arXiv subjects

Naoya Takahashi

Publications and source records attributed to Naoya Takahashi.

41 records · Page 3Linked to original sources

arXiv2016

Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection

We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due to the lack of a clear sub-word unit. In order to incorporate the long-time frequency structure for AED, we introduce a convolutional neural network (CNN) with a large input field. In contrast to previous works, this enables to train audio event detection end-to-end. Our architecture is inspired by the success of VGGNet and uses small, 3x3 convolutions, but more depth than previous methods in AED. In order to prevent over-fitting and to take full advantage of the modeling capabilities of our network, we further propose a novel data augmentation method to introduce data variation. Experimental results show that our CNN significantly outperforms state of the art methods including Bag of Audio Words (BoAW) and classical CNNs, achieving a 16% absolute improvement.

cs.SD↗

arXiv2016

Noise reduction combining microphone and piezoelectric device

It is often required to extract the sound of an objective instrument played in concert with other instruments. Microphone array is one of the effective ways to enhance a sound from a specific direction. However it is not effective in an echoic room such as concert hall. The pickup microphone attached on the specific musical instrument is often employed to obtain the sound exclusively from other instrumental sounds. The obtained timbre differ from the one we hear at the usual listening position. The purpose of this paper is to propose a new method of sound separation that utilizes the piezoelectric device attached on the body of the instrument. The signal from the attached device has a different spectrum from the sound heard by the audience but has the same frequency components as the instrumental sound. Our idea is to use the device signal as a modifier of the sound focusing filter applied to the microphone sound at the listening position. The proposed method firstly estimates the frequency components of the signal from the piezoelectric device. The frequency characteristics for filtering the microphone sound are changed so that it pass the estimated frequency components. Thus we can extractthe target sound without distortion. The proposed method is a sort of dynamic sparseness approach. It was found that SNR is improved by 8.7dB through the experiments.

cs.SD↗

arXiv2016

Automatic Pronunciation Generation by Utilizing a Semi-supervised Deep Neural Networks

Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft a pronunciation dictionary, pronunciation variations, human mistakes and under-resourced dialects and languages. Here, we propose a data-driven pronunciation estimation and acoustic modeling method which only takes the orthographic transcription to jointly estimate a set of sub-word units and a reliable dictionary. Experimental results show that the proposed method which is based on semi-supervised training of a deep neural network largely outperforms phoneme based continuous speech recognition on the TIMIT dataset.

cs.CL↗

arXiv1998

Probability Density Function of Longitudinal Velocity Increment in Homogeneous Turbulence

Two conditional averages for the longitudinal velocity increment u_r of the simulated turbulence are calculated: h(u_r) is the average of the increment of the longitudinal Laplacian velocity field with u_r fixed, while g(u_r) is the corresponding one of the square of the difference of the gradient of the velocity field. Based on the physical argument, we suggest the formulae for h and g, which are quite satisfactorily fitted to the 512^3 DNS data. The predicted PDF is characterized as (1) the Gaussian distribution for the small amplitudes, (2) the exponential distribution for the large ones, and (3) a prefactor before the exponential function for the intermediate ones.

chao-dyn↗

arXiv1997

Conditional Averages and Probability Density Functions in the Passive Scalar Field

Two conditional averages for the increment Delta(x,x+r) = T(x)-T(x+r) of the scalar field are estimated for DNS data: H(Delta)= and G(Delta)=<|nabla Delta(x,x+r)|^2| Delta(x,x+r)>. The probability density function P(Delta) for Delta(x,x+r) is also calculated. If Delta, P(Delta), H(Delta), and G(Delta) are expressed as theta, P(theta), h(theta), and g(theta) in a dimensionless form, the data analysis has revealed interesting simple relationships between them. These relations may be helpful to construct a turbulence model.

chao-dyn↗