Results 41 to 50 of about 623,333 (376)

A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS [PDF]

arXiv, 2022
The generative adversarial network (GAN) has shown its outstanding capability in improving Non-Autoregressive TTS (NAR-TTS) by adversarially training it with an extra model that discriminates between the real and the generated speech. To maximize the benefits of GAN, it is crucial to find a powerful discriminator that can capture rich distinguishable ...
arxiv  

Speech recognition in individuals with sensorineural hearing loss

Brazilian Journal of Otorhinolaryngology
INTRODUCTION: Hearing loss can negatively influence the communication performance of individuals, who should be evaluated with suitable material and in situations of listening close to those found in everyday life.
Adriana Neves de Andrade, Maria Cecilia Martinelli Iorio, Daniela Gil   +2 more
doaj   +1 more source

Text-to-Speech Pipeline for Swiss German -- A comparison [PDF]

arXiv, 2023
In this work, we studied the synthesis of Swiss German speech using different Text-to-Speech (TTS) models. We evaluated the TTS models on three corpora, and we found, that VITS models performed best, hence, using them for further testing. We also introduce a new method to evaluate TTS models by letting the discriminator of a trained vocoder GAN model ...
arxiv  

Auditory Processing in Children with Specific Language Impairments: Are there Deficits in Frequency Discrimination, Temporal Auditory Processing or General Auditory Processing? [PDF]

, 2009
Background/Aims: Specific language impairment (SLI) is believed to be associated with nonverbal auditory (NVA) deficits. It remains unclear, however, whether children with SLI show deficits in auditory time processing, time processing in general ...
Massinger, Claudia, Nickisch, Andreas
core   +1 more source

Self-Supervised Speech Representations Preserve Speech Characteristics while Anonymizing Voices [PDF]

arXiv, 2022
Collecting speech data is an important step in training speech recognition systems and other speech-based machine learning models. However, the issue of privacy protection is an increasing concern that must be addressed. The current study investigates the use of voice conversion as a method for anonymizing voices.
arxiv  

Resultados na percepção de fala após conversão do Spectra® para Freedom® Result on speech perception after conversion from Spectra® to Freedom®

Brazilian Journal of Otorhinolaryngology, 2012
As novas tecnologias do processador Freedom® foram criadas para proporcionar melhorias no processamento do som acústico de entrada, não apenas para novos usuários, como para gerações anteriores de implante coclear. OBJETIVO: Identificar a contribuição da
Ana Tereza de Matos Magalhães, Maria Valéria Schmidt Goffi-Gomez, Ana Cristina Hoshino, Robinson Koji Tsuji, Ricardo Ferreira Bento, Rubens Brito   +5 more
doaj   +1 more source

Design and Development of a Spanish Hearing Test for Speech in Noise (PAHRE)

Audiology Research, 2022
Background: There are few hearing tests in Spanish that assess speech discrimination in noise in the adult population that take into account the Lombard effect. This study presents the design and development of a Spanish hearing test for speech in noise (
Marlene Rodríguez-Ferreiro, Montserrat Durán-Bouza, Victoria Marrero-Aguiar   +2 more
doaj   +1 more source

Identifying Source Speakers for Voice Conversion based Spoofing Attacks on Speaker Verification Systems [PDF]

arXiv, 2022
An automatic speaker verification system aims to verify the speaker identity of a speech signal. However, a voice conversion system could manipulate a person's speech signal to make it sound like another speaker's voice and deceive the speaker verification system.
arxiv  

Cognitive and linguistic sources of variance in 2-year-olds’ speech-sound discrimination: a preliminary investigation.

Journal of Speech, Language and Hearing Research, 2014
PURPOSE This preliminary investigation explored potential cognitive and linguistic sources of variance in 2-year-olds’ speech-sound discrimination by using the toddler change/ no-change procedure and examined whether modifications would result in a ...
Kaylah Lalonde, R. Holt
semanticscholar   +1 more source

Cellular liquid biopsy provides unique chances for disease monitoring, preclinical model generation and therapy adjustment in rare salivary gland cancer patients

Molecular Oncology, EarlyView.
We quantified and cultured circulating tumor cells (CTCs) of 62 patients with various cancer types and generated CTC‐derived tumoroid models from two salivary gland cancer patients. Cellular liquid biopsy‐derived information enabled molecular genetic assessment of systemic disease heterogeneity and functional testing for therapy selection in both ...
Nataša Stojanović Gužvić, Florian Lüke, Steffi Treitschke, Andrea Coluccio, Martin Hoffmann, Giancarlo Feliciello, Adithi Ravikumar Varadarajan, Xin Lu, Kathrin Weidele, Catherine Botteron, Silvia Materna–Reichelt, Felix Keil, Katja Evert, Florian Weber, Thomas Schamberger, Michael Althammer, Jirka Grosse, Dirk Hellwig, Christian Schulz, Stephan Seitz, Peter Ugocsai, Anke Schlenska‐Lange, Roman Mayr, Ulrich Kaiser, Wolfgang Dietmaier, Bernhard Polzer, Jens Warfsmann, Kamran Honarnejad, Tobias Pukrop, Daniel Heudobler, Christoph A. Klein, Christian Werno   +31 more
wiley   +1 more source