Raw Speech Signal Research Articles

Vector Quantization Approach for Speaker Recognition using MFCC and Inverted MFCC

Front-end or feature extractor is the first component in an automatic speaker recognition system. Feature extraction transforms the raw speech signal into a compact but effective representation that is more stable and discriminative than the original signal. Since the front-end is the first component in the chain, the quality of the later components (speaker modeling and pattern matching) is strongly determined by the quality of the front-end. In other words, classification can be at most as accurate as the features. Over the years, MelFrequency Cepstral Coefficients (MFCC) modeled on the human auditory system has been used as a standard acoustic feature set for speech related applications. In this paper it has been shown that the inverted Mel-Frequency Cepstral Coefficients is one of the performance enhancement parameters for speaker recognition, which contains high frequency region complementary information in it. This paper introduces the Gaussian shaped filter (GF) while calculation MFCC and inverted MFCC in place of traditional triangular shaped bins. The main idea is to introduce a higher amount of correlation between subband outputs. The performance of both MFCC and inverted MFCC improve with GF over traditional triangular filter (TF) based implementation, individually as well as in combination. In this study the Vector Quantization (VQ) feature matching technique was used, due to high accuracy and its simplicity. The proposed investigation achieved 98.57% of efficiency with a very short test voice sample 2 seconds.

Switching Linear Dynamical Systems for Noise Robust Speech Recognition

Real world applications such as hands-free dialling in cars may have to deal with potentially very noisy environments. Existing state-of-the-art solutions to this problem use feature-based HMMs, with a preprocessing stage to clean the noisy signal. However, the effect that raw signal noise has on the induced HMM features is poorly understood, and limits the performance of the HMM system. An alternative to feature-based HMMs is to model the raw signal, which has the potential advantage that including an explicit noise model is straightforward. Here we jointly model the dynamics of both the raw speech signal and the noise, using a switching linear dynamical system (SLDS). The new model was tested on isolated digit utterances corrupted by Gaussian noise. Contrary to the autoregressive HMM and its derivatives, which provides a model of uncorrupted raw speech, the SLDS is comparatively noise robust and also significantly outperforms a state-of-the-art feature-based HMM. The computational complexity of the SLDS scales exponentially with the length of the time series. To counter this we use expectation correction which provides a stable and accurate linear-time approximation for this important class of models, aiding their further application in acoustic modeling.

Pseudo Pitch Synchronous Analysis of Speech With Applications to Speaker Recognition

The fine spectral structure related to pitch information is conveyed in Mel cepstral features, with variations in pitch causing variations in the features. For speaker recognition systems, this phenomenon, known as “pitch mismatch” between training and testing, can increase error rates. Likewise, pitch-related variability may potentially increase error rates in speech recognition systems for languages such as English in which pitch does not carry phonetic information. In addition, for both speech recognition and speaker recognition systems, the parsing of the raw speech signal into frames is traditionally performed using a constant frame size and a constant frame offset, without aligning the frames to the natural pitch cycles. As a result the power spectral estimation that is done as part of the Mel cepstral computation may include artifacts. Pitch synchronous methods have addressed this problem in the past, at the expense of adding some complexity by using a variable frame size and/or offset. This paper introduces Pseudo Pitch Synchronous (PPS) signal processing procedures that attempt to align each individual frame to its natural cycle and avoid truncation of pitch cycles while still using constant frame size and frame offset, in an effort to address the above problems. Text independent speaker recognition experiments performed on NIST speaker recognition tasks demonstrate a performance improvement when the scores produced by systems using PPS are fused with traditional speaker recognition scores. In addition, a better distribution of errors across trials may be obtained for similar error rates, and some insight regarding of role of the fundamental frequency in speaker recognition is revealed. Speech recognition experiments run on the Aurora-2 noisy digits task also show improved robustness and better accuracy for extremely low signal-to-noise ratio (SNR) data.

Automatic gender identification

In this paper, a new automatic gender identification method is proposed as a part of an Automatic Speaker Recognition (ASR) system. The short time raw speech signal (180–450 ms) was filtered by the nine-order Butterworth low pass filter and decomposed to different frequency bands by the wavelet filter bank analyzer. The energy of the 120 sub-bands was used as a feature vector and applied to a standard classifier. This classifier was trained by the gradient descent method with 1594 utterances spoken by various males and females. The system was tested with different 2542 utterances giving 99.2% correct classification rate. The high performance and simplicity of implementation are the characteristics of this system in comparison to the other methods. [Work supported by DARPA.]

Real-time pitch extraction of voiced speech

This paper describes a novel speech analysis application which was implemented using a Motorola M68HC11 microcontroller system. This microcontroller-based platform was designed to function as a pitch extractor for voiced speech in real time. In this context, pitch extraction is the identification of individual pitch periods, or glottal cycles, from a raw speech waveform. The system implements a new pitch determination algorithm (PDA) that is based on a progressing wave model of speech generation. The PDA was developed specifically to operate in real-time and to maintain phase characteristics with the raw speech signal. As one possible application, the pitch extractor was incorporated into a dual processor system designed to function as a Musical Instrument Digital Interface (MIDI)-compatible controller.