LSTM-Based Speech Segmentation for TTS Synthesis

2019 ◽  
pp. 361-372 ◽  
Author(s):  
Zdeněk Hanzlíček ◽  
Jakub Vít ◽  
Daniel Tihelka
Keyword(s):  
Speech Segmentation

Rapid Serial Auditory Presentation

2015 ◽  
Vol 62 (5) ◽  
pp. 346-351 ◽  
Author(s):  
Ana Franco ◽  
Julia Eberlen ◽  
Arnaud Destrebecqz ◽  
Axel Cleeremans ◽  
Julie Bertels
Keyword(s):  
Statistical Learning ◽  
Reaction Times ◽  
Visual Presentation ◽  
Detection Task ◽  
Speech Segmentation ◽  
Auditory Presentation ◽  
Indirect Measure ◽  
Speech Stream ◽  
Adult Participants ◽  
Presentation Procedure

Abstract. The Rapid Serial Visual Presentation procedure is a method widely used in visual perception research. In this paper we propose an adaptation of this method which can be used with auditory material and enables assessment of statistical learning in speech segmentation. Adult participants were exposed to an artificial speech stream composed of statistically defined trisyllabic nonsense words. They were subsequently instructed to perform a detection task in a Rapid Serial Auditory Presentation (RSAP) stream in which they had to detect a syllable in a short speech stream. Results showed that reaction times varied as a function of the statistical predictability of the syllable: second and third syllables of each word were responded to faster than first syllables. This result suggests that the RSAP procedure provides a reliable and sensitive indirect measure of auditory statistical learning.

Trochaic rhythm in speech segmentation

1997 ◽  
Author(s):  
Jean Vroomen ◽  
Beatrice de Gelder
Keyword(s):  
Speech Segmentation

scholarly journals Statistical Speech Segmentation in Tone Languages: The Role of Lexical Tones

2017 ◽  
Vol 61 (1) ◽  
pp. 84-96 ◽  
Author(s):  
David M. Gómez ◽  
Peggy Mok ◽  
Mikhail Ordin ◽  
Jacques Mehler ◽  
Marina Nespor
Keyword(s):  
Speech Processing ◽  
Additional Data ◽  
Native Speakers ◽  
Speech Segmentation ◽  
Lexical Tones ◽  
Tone Languages ◽  
Transitional Probabilities ◽  
Lexical Processes

Research has demonstrated distinct roles for consonants and vowels in speech processing. For example, consonants have been shown to support lexical processes, such as the segmentation of speech based on transitional probabilities (TPs), more effectively than vowels. Theory and data so far, however, have considered only non-tone languages, that is to say, languages that lack contrastive lexical tones. In the present work, we provide a first investigation of the role of consonants and vowels in statistical speech segmentation by native speakers of Cantonese, as well as assessing how tones modulate the processing of vowels. Results show that Cantonese speakers are unable to use statistical cues carried by consonants for segmentation, but they can use cues carried by vowels. This difference becomes more evident when considering tone-bearing vowels. Additional data from speakers of Russian and Mandarin suggest that the ability of Cantonese speakers to segment streams with statistical cues carried by tone-bearing vowels extends to other tone languages, but is much reduced in speakers of non-tone languages.

Which came first: Infants learning language or motherese?

2004 ◽  
Vol 27 (4) ◽  
pp. 505-506 ◽  
Author(s):  
Heather Bortfeld
Keyword(s):  
Language Acquisition ◽  
Word Recognition ◽  
Language Learning ◽  
Learning Process ◽  
Building Blocks ◽  
Speech Segmentation ◽  
Learning Language

Although motherese may facilitate language acquisition, recent findings indicate that not all aspects of motherese are necessary for word recognition and speech segmentation, the building blocks of language learning. Rather, exposure to input that has prosodic, phonological, and statistical consistencies is sufficient to jump-start the learning process. In light of this, the infant-directedness of the input might be considered superfluous, at least insofar as language acquisition is concerned.

scholarly journals Automatic speech segmentation using throat-acoustic correlation coefficients

2016 ◽  
Vol 6 (1) ◽  
Author(s):  
Rustam Rafikovich Mussabayev ◽  
Maksat N. Kalimoldayev ◽  
Yedilkhan N. Amirgaliyev ◽  
Timur R. Mussabayev
Keyword(s):  
Large Volume ◽  
Automatic Segmentation ◽  
Correlation Coefficients ◽  
High Accuracy ◽  
Speech Segmentation ◽  
Preliminary Training ◽  
Effi Ciency ◽  
Segmentation Accuracy ◽  
New Type ◽  
The Given

Abstract This work considers one of the approaches to the solution of the task of discrete speech signal automatic segmentation. The aim of this work is to construct such an algorithm which should meet the following requirements: segmentation of a signal into acoustically homogeneous segments, high accuracy and segmentation speed, unambiguity and reproducibility of segmentation results, lack of necessity of preliminary training with the use of a special set consisting of manually segmented signals. Development of the algorithm which corresponds to the given requirements was conditioned by the necessity of formation of automatically segmented speech databases that have a large volume. One of the new approaches to the solution of this task is viewed in this article. For this purpose we use the new type of informative features named TAC-coefficients (Throat-Acoustic Correlation coefficients) which provide sufficient segmentation accuracy and effi- ciency.

Sequential speech segmentation based on the spectral ARMA transition measure

1996 ◽  
Vol 15 (1) ◽  
pp. 71-92 ◽  
Author(s):  
Srbijanka R. Turajlić ◽  
Zoran M. Šarić
Keyword(s):  
Speech Segmentation ◽  
Transition Measure

Automatic speech segmentation with multiple statistical models

2006 ◽  
Author(s):  
Seung Seop Park ◽  
Jong Won Shin ◽  
Nam Soo Kim
Keyword(s):  
Statistical Models ◽  
Speech Segmentation
Sign in / Sign up

Export Citation Format

Share Document