Fundamental Frequency Information for Speech Recognition via Bimodal Stimulation

2014 ◽  
Vol 35 (1) ◽  
pp. 97-109 ◽  
Author(s):  
Talma Shpak ◽  
Tova Most ◽  
Michal Luntz
Keyword(s):  
Speech Recognition ◽  
Fundamental Frequency ◽  
Bimodal Stimulation ◽  
Frequency Information

Saliency of Vowel Features in Neural Responses of Cochlear Implant Users

2018 ◽  
Vol 49 (6) ◽  
pp. 388-397
Author(s):  
François Prévost ◽  
Alexandre Lehmann
Keyword(s):  
Speech Recognition ◽  
Cochlear Implant ◽  
Fundamental Frequency ◽  
Mismatch Negativity ◽  
Free Field ◽  
Event Related Potentials ◽  
Oddball Paradigm ◽  
Aural Rehabilitation ◽  
Spectral Components ◽  
Related Potentials

Cochlear implants restore hearing in deaf individuals, but speech perception remains challenging. Poor discrimination of spectral components is thought to account for limitations of speech recognition in cochlear implant users. We investigated how combined variations of spectral components along two orthogonal dimensions can maximize neural discrimination between two vowels, as measured by mismatch negativity. Adult cochlear implant users and matched normal-hearing listeners underwent electroencephalographic event-related potentials recordings in an optimum-1 oddball paradigm. A standard /a/ vowel was delivered in an acoustic free field along with stimuli having a deviant fundamental frequency (+3 and +6 semitones), a deviant first formant making it a /i/ vowel or combined deviant fundamental frequency and first formant (+3 and +6 semitones /i/ vowels). Speech recognition was assessed with a word repetition task. An analysis of variance between both amplitude and latency of mismatch negativity elicited by each deviant vowel was performed. The strength of correlations between these parameters of mismatch negativity and speech recognition as well as participants’ age was assessed. Amplitude of mismatch negativity was weaker in cochlear implant users but was maximized by variations of vowels’ first formant. Latency of mismatch negativity was later in cochlear implant users and was particularly extended by variations of the fundamental frequency. Speech recognition correlated with parameters of mismatch negativity elicited by the specific variation of the first formant. This nonlinear effect of acoustic parameters on neural discrimination of vowels has implications for implant processor programming and aural rehabilitation.

scholarly journals The effect of target/masker fundamental frequency contour similarity on masked-speech recognition

2019 ◽  
Vol 146 (2) ◽  
pp. 1065-1076 ◽  
Author(s):  
Lauren Calandruccio ◽  
Peter A. Wasiuk ◽  
Emily Buss ◽  
Lori J. Leibold ◽  
Jessica Kong ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Fundamental Frequency

scholarly journals Estimation and tracking of fundamental, 2nd and 3d harmonic frequencies for spectrogram normalization in speech recognition

2012 ◽  
Vol 60 (1) ◽  
pp. 71-81
Author(s):  
K. Fujimoto ◽  
N. Hamada ◽  
W. Kasprzak
Keyword(s):  
Speech Recognition ◽  
Fundamental Frequency ◽  
Likelihood Function ◽  
Estimation Method ◽  
Recursive Estimation ◽  
Accurate Estimation ◽  
Harmonic Frequencies ◽  
Music Signal ◽  
Speech Features ◽  
Normalization Scheme

Estimation and tracking of fundamental, 2nd and 3d harmonic frequencies for spectrogram normalization in speech recognitionA stable and accurate estimation of the fundamental frequency (pitch,F0) is an important requirement in speech and music signal analysis, in tasks like automatic speech recognition and extraction of target signal in noisy environment. In this paper, we propose a pitch-related spectrogram normalization scheme to improve the speaker - independency of standard speech features. A very accurate estimation of the fundamental frequency is a must. Hence, we develop a non-parametric recursive estimation method ofF0 and its 2nd and 3d harmonic frequencies in noisy circumstances. The proposed method is different from typical Kalman and particle filter methods in the way that no particular sum of sinusoidal model is used. Also we tend to estimate F0 and its lower harmonics by using novel likelihood function. Through experiments under various noise levels, the proposed method is proved to be more accurate than other conventional methods. The spectrogram normalization scheme makes a mapping of real harmonic structure to a normalized structure. Results obtained for voiced phonemes show an increase in stability of the standard speech features - the average within-phoneme distance of the MFCC features for voiced phonemes can be decreased by several percent.

Sign in / Sign up

Export Citation Format

Share Document