Improving speech recognition performance by using multi-model approaches

Combined speech enhancement and auditory modelling for robust distributed speech recognition

This paper presents an investigation of robust features for speech recognition in three different noisy environments. The state-of art Mel-frequency cepstral coefficients were extensively explored in additive, convolutive and reverberant environments. These environments have captured the interest of many researches in speech recognition systems. We evaluate robust speech recognition results on the TI-DIGIT database. Significant word error rate reductions were observed in the connected digit recognition experiments. The recognition experiments vindicate the robustness of Mel-frequency cepstral coefficient with dynamic features and cepstral mean normalization in hostile environments, especially additive and reverberant noise

Intra-speaker variations due to perceptually induced stress or emotion adversely affect speech recognition system performance. In this paper, we combine auditory based (Mel frequency cepstral coefficients and linear predictive cepstral coefficients) features and articulatory based (voicedness) features for robust speech recognition. Voicedness features are derived using linear and teager energy operator (TEO) based nonlinear fast Fourier transform (FFT) spectra. Nonlinear properties are analyzed in both the time and frequency domains. In addition, we investigate the sensitivity of all these FFT spectra to stress and observe the performance of individual FFT spectra. The system is tested using stressed speech data from the speech under simulated and actual stress (SUSAS) database. The results show that articulatory based features help to improve the system performance. Furthermore, significant performance improvement has been observed when using the FFT spectrum which is less sensitive to stress

This paper proposes a neural mechanism motivated system to extract noise resistant features for robust speech recognition. We use nonnegative matrix factorization to construct two layers of auditory neurons which captures the essence of speech patterns. The responses of these neurons to speech are further processed to form an auditory neural cepstral coefficient (ANCC) representation for speech recognition. We test the robustness of ANCC feature on a 51-word corpus, with recognizers trained on clean speech in noisy conditions. Compared with MFCC, ANCC shows less performance degradation and achieves satisfactory recognition accuracies in both non-stationary noise and high noise level conditions.

S.5492-5495

Recently, Li et al. proposed a new auditory feature for robust speech recognition in noise environments. The new feature was derived by mimicking closely the function of human auditory process. Several filters were used to model the outer ear, middle ear, and cochlea, and the initial filter parameters and shapes were obtained from crude psychoacoustics results, experience, or experiments. Although one may adjust the feature parameters by hand to get better performance, the resulting feature parameters still may not be optimal in the sense of minimal recognition errors, especially for different tasks. To further improve the auditory feature, in this paper we apply discriminative training to optimize the auditory feature parameters with some guidance from psychoacoustic evidence but otherwise in a data-driven approach so as to minimize the recognition errors. One significant contribution over similar efforts in the past, such as discriminative feature extraction, is that we make no assumption on the parametric form of the auditory filters. Instead, we only require the filters to be smooth and triangular-like as suggested by psychoacoustics research. Our approach is evaluated on the Aurora database and achieves a word error reduction of 19.2%.

Spectral representation of speech is complete when both the Fourier transform magnitude and phase spectra are specified. In conventional speech recognition systems, features are generally derived from the short-time magnitude spectrum. Although the importance of Fourier transform phase in speech perception has been realized, few attempts have been made to extract features from it. This is primarily because the resonances of the speech signal which manifest as transitions in the phase spectrum are completely masked by the wrapping of the phase spectrum. Hence, an alternative to processing the Fourier transform phase, for extracting speech features, is to process the group delay function which can be directly computed from the speech signal. The group delay function has been used in earlier efforts, to extract pitch and formant information from the speech signal. In all these efforts, no attempt was made to extract features from the speech signal and use them for speech recognition applications. This is primarily because the group delay function fails to capture the short-time spectral structure of speech owing to zeros that are close to the unit circle in the z-plane and also due to pitch periodicity effects. In this paper, the group delay function is modified to overcome these effects. Cepstral features are extracted from the modified group delay function and are called the modified group delay feature (MODGDF). The MODGDF is used for three speech recognition tasks namely, speaker, language, and continuous-speech recognition. Based on the results of feature and performance evaluation, the significance of the MODGDF as a new feature for speech recognition is discussed

Speech dynamic features are routinely used in current speech recognition systems in combination with short-term (static) spectral features. Although many existing speech recognition systems do not weight both kinds of features, it seems convenient to use some weighting in order to increase the recognition accuracy of the system. In the cases that this weighting is performed, it is manually tuned or it consists simply in compensating the variances. The aim of this paper is to propose a method to automatically estimate an optimum state-dependent stream weighting in a continuous density hidden Markov model (CDHMM) recognition system by means of a maximum-likelihood based training algorithm. Unlike other works, it is shown that simple constraints on the new weighting parameters permit to apply the maximum-likelihood criterion to this problem. Experimental results in speaker independent digit recognition show an important increase of recognition accuracy.

We describe an audio-visual automatic continuous speech recognition system, which significantly improves speech recognition performance over a wide range of acoustic noise levels, as well as under clean audio conditions. The system utilizes facial animation parameters (FAPs) supported by the MPEG-4 standard for the visual representation of speech. We also describe a robust and automatic algorithm we have developed to extract FAPs from visual data, which does not require hand labeling or extensive training procedures. The principal component analysis (PCA) was performed on the FAPs in order to decrease the dimensionality of the visual feature vectors, and the derived projection weights were used as visual features in the audio-visual automatic speech recognition (ASR) experiments. Both single-stream and multistream hidden Markov models (HMMs) were used to model the ASR system, integrate audio and visual information, and perform a relatively large vocabulary (approximately 1000 words) speech recognition experiments. The experiments performed use clean audio data and audio data corrupted by stationary white Gaussian noise at various SNRs. The proposed system reduces the word error rate (WER) by 20% to 23% relatively to audio-only speech recognition WERs, at various SNRs (0–30 dB) with additive white Gaussian noise, and by 19% relatively to audio-only speech recognition WER under clean audio conditions.

In a study presented at the fall 2010 meeting of the Acoustical Society of America (Zahorian etal., “Time/frequency resolution of acoustic features for automatic speech recognition”), we demonstrated that spectral/temporal evolution features which emphasize temporal aspects of acoustic features, with relatively low spectral resolution, are effective for phonetic recognition in continuous speech. These features are computed using discrete cosine transform coefficients for spectral information from 8 ms frames and discrete cosine series coefficients (DCSCs) for their temporal evolution, over overlapping intervals (blocks) longer than 200 ms. These features are presented as an alternative to mel-frequency cepstral coefficients, and their delta terms, for automatic speech recognition (ASR). In the present work, it is shown that these features are even more effective for ASR, using a non-symmetric time window which is tilted toward the beginning of each block when computing DCSCs. This non-symmetry can be implemented by combining two Gaussian windows with different standard deviations. This work also supports the hypothesis that the left context is somewhat more informative to phonetic identity than is the right context. Experimental results for automatic phone recognition are given for various conditions using the TIMIT and NTIMIT databases.

Exploring joint equalization of spatial-temporal contextual statistics of speech features for robust speech recognition

In this paper, we propose two estimators for the autocorrelation sequence of a periodic signal in additive noise. Both estimators are formulated employing tables which contain all the possible products of sample pairs in a speech signal frame. The first estimator is based on a pitch-synchronous averaging. This estimator is statistically analyzed and we show that the signal-to-noise ratio (SNR) can be increased up to a factor equal to the number of available periods. The second estimator is similar to the former one but it avoids the use of those sample products more likely affected by noise. We prove that, under certain conditions, this estimator can remove the effect of an additive noise in a statistical sense. Both estimators are employed to extract mel frequency cepstral coefficients (MFCCs) as features for robust speech recognition. Although these estimators are initially conceived for voiced speech frames, we extend their application to unvoiced sounds in order to obtain a coherent feature extractor. The experimental results show the superiority of the proposed approach over other MFCC-based front-ends such as the higher-lag autocorrelation spectrum estimation (HASE), which also employs the idea of avoiding those autocorrelation coefficients more likely affected by noise.

In this work, we investigate the joint use of articulatory and acoustic features for automatic speech recognition (ASR) of pathological speech. Despite long-lasting efforts to build speaker- and text-independent ASR systems for people with dysarthria, the performance of state-of-the-art systems is still considerably lower on this type of speech than on normal speech. The most prominent reason for the inferior performance is the high variability in pathological speech that is characterized by the spectrotemporal deviations caused by articulatory impairments due to various etiologies. To cope with this high variation, we propose to use speech representations which utilize articulatory information together with the acoustic properties. A designated acoustic model, namely a fused-feature-map convolutional neural network (fCNN), which performs frequency convolution on acoustic features and time convolution on articulatory features is trained and tested on a Dutch and a Flemish pathological speech corpus. The ASR performance of fCNN-based ASR system using joint features is compared to other neural network architectures such conventional CNNs and time-frequency convolutional networks (TFCNNs) in several training scenarios.

Speech production knowledge has been used to enhance the phonetic representation and the performance of automatic speech recognition (ASR) systems successfully. Representations of speech production make simple explanations for many phenomena observed in speech. These phenomena can not be easily analyzed from either acoustic signal or phonetic transcription alone. One of the most important aspects of speech production knowledge is the use of articulatory knowledge, which describes the smooth and continuous movements in the vocal tract. In this paper, we present a new articulatory model to provide available information for rescoring the speech recognition lattice hypothesis. The articulatory model consists of a feature front-end, which computes a voicing feature based on a spectral harmonics correlation (SHC) function, and a back-end based on the combination of deep neural networks (DNNs) and hidden Markov models (HMMs). The voicing features are incorporated with standard Mel frequency cepstral coefficients (MFCCs) using heteroscedastic linear discriminant analysis (HLDA) to compensate the speech recognition accuracy rates. Moreover, the advantages of two different models are taken into account by the algorithm, which retains deep learning properties of DNNs, while modeling the articulatory context powerfully through HMMs. Mandarin speech recognition experiments show the proposed method achieves significant improvements in speech recognition performance over the system using MFCCs alone.

Current speech recognition systems use mainly amplitude spectrum-based features such as MFFC for acoustic feature parameters, while discarding phase spectral information. The results of perceptual experiments, however, suggested that phase spectral information based on long-term analysis includes certain linguistic information. In this paper, we propose the use of phase features based on long-term analysis for speech recognition. We use two types of parameters: the delta phase parameter as a group delay and analytic group delay features. Isolated word and continuous digit recognition experiments were performed, resulting in a greater than 90% word or digit accuracy for each of the experiments. The experimental results confirmed that a long-term phase spectrum includes sufficient information for recognizing speech. Furthermore, combining likelihoods of MFCC and long-term group delay cepstrum outperformed the baseline MFCC relatively 20% for clean speech. Index Terms: speech recognition, phase information, longterm analysis, group delay