Speaker Verification Using A Novel Set of Dynamic Features

Nosratighods, Mohaddeseh; Ambikairajah, Eliathamby; Epps, Julien

doi:10.1109/icpr.2006.1071

Cited by 6 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given that the speech signal has been sliced into M frames, and each frame contains N samples, we can conduct a frame based on noisy speech model from (8) Where y(m,n) denotes the noisy speech signal, x(m,n) denotes the clean speech signal, h(m,n) represents the convolutional noise, and w(m,n) is the additive noise. Hereon, we not only assume that the additive noise is stationary and is uncorrelated with the speech, but also asswne the power spectrum of the convolutional noise is stationary or changes considerably slow.…”

Section: IImentioning

confidence: 99%

“…As we all know, Mel-scale frequency cepstrum coefficients (MFCCs) curr ently are commonly used features in speaker recognition systems, Furthermore, dynamic cepstral features such as delta and delta-delta cepstra have been shown to play an essential role in capturing the transitional characteristics of the speech signal. So, LlMFCC, Ll 2 MFCC [7], and other related features such as delta cepstral energy (DCE) [8] and delta-delta cepstral energy (DDCE) have also been introduced into the speaker recognition systems. Since MFCC values are not very robust in the presence of noise, researchers propose various modifications to the basic MFCC to improve robustness.…”

Section: Introducrionmentioning

confidence: 99%

See 1 more Smart Citation

Modified MFCCs for robust speaker recognition

Wang

Pan

2010

2010 IEEE International Conference on Intelligent Computing and Intelligent Systems

View full text Add to dashboard Cite

Mel-scale frequency cepstrum coefficienls (MFCCs) are commonly used katues in speaker recognition systems, but MFCC values are not very robust in the presence of noise. thus, the modified MFCCs (named as SMN-CMN MFCC) based on the general noisy speech model is proposed in this paper, which uses spectrum mean normalization (SMN) to suppress the additive noise, and uses cepstral mean normalization (CMN) to remove the effect of convolutional noise. Theoretical analyses show that the combination of SMN and CMN can inhibit additive and convolutional noise at the same time. To verify the performance of the SMN-CMN MFCC, \\e have conducted some speaker recognition tesls. With the same convolutional noise component, the additive white noise experimenls and the additive factory noise experimenls show that SMN-CMN-MFCC provides 10.5% and 9.6% relative improvement than the conventional MFCC and AMFCC features, respectively.

show abstract

Section: IImentioning

confidence: 99%

Section: Introducrionmentioning

confidence: 99%

Modified MFCCs for robust speaker recognition

Wang

Pan

2010

2010 IEEE International Conference on Intelligent Computing and Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…coefficients [2,9], octave-based spectral contrast (OSC) [3,4], etc. Generally, the transitional information between short-term features of two neighboring frames, including delta and delta-delta values, have been proven useful in speech recognition system [10,11].…”

Section: Introductionmentioning

confidence: 99%

Fusion of Static and Transitional Information of Cepstral and Spectral Features for Music Genre Classification

Lee

Shih

et al. 2008

2008 IEEE Asia-Pacific Services Computing Conference

View full text Add to dashboard Cite

show abstract

“…In [Kumar et al, 2011], it is shown that the addition of delta-cepstral features to the static 13-dimensional MFCC features improves speech recognition accuracy, and a further (smaller) improvement is provided by the addition of double-delta cepstral. It is also reported in [Nosratighods et al, 2006] that the short-term dynamic features such as delta and delta-delta coefficients can be used to improve speech and speaker verification system by modelling the short-term transitional information in the speech.…”

Section: Dynamic Featuresmentioning

confidence: 99%

Discriminative features for GMM and i-vector based speaker diarization

Zewoudie

View full text Add to dashboard Cite

Speaker diarization has received several research attentions over the last decade. Among the different domains of speaker diarization, diarization in meeting domain is the most challenging one. It usually contains spontaneous speech and is, for example, susceptible to reverberation. The appropriate selection of speech features is one of the factors that affect the performance of speaker diarization systems. Mel Frequency Cepstral Coefficients (MFCC) are the most widely used short-term speech features in speaker diarization. Other factors that affect the performance of speaker diarization systems are the techniques employed to perform both speaker segmentation and speaker clustering. In this thesis, we have proposed the use of jitter and shimmer long-term voice-quality features both for Gaussian Mixture Modeling (GMM) and i-vector based speaker diarization systems. The voice-quality features are used together with the state-of-the-art short-term cepstral and long-term speech ones. The long-term features consist of prosody and Glottal-to-Noise excitation ratio (GNE) descriptors. Firstly, the voice-quality, prosodic and GNE features are stacked in the same feature vector. Then, they are fused with cepstral coefficients at the score likelihood level both for the proposed Gaussian Mixture Modeling (GMM) and i-vector based speaker diarization systems. For the proposed GMM based speaker diarization system, independent HMM models are estimated from the short-term and long-term speech feature sets. The fusion of the short-term descriptors with the long-term ones in speaker segmentation is carried out by linearly weighting the log-likelihood scores of Viterbi decoding. In the case of speaker clustering, the fusion of the short-term cepstral features with the long-term ones is carried out by linearly fusing the Bayesian Information Criterion (BIC) scores corresponding to these feature sets. For the proposed i-vector based speaker diarization system, the speaker segmentation is carried out exactly the same as in the previously mentioned GMM based speaker diarization system. However, the speaker clustering technique is based on the recently introduced factor analysis paradigm. Two set of i-vectors are extracted from the speaker segmentation hypothesis. Whilst the first i-vector is extracted from short-term cepstral features, the second one is extracted from the voice quality, prosody and GNE descriptors. Then, the cosine-distance and Probabilistic Linear Discriminant Analysis (PLDA) scores of i-vectors are linearly weighted to obtain a fused similarity score. Finally, the fused score is used as speaker clustering distance. We have also proposed the use of delta dynamic features for speaker clustering. The motivation for using deltas in clustering is that delta dynamic features capture the transitional characteristics of the speech signal which contain speaker specific information. This information is not captured by the static cepstral coefficients. The delta features are used together with the short-term static cepstral coefficients and long-term speech features (i.e., voice-quality, prosody and GNE) both for GMM and i-vector based speaker diarization systems. The experiments have been carried out on Augmented Multi-party Interaction (AMI) meeting corpus. The experimental results show that the use of voice-quality, prosody, GNE and delta dynamic features improve the performance of both GMM and i-vector based speaker diarization systems. La diarización del altavoz ha recibido varias atenciones de investigación durante la última década. Entre los diferentes dominios de la diarización del hablante, la diarización en el dominio del encuentro es la más difícil. Normalmente contiene habla espontánea y, por ejemplo, es susceptible de reverberación. La selección apropiada de las características del habla es uno de los factores que afectan el rendimiento de los sistemas de diarización de los altavoces. Los Coeficientes Cepstral de Frecuencia Mel (MFCC) son las características de habla de corto plazo más utilizadas en la diarización de los altavoces. Otros factores que afectan el rendimiento de los sistemas de diarización del altavoz son las técnicas empleadas para realizar tanto la segmentación del altavoz como el agrupamiento de altavoces. En esta tesis, hemos propuesto el uso de jitter y shimmer características de calidad de voz a largo plazo tanto para GMM y i-vector basada en sistemas de diarización de altavoces. Las características de calidad de voz se utilizan junto con el estado de la técnica a corto plazo cepstral y de larga duración de habla. Las características a largo plazo consisten en la prosodia y los descriptores de relación de excitación Glottal-a-Ruido (GNE). En primer lugar, las características de calidad de voz, prosódica y GNE se apilan en el mismo vector de características. A continuación, se fusionan con coeficientes cepstrales en el nivel de verosimilitud de puntajes tanto para los sistemas de diarización de altavoces basados ¿¿en el modelo Gaussian Mixture Modeling (GMM) como en los sistemas basados ¿¿en i-vector. . Para el sistema de diarización de altavoces basado en GMM propuesto, se calculan modelos HMM independientes a partir de cada conjunto de características. En la segmentación de los altavoces, la fusión de los descriptores a corto plazo con los de largo plazo se lleva a cabo mediante la ponderación lineal de las puntuaciones log-probabilidad de decodificación Viterbi. En la agrupación de altavoces, la fusión de las características cepstrales a corto plazo con las de largo plazo se lleva a cabo mediante la fusión lineal de las puntuaciones Bayesian Information Criterion (BIC) correspondientes a estos conjuntos de características. Para el sistema de diarización de altavoces basado en un vector i, la fusión de características se realiza exactamente igual a la del sistema basado en GMM antes mencionado. Sin embargo, la técnica de agrupación de altavoces se basa en el paradigma de análisis de factores recientemente introducido. Dos conjuntos de i-vectores se extraen de la hipótesis de segmentación de altavoz. Mientras que el primer vector i se extrae de características espectrales a corto plazo, el segundo se extrae de los descriptores de calidad de voz apilados, prosódicos y GNE. A continuación, las puntuaciones de coseno-distancia y Probabilistic Linear Discriminant Analysis (PLDA) entre i-vectores se ponderan linealmente para obtener una puntuación de similitud fundida. Finalmente, la puntuación fusionada se utiliza como distancia de agrupación de altavoces. También hemos propuesto el uso de características dinámicas delta para la agrupación de locutores. La motivación para el uso de deltas en la agrupación es que las características dinámicas delta capturan las características de transición de la señal de voz que contienen información específica del locutor. Esta información no es capturada por los coeficientes cepstrales estáticos. Las características delta se usan junto con los coeficientes cepstrales estáticos a corto plazo y las características de voz a largo plazo (es decir, calidad de voz, prosodia y GNE) tanto para sistemas de diarización de altavoces basados en GMM como en sistemas i-vector. Los resultados experimentales sobre AMI muestran que el uso de calidad vocal, prosódica, GNE y dinámicas delta mejoran el rendimiento de los sistemas de diarización de altavoces basados en GMM e i-vector.

show abstract

Speaker Verification Using A Novel Set of Dynamic Features

Cited by 6 publications

References 5 publications

Modified MFCCs for robust speaker recognition

Modified MFCCs for robust speaker recognition

Fusion of Static and Transitional Information of Cepstral and Spectral Features for Music Genre Classification

Discriminative features for GMM and i-vector based speaker diarization

Contact Info

Product

Resources

About