Subband based classification of speech under stress

نویسندگان

  • Ruhi Sarikaya
  • John N. Gowdy
چکیده

This study proposes a new set of feature parameters based on subband analysis of the speech signal for classi cation of speech under stress. The new speech features are Scale Energy (SE), Autocorrelation-Scale-Energy (ACSE), Subband based cepstral parameters (SC), and Autocorrelation-SC (ACSC). The parameters' ability to capture di erent stress types is compared to widely used Mel-scale cepstrum based representations: Mel-frequency cepstral coe cents (MFCC) and Autocorrelation-Mel-scale (AC-Mel). Next, a feedforward neural network is formulated for speaker-dependent stress classi cation of 10 stress conditions: Angry, Clear, Cond50/70, Fast, Loud, Lombard, Neutral, Question, Slow, and Soft. The classi cation algorithm is evaluated using a previously established stressed speech database (SUSAS)[4]. Subband based features are shown to achieve +7:3% and +9:1% increase in the classi cation rates over the MFCC based parameters for ungrouped and grouped stress closed vocabulary test scenarios respectively. Moreover the average scores across the simulations of new features are +8:6% and +13:6% higher than MFCC based features for the ungrouped and grouped stress test scenarious respectively.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A High-Dimensional Subband Speech Representation and SVM Framework for Robust Speech Recognition

This work proposes a novel support vector machine (SVM) based robust automatic speech recognition (ASR) frontend that operates on an ensemble of the subband components of high-dimensional acoustic waveforms. The key issues of selecting the appropriate SVM kernels for classification in frequency subbands and the combination of individual subband classifiers using ensemble methods are addressed. ...

متن کامل

A New Algorithm for Voice Activity Detection Based on Wavelet Packets (RESEARCH NOTE)

Speech constitutes much of the communicated information; most other perceived audio signals do not carry nearly as much information. Indeed, much of the non-speech signals maybe classified as ‘noise’ in human communication. The process of separating conversational speech and noise is termed voice activity detection (VAD). This paper describes a new approach to VAD which is based on the Wavelet ...

متن کامل

New Adaptive Speech Enhancement System Using a Novel Wavelet Thresholding Technique

A new adaptive speech enhancement system, which utilizes a second-generation wavelet transform (SGWT) decomposition and a novel adaptive subband thresholding technique, is presented. The adaptive thresholding technique is based on accurate estimation of subband segmental signal-to-noise ratio (SegSNR) and voiced/unvoiced classification of the speech. First, the speech signal is segmented and ea...

متن کامل

Stress level detection using double-layer subband filter

Stress level detection is important for human error prevention and health care services. Speech based stress level detection is the most effective as speech data can be obtained in nonintrusive and inexpensive ways. In this paper, we explore the features that use Double-Layered Subband (DLS) filter for detecting stress level from speech. Spectral Centroid Frequency (SCF) and Spectral Centroid A...

متن کامل

Non-negative matrix factorization-based subband decomposition for acoustic source localization

A novel Non-negative Matrix Factorization (NMF) based subband decomposition in frequency-spatial domain for acoustic source localization using a microphone array. The proposed method decomposes source and noise subband and emphasizes source dominant frequency bins for more accurate source representation. By employing NMF, we extract Delay Basis Vectors (DBV) and their subband information in fre...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998