On the issues of intra-speaker variability and realism in speech, speaker, and language recognition tasks

JHL Hansen, H Bořil - Speech Communication, 2018 - Elsevier
Recent years have witnessed notable advancements in the areas of speech, speaker and
language/dialect recognition. However, many of the emerging scientific principles appear to …

Physical task stress and speaker variability in voice quality

KW Godin, JHL Hansen - EURASIP Journal on Audio, Speech, and Music …, 2015 - Springer
The presence of physical task stress induces changes in the speech production system
which in turn produces changes in speaking behavior. This results in measurable acoustic …

Speech variability: A cross-language study on acoustic variations of speaking versus untrained singing

JHL Hansen, M Bokshi… - The Journal of the …, 2020 - pmc.ncbi.nlm.nih.gov
Speech production variability introduces significant challenges for existing speech
technologies such as speaker identification (SID), speaker diarization, speech recognition …

Genome to phenome: a systems biology approach to PTSD using an animal model

N Chakraborty, J Meyerhoff, M Jett… - … : Methods and Protocols, 2017 - Springer
Post-traumatic stress disorder (PTSD) is a debilitating illness that imposes significant
emotional and financial burdens on military families. The understanding of PTSD etiology …

I-vector based physical task stress detection with different fusion strategies

C Zhang, G Liu, C Yu, JHL Hansen - 2015 - utd-ir.tdl.org
It is common for subjects to produce speech while performing a physical task where speech
technology may be used. Variabilities are introduced to speech since physical task can …

GAN-based augmentation for gender classification from speech spectrograms

H Bořil, S Horn - … conference on electrical, computer and energy …, 2022 - ieeexplore.ieee.org
The focus of this study is on gender classification from speech signals produced by adults.
Automatic estimation of gender has a broad variety of applications ranging from forensics …

GlitchOS: An Open Source Virtual Assistant

W Husen, H Bořil, M Roopaei - 2024 IEEE 14th Annual …, 2024 - ieeexplore.ieee.org
This paper presents the GlitchOS, an open-source virtual assistant project with a focus on
privacy. It has the same feature set as other typical virtual assistants but runs completely on …

[PDF][PDF] Engineering analysis and recognition of Nigerian English: an insight into low resource languages

SAY Amuda, H Boril, A Sangwan… - … on Machine Learning …, 2014 - utdallas.edu
ABSTRACT A comparative analysis between Nigerian English (NE) and American English
(AE) is presented in this article. The study is aimed at highlighting differences in the speech …

Identifying tense arousal in speech using phase based features

I Guoth, M Rusko, M Ritomský, M Trnka… - Proceedings of Meetings …, 2017 - pubs.aip.org
The scientific field that focuses on the emotion recognition from speech is called speech
emotion recognition (SER). Methods and techniques from SER have been incorporated in …

[PDF][PDF] Robustness in Speech, Speaker, and Language Recognition:" You've Got to Know Your Limitations".

JHL Hansen, H Boril - INTERSPEECH, 2016 - researchgate.net
In the field of speech, speaker and language recognition, significant gains have and are
being made with new machine learning strategies along with the availability of new and …