Individuals on the autism spectrum often have difficulties producing intelligible speech with either high or low speech rate, and atypical pitch and/or amplitude affect. In this study, we present a novel intervention towards customizing speech enabled games to help them produce intelligible speech. In this approach, we clinically and computationally identify the areas of speech production diffi...

This study investigates a signal theoretic approach to rendering acoustic events. Acoustic events modeling language (AEML) is an essential part of acoustic events rendering using an acoustic-data stream based on structured audio representation. This article mainly describes sinusoidal and envelope-modulation modeling for intelligible speech modification and reverberation signals rendering. The ...

Introduction: Overview: A training program, under the lead of Professor Jeremy Loebach, was previously developed to help new adult cochlear implant users learn to hear. Users have taken part in a long term training paradigm that has had them identify speech sounds (phonemes, words, sentences), speakers, and environmental sounds. Stimuli for the cochlear implant users have been obtained from mul...

This paper shows how it is possible to count languages vs. dialects if, for every pair of varieties, we are given whether they are mutually intelligible or not. The method is to divide the varieties into a minimum number of internally mutually intelligible groups. In terms of graphs (as in discrete mathematics), the method is even easier understood as: applying graph-coloring to a graph over va...

This paper describes experiments in training HMM-based text-to-speech (TTS) voices on data collected for Automatic Speech Recognition (ASR) training. We compare a number of filtering techniques designed to identify the best utterances from a noisy, multi-speaker corpus for training voices, to exclude speech containing noise and to include speech close in nature to more traditionally-collected T...

Text-to-speech (TTS) synthesis systems have grown popularity due to their diverse practical usability. While most of the technologies developed aims to meet requirements in laboratory environment, the practical appliance is not limited to a specific environment. This work aims towards improving intelligibility of synthesized speech to make it deployable in realism. Based on the comparison of Lo...

This paper describes modification of a TTS system for improving the intelligibility of speech in various noise conditions. First, the GlottHMM vocoder is used for training a voice with modal speech data. The vocoder and voice parameters are then modified to mimic the properties of Lombard effect based on a small amount of Lombard speech from the same speaker. More specifically, the durations ar...

Word Complexity Measure (WCM, Stoel-Gammon, 2010) is a system of phonological assessment for children’s speech productions, a method that focuses on the complexity rather than accuracy. With its flexible parameter program, the assessment can be adjusted to the phonological properties of different languages. In the current study, the WCM was used to assess speech production of three Mandarin-lea...

Previous research has shown that familiar talkers are more intelligible than unfamiliar talkers. In the current study, we tested the source of this familiar talker advantage by manipulating the type of talker information available in the signal. Two groups of listeners were trained to identify the voices of five German-English bilingual talkers; one group learned the voices from German stimuli ...

This paper proposes a new task for artificial intelligence. The image2speech task generates a spoken description of an image. We present baseline experiments in which the neural net used is a sequence-to-sequence model with attention, and the speech synthesizer is clustergen. Speech is generated from four different types of segmentations: two that require a language with known orthography (word...