconds) of continuous speech included. The result of study 1 shows that out of 129 identified studies, 85 reported on AVQI measurements. The review highlighted substantial variability in continuous speech lengths used across studies, ranging from 4–200 words. A recommendation of 3 s of voiced segments was often adhered to, but was found to lack sufficiently robust grounding. The simulations indicated that AVQI achieves internal consistency at speech lengths of approximately 50 words (or 20 s), which is longer than the current recommendation. Both read and spontaneous speech provided stable AVQI measurements at these speech lengths. AVQI thresholds obtained using speech lengths shorter than 50 words (20 s) may require re-evaluation. Robust standardization of continuous speech lengths is essential for the successful adoption of AVQI in digital health applications.

Individuals who share a dialect nonetheless differ consistently in phonetic expression. The origin of such idiolectal differences has been sought in sociolinguistically and in physiologically motivated accounts. Our study focused on characteristic differences in the habitual rate of speech production within a dialect, aiming to calibrate the contribution of neuromuscular constraint in idiolect differences. We sampled and analyzed the temporal characteristics of spontaneous and read speech produced by a set of adolescent female talkers from Brooklyn, New York. Spontaneous speech was elicited by open-ended questions, while the Farm Script was used as the text for production of read speech at comfortable and at rapid rates. Overall, the rate of rapid read speech was correlated with the rate of comfortable spontaneous speech and comfortable reading, indicating a clear contribution of neuromuscular constraints to characteristic differences in speech rate. However, some talkers exhibiting the ability to produce rapid speech at the fastest rates adopted comfortable speaking rates at the slower end of the distribution. In light of these findings, we doubt that idiolectal differences in speaking rate can be accountable solely by appeal to differences between individuals in agility of oral articulators. [Work supported by NIH DC00308.]

Multiethnolectal ways of speaking have been emerging for 30 years in culturally and linguistically diverse neighborhoods of European cities, including Zurich (Switzerland). Among the prosodic features of Germanic multiethnolects, a so-called ‘staccato’ rhythm has been mentioned in several studies. For instance, a comparison between two groups of adolescents (12 speakers each) showed that speakers of multiethnolectal Zurich German displayed slower syllable rates and less vowel duration variability than speakers of a rather traditional dialect. This study compares syllable rate and speech rhythm metrics (nPVI-V, nPVI-C) in spontaneous and read speech of 48 Zurich German adolescents. In a regression analysis, rhythmic measures were compared with the perception of how multiethnolectal the speakers sounded (rating score). The results showed that syllable rate and nPVI-V were related to rating score independently of speaking style (read, spontaneous speech): Speakers who were perceived as more multiethnolectal had a slower syllable rate and less vowel duration variability. Such findings were not observed for nPVI-C. These results suggest that syllable rate and speech rhythm (at least, vowel duration variability) are stable phonetic features of multiethnolectal Zurich German, since the relationship between these features and the perception of multiethnolectal speech was observed in both read and spontaneous speech.

In this work, we present a complete framework of discriminative training using non-uniform criteria for keyword spotting, adaptive boosted non-uniform minimum classification error (MCE) for keyword spotting on spontaneous speech. To further boost the spotting performance and tackle the potential issue of over-training in the non-uniform MCE proposed in our prior work, we make two improvements to the fundamental MCE optimization procedure. Furthermore, motivated by AdaBoost, we introduce an adaptive scheme to embed error cost functions together with model combinations during the decoding stage. The proposed framework is comprehensively validated on two challenging large-scale spontaneous conversational telephone speech (CTS) tasks in different languages (English and Mandarin) and the experimental results show it can achieve significant and consistent figure of merit (FOM) gains over both ML and discriminatively trained systems.

Long-Term Effects of Gender-Affirming Hormone Therapy from Adolescence to Adulthood on Voice.

OBJETIVO: Investigar e caracterizar a velocidade de fala e as rupturas da fala em situação espontânea e em leitura oral, em indivíduos gagos e não gagos e investigar a relação entre essas variáveis. MÉTODOS: Trinta participantes com idades entre 17 e 59 anos e, no mínimo, oito anos de escolaridade, constituíram o Grupo Estudo, com 15 indivíduos gagos, e o Grupo Controle, com 15 indivíduos não gagos. Os indivíduos do Grupo Controle e do Grupo Estudo foram pareados por idade, gênero e nível de escolaridade. Após anamnese, foram realizadas as seguintes avaliações: neuropsicológica breve, específica da gagueira e específicas da leitura. As disfluências foram analisadas e calculou-se a velocidade da fala espontânea e na leitura oral. RESULTADOS: Ocorreram mais disfluências na fala espontânea que na leitura oral de texto, em ambos os grupos. Em relação à velocidade, no Grupo Controle, a leitura de pseudopalavras e de texto correlacionaram-se positivamente e no Grupo Estudo, todas as variáveis correlacionaram-se positivamente. CONCLUSÃO: A análise da velocidade e das rupturas de fala caracterizou ambos os grupos, tanto em situação de fala espontânea, quanto na leitura que evidencia perfis de desempenho diferenciados pela velocidade de fala, frequência e tipologia das rupturas. A investigação demonstra que indivíduos gagos apresentaram valores mais baixos de velocidade, assim como maior ocorrência de disfluências, tanto na fala espontânea quanto na leitura oral, em comparação com indivíduos não gagos.

Oral cancer speech is a disease which impacts more than half a million people worldwide every year. Analysis of oral cancer speech has so far focused on read speech. In this paper, we 1) present and 2) analyse a three-hour long spontaneous oral cancer speech dataset collected from YouTube. 3) We set baselines for an oral cancer speech detection task on this dataset. The analysis of these explainable machine learning baselines shows that sibilants and stop consonants are the most important indicators for spontaneous oral cancer speech detection.

Previous studies have demonstrated a number of ways in which normal speakers' phonetic performance varies across reading and spontaneous speech tasks. This study set out to investigate whether similar differences across speech sampling tasks were found in a mixed group of dysarthric subjects. A selection of segmental and prosodic parameters were investigated acoustically in the performance of five mild dysarthric speakers and five matched control subjects. The results demonstrated that breath-pause position, unstressed vowel duration and voice-onset time were subject to variation across sampling task in the speech produced by different types of dysarthric speaker. The results suggest that read material produced by dysarthric speakers may not be wholly representative of those speakers' spontaneous speech. Preliminary implications for clinical practice are discussed. The findings point to the need for further research to investigate the extent of such differences and their implications for dysarthria assessment, which up to the present has relied predominantly on read material.

The purpose of this study was to determine consistency of the acoustic measurement of fundamental frequency (f0) and f0 perturbation using the Visi-Pitch. Samples of speech including a reading passage, vowels, and spontaneous speech were recorded for 12 normal young adults (6 men and 6 women). The results indicated that test-retest reliability was highest for the reading passage. The measurements of fundamental frequency for reading and spontaneous speech were very similar, but vowel production was, on average, higher in frequency than the other contexts. Test-retest measures of perturbation using the Visi-Pitch did not have a high correlation coefficient. Perturbation measures must be interpreted cautiously because of the influence of frequency.