Filters








107 Hits in 8.5 sec

Voice Activation Systems for Embedded Devices: Systematic Literature Review

Aliaksei Kolesau, Dmitrij Šešok
2020 Informatica  
Therefore, most of these devices use a voice activation system, whose task is to find the specified in advance word or phrase in the audio stream (for example, Ok, Google) and to activate the voice request  ...  approaches used to assess the models' quality.  ...  For example, responding only to a keyword that was addressed to the system, but not to the same keyword spoken in the conversation (wake-up-word detection) (Këpuska and Klein, 2009; Zhang et al., 2016  ... 
doi:10.15388/20-infor398 fatcat:mrz26mif2zgwdb6r72xsr7ceji

Deep Spoken Keyword Spotting: An Overview

Ivan Lopez-Espejo, Zheng-Hua Tan, John Hansen, Jesper Jensen
2021 IEEE Access  
ladevuni, “On front-end gain invariant modeling for wake word spotting,” [97] X. Ji, M. Yu, J. Chen, J. Zheng, D. Su, and D.  ...  that the resulting word class wake-up word detection, KWS systems will hear other word distribution is unbalanced.  ... 
doi:10.1109/access.2021.3139508 fatcat:i4pfpfxcpretlkbefp7owtxcti

Rhythms of Relation [chapter]

Sumanth Gopinath, Jason Stanyek, Alexander G. Weheliye
2014 The Oxford Handbook of Mobile Music Studies, Volume 2  
In other words, black musical formations relish the synthetic artificiality of cell phones and other mobile gadgets as much as making these a vital component of the performed body.  ...  the general co-dependence of mobiles and music without silencing the breaks that separate these "epochs. " Finally, I gloss a visual example that stages overlooked dimensions of mobile technologies so  ...  Thus, Monica's particular staging of the word "blackberry" relies on its cultural meanings (mobile device and attendant practices) at the same time as it recodes this linguistic unit as a sonic emoticon  ... 
doi:10.1093/oxfordhb/9780199913657.013.014 fatcat:vykyydvwxfclvhfsh4ycneip2q

Techniques and Challenges in Speech Synthesis [article]

David Ferris
2017 arXiv   pre-print
CMUdict was used to determine the pronunciation of known words. A system for smoothing the transitions between diphone recordings was designed and implemented.  ...  This approach was used to add correct lexical stress to vowels within words.  ...  model uses likelihoods based on two prior values.  ... 
arXiv:1709.07552v1 fatcat:o75yc226ubanppunnqy37jhdua

Speaker comfort and increase of voice level in lecture rooms

Jonas Brunskog, Anders C. Gade, Gaspar Payà Bellester, Lilian Reig Calbo
2008 Journal of the Acoustical Society of America  
Where the flap allophone of "t" and "d" is expected in American English, one frequently sees an approximant-like or even vocalic pattern, rather than a clear flap.  ...  The current work identifies acoustic characteristics of reduced 'flaps' and presents phonetic identification data for continua that manipulate these characteristics.  ...  In virtual auditory environments, a spatialized sound source is typically simulated in two stages: first a ЉdryЉ monophonic signal is recorded or synthesized, and then spatial attributes ͑directivity,  ... 
doi:10.1121/1.2934367 fatcat:xr6gp4ldo5bylnxytx2iumrdmi

Fine‐structure processing, frequency selectivity and speech perception in hearing‐impaired listeners

Olaf Strelcyk, Torsten Dau
2008 Journal of the Acoustical Society of America  
Where the flap allophone of "t" and "d" is expected in American English, one frequently sees an approximant-like or even vocalic pattern, rather than a clear flap.  ...  The current work identifies acoustic characteristics of reduced 'flaps' and presents phonetic identification data for continua that manipulate these characteristics.  ...  In virtual auditory environments, a spatialized sound source is typically simulated in two stages: first a ЉdryЉ monophonic signal is recorded or synthesized, and then spatial attributes ͑directivity,  ... 
doi:10.1121/1.2935148 fatcat:nqyyia5pubamnhqgonegghrudm

A binaural advantage in the subjective modulation transfer function with simple impulse responses

Eric R. Thompson, Torsten Dau
2008 Journal of the Acoustical Society of America  
The two-medium nonlinear theory of aerodynamic sound, based on the original decomposition of each flow variable into two components, for unsteady background flow and for acoustic field, has been created  ...  Each mispronounced word could be ЉreconstructedЉ to either of two familiar Danish words.  ...  It is based on a model for received signals, accounting for the Doppler-shifted frequency.  ... 
doi:10.1121/1.2933699 fatcat:4nc5pg4ysbhgrjcatwhr7fh77q

On determination of microphone response and other parameters by a hybrid experimental and numerical method

Salvador Barrera‐Figueroa, Finn Jacobsen, Knud Rasmussen
2008 Journal of the Acoustical Society of America  
The two-medium nonlinear theory of aerodynamic sound, based on the original decomposition of each flow variable into two components, for unsteady background flow and for acoustic field, has been created  ...  Each mispronounced word could be ЉreconstructedЉ to either of two familiar Danish words.  ...  It is based on a model for received signals, accounting for the Doppler-shifted frequency.  ... 
doi:10.1121/1.2933455 fatcat:gl6kkwih6rbkriigc7g6ghdlnq

The importance of bass clarity in pop and rock venues

Niels W. Adelman‐Larsen, Eric R. Thompson
2008 Journal of the Acoustical Society of America  
The two-medium nonlinear theory of aerodynamic sound, based on the original decomposition of each flow variable into two components, for unsteady background flow and for acoustic field, has been created  ...  Each mispronounced word could be ЉreconstructedЉ to either of two familiar Danish words.  ...  It is based on a model for received signals, accounting for the Doppler-shifted frequency.  ... 
doi:10.1121/1.2932922 fatcat:fvtlbt6x5vgelp5p67x53qtvgi

Green's-function reaction dynamics: A particle-based approach for simulating biochemical networks in time and space

Jeroen S. van Zon, Pieter Rein ten Wolde
2005 Journal of Chemical Physics  
The two-medium nonlinear theory of aerodynamic sound, based on the original decomposition of each flow variable into two components, for unsteady background flow and for acoustic field, has been created  ...  Each mispronounced word could be ЉreconstructedЉ to either of two familiar Danish words.  ...  In two separate sessions ͑1-2 weeks apart͒, 28 listeners were tested on recognition of noise-vocoded Sentences, Words, and isolated segments ͑Consonants and Vowels͒.  ... 
doi:10.1063/1.2137716 pmid:16392952 fatcat:tyehqewfnzahfju3rxvivugvaa

Nonnative listeners prefer perceptual cues they know from their L1: Dutch listeners use vowel duration less than English listeners for English final /v/‐/f/

Mirjam Broersma
2008 Journal of the Acoustical Society of America  
The two-medium nonlinear theory of aerodynamic sound, based on the original decomposition of each flow variable into two components, for unsteady background flow and for acoustic field, has been created  ...  Each mispronounced word could be ЉreconstructedЉ to either of two familiar Danish words.  ...  In two separate sessions ͑1-2 weeks apart͒, 28 listeners were tested on recognition of noise-vocoded Sentences, Words, and isolated segments ͑Consonants and Vowels͒.  ... 
doi:10.1121/1.2933287 fatcat:gqdetkftz5cmrghkql35figuw4

Relationship between room shape and acoustics of rectangular concert halls

Andrzej K. Klosak, Anders C. Gade
2008 Journal of the Acoustical Society of America  
The two-medium nonlinear theory of aerodynamic sound, based on the original decomposition of each flow variable into two components, for unsteady background flow and for acoustic field, has been created  ...  Each mispronounced word could be ЉreconstructedЉ to either of two familiar Danish words.  ...  It is based on a model for received signals, accounting for the Doppler-shifted frequency.  ... 
doi:10.1121/1.2933354 fatcat:eymbpllxwjcfdbkedeijrtwbwq

The neural bases of normalising for accented speech: A repetition suppression functional magnetic resonance imaging study

Patti Adank, Peter Hagoort
2008 Journal of the Acoustical Society of America  
Where the flap allophone of "t" and "d" is expected in American English, one frequently sees an approximant-like or even vocalic pattern, rather than a clear flap.  ...  The current work identifies acoustic characteristics of reduced 'flaps' and presents phonetic identification data for continua that manipulate these characteristics.  ...  In virtual auditory environments, a spatialized sound source is typically simulated in two stages: first a ЉdryЉ monophonic signal is recorded or synthesized, and then spatial attributes ͑directivity,  ... 
doi:10.1121/1.2934685 fatcat:qqmjcl5gjzcj7kssv2pi6efwti

Voronoi polygons and self-consistent technique used to compute the airflow resistivity of randomly placed fibers in glass wool

Viggo Tarnow
2002 Journal of the Acoustical Society of America  
His theory is based on Euler's solution for two coupled pendulums with the free reed and the air column of the resonator as the two oscillators.  ...  The in-axis response of these devices will be compared. Cross-axis response will be presented for one device.  ...  Progress on the experimental apparatus and theoretical model for the EK transmission case will be reported. ͓Work supported by ONR, Ocean Acoustics.͔ 2:05 2pUW5.  ... 
doi:10.1121/1.4809175 fatcat:jqxtrgkn2fcf3a7vzsp2u56akm

Acoustic source identification in an enclosed space using the inverse phased beam tracing at medium frequencies

Jeong‐Guon Ih, Cheol‐Ho Jeong
2008 Journal of the Acoustical Society of America  
. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making  ...  The two-medium nonlinear theory of aerodynamic sound, based on the original decomposition of each flow variable into two components, for unsteady background flow and for acoustic field, has been created  ...  The use of communication device in background noise.  ... 
doi:10.1121/1.2933749 fatcat:xiro7xkminfl5o3psp2ejziawq
« Previous Showing results 1 — 15 out of 107 results