Exemplar-based noise robust automatic speech recognition using modulation spectrogram features

The histogram equalization approach is an efficient feature normalization technique for noise robust automatic speech recognition. However, it suffers from performance degradation when some fundamental conditions are not satisfied in the test environment. To remedy these limitations of the original histogram equalization methods, class-based histogram equalization approach has been proposed. Although this approach showed substantial performance improvement under noise environments, it still suffers from performance degradation due to the overfitting problem when test data are insufficient. To address this issue, the proposed histogram equalization technique employs the Bayesian estimation method in the test cumulative distribution function estimation. It was reported in a previous study conducted on the Aurora-4 task that the proposed approach provided substantial performance gains in speech recognition systems based on the acoustic modeling of the Gaussian mixture model-hidden Markov model. In this work, the proposed approach was examined in speech recognition systems with deep neural network-hidden Markov model (DNN-HMM), the current mainstream speech recognition approach where it also showed meaningful performance improvement over the conventional maximum likelihood estimation-based method. The fusion of the proposed features with the mel-frequency cepstral coefficients provided additional performance gains in DNN-HMM systems, which otherwise suffer from performance degradation in the clean test condition.

As with many approaches to noise robust automatic speech recognition (ASR) the benefits of spectral subtraction tend to diminish as noise levels in the order of 0 dB are approached. Whilst the majority of related work focuses on reducing magnitude errors a number of new approaches addressing the often overlooked, additional sources of error have appeared in the literature in recent years. Relatively lacking in the literature, however, is an empirical assessment which compares the effects of each error when noisy speech is processed by spectral subtraction. Such studies are vital in order to appreciate the potential penalty in performance when sources of error are overlooked. The objective in this paper is to assess, through ASR, the performance penalty associated with each source of error when noisy speech is treated with spectral subtraction. Experimental evidence based on two standard European databases and ASR protocols illustrates that, perhaps contrary to popular belief, for noise levels in the order of 0 dB and below, these often overlooked sources of error can lead to non-negligible degradations in performance. Whilst not a new idea, here the original emphasis is a thorough assessment that empirically highlights both the fundamental limitations and potential benefit of including the full complement of errors in the spectral subtraction model.

In this paper we investigate stereo-based stochastic mapping (SSM) with context for the noise robustness of automatic speech recognition, especially under unseen conditions. Probabilistic PCA (PPCA) is used in the SSM framework to reduce the high dimensionality of the noisy speech features with context and derive an eigen representation in the noisy feature space for the prediction of clean features. To reduce the computational cost in training, an approximation by single-pass re-training is considered for the estimation of joint GMM. We also show that the SSM estimate under the minimum mean square error (MMSE) in a space where low dimensional representation of clean speech and uncorrelated additive noise can be assumed is related to the subspace speech enhancement. Experiments on large vocabulary continuous speech recognition tasks observe gains from the proposed approach under the conditions with seen, unseen and real noise.

This paper proposes a new model for a noise-robust Automatic Speech Recognition (ASR) based on parallel branch Hidden Markov Model (HMM) structure with a novel approach for robust speech recognition. Automatic Speech Recognition applications such as voice command and control, audio indexing, speech-to-speech translation, do not usually work well in noisy environments. In this paper, we present the characteristics of a novel model by exploring vibrocervigraphic and electromyographic ASR methods and some other effective approaches to achieve the best results. By employing the proposed model, we obtain the word error rate, available bandwidths with cutoff frequencies, word recognition rate, etc. This paper includes advanced front-end processing with less computational requirements and a statistical modeling for large-vocabulary myoelectric speech. Therefore parameters estimation of ASR system like Mel-Frequency Cepstral Coefficients (MFCC) are investigated to create the statistically optimized model.

Use of a linear projection (LP) function to transform multiple sets of acoustic models into a single set of acoustic models is proposed for characterizing testing environments for robust automatic speech recognition. The LP function is an extension of the linear regression (LR) function used in maximum likelihood linear regression (MLLR) and maximum a posteriori linear regression (MAPLR) by incorporating local information in the ensemble acoustic space to enhance the environment modeling capacity. To estimate the nuisance parameters of the LP function, we developed maximum likelihood LP (MLLP) and maximum a posteriori LP (MAPLP) and derived a set of integrated prior (IP) densities for MAPLP. The IP densities integrate multiple knowledge sources from the training set, previously seen speech data, current utterance, and a prepared tree structure. We evaluated the proposed MLLP and MAPLP on the Aurora-2 database in an unsupervised model adaptation manner. Experimental results show that the LP function outperforms the LR function with both ML- and MAP-based estimates over different test conditions. Moreover, because the MAP-based estimate can handle over-fittings well, MAPLP has clear improvements over MLLP. Compared to the baseline result, MAPLP provides a significant 10.99% word error rate reduction.

In this paper, we propose the use of deep neural networks to expand conventional methods of statistical feature enhancement based on piecewise linear transformation. Stereo-based piecewise linear compensation for environments (SPLICE), which is a powerful statistical approach for feature enhancement, models the probabilistic distribution of input noisy features as a mixture of Gaussians. However, soft assignment of an input vector to divided regions is sometimes done inadequately and the vector comes to go through inadequate conversion. Especially when conversion has to be linear, the conversion performance will be easily degraded. Feature enhancement using neural networks is another powerful approach which can directly model a non-linear relationship between noisy and clean feature spaces. In this case, however, it tends to suffer from over-fitting problems. In this paper, we attempt to mitigate this problem by reducing the number of model parameters to estimate. Our neural network is trained whose output layer is associated with the states in the clean feature space, not in the noisy feature space. This strategy makes the size of the output layer independent of the kind of a given noisy environment. Firstly, we characterize the distribution of clean features as a Gaussian mixture model and then, by using deep neural networks, estimate discriminatively the state in the clean space that an input noisy feature corresponds to. Experimental evaluations using the Aurora 2 dataset demonstrate that our proposed method has the best performance compared to conventional methods.

Sparse representations have been found to provide high classification accuracy in many fields. Their drawback is the high computational load. In this work, we propose a novel cascaded classifier structure to speed up the decision process while utilizing sparse signal representation. In particular, we apply the cascaded decision process for noise robust automatic speech recognition task. The cascaded decision process is implemented using a feedforward neural network (NN) and time sparse versions of a non-negative matrix factorization (NMF) based sparse classification method of [1]. The recognition accuracy of our cascade is among the three best in the recent CHiME2013 benchmark and obtains six times faster the accuracy of NMF alone as in [1].

Combined speech enhancement and auditory modelling for robust distributed speech recognition

To address the limitations of traditional cepstrum or LPC based front-end processing methods for automatic speech recognition, more elaborate methods based on physiological models of the human auditory system may be used to achieve more robust speech recognition in adverse environments. For this purpose, a modified version of a model of the primary auditory cortex featuring a three dimensional mapping of auditory spectra [Wang and Shamma, IEEE Trans. Speech Audio Process. 3, 382–395 (1995)] is adopted and investigated for its use as an improved front-end processing method. The study is conducted in two ways: first, by relating the model’s redundant representation to traditional spectral representations and showing that the former not only encompasses information provided by the latter, but also reveals more relevant information that makes it superior in describing the identifying features of speech signals; and second, by observing the statistical features of the representation for various classes of sound to show how different identifying features manifest themselves as specific patterns on the cortical map, thereby becoming a place-coded data set on which detection theory could be applied to simulate auditory perception and cognition.

Ambient clinical documentation technology uses automatic speech recognition (ASR) and natural language processing (NLP) to turn patient-clinician conversations into clinical documentation. It is a promising approach to reducing clinician burden and improving documentation quality. However, the performance of current-generation ASR remains inadequately validated. In this study, we investigated the impact of non-lexical conversational sounds (NLCS) on ASR performance. NLCS, such as Mm-hm and Uh-uh, are commonly used to convey important information in clinical conversations, for example, Mm-hm as a "yes" response from the patient to the clinician question "are you allergic to antibiotics?" In this study, we evaluated 2 contemporary ASR engines, Google Speech-to-Text Clinical Conversation ("Google ASR"), and Amazon Transcribe Medical ("Amazon ASR"), both of which have their language models specifically tailored to clinical conversations. The empirical data used were from 36 primary care encounters. We conducted a series of quantitative and qualitative analyses to examine the word error rate (WER) and the potential impact of misrecognized NLCS on the quality of clinical documentation. Out of a total of 135647 spoken words contained in the evaluation data, 3284 (2.4%) were NLCS. Among these NLCS, 76 (0.06% of total words, 2.3% of all NLCS) were used to convey clinically relevant information. The overall WER, of all spoken words, was 11.8% for Google ASR and 12.8% for Amazon ASR. However, both ASR engines demonstrated poor performance in recognizing NLCS: the WERs across frequently used NLCS were 40.8% (Google) and 57.2% (Amazon), respectively; and among the NLCS that conveyed clinically relevant information, 94.7% and 98.7%, respectively. Current ASR solutions are not capable of properly recognizing NLCS, particularly those that convey clinically relevant information. Although the volume of NLCS in our evaluation data was very small (2.4% of the total corpus; and for NLCS that conveyed clinically relevant information: 0.06%), incorrect recognition of them could result in inaccuracies in clinical documentation and introduce new patient safety risks.

In this paper, we propose the use of the multi-frame Gaussian mixture model-based block quantizer for the coding of Mel frequency-warped cepstral coefficient (MFCC) features in distributed speech recognition (DSR) applications. This coding scheme exploits intraframe correlation via the Karhunen-Loeve transform (KLT) and interframe correlation via the joint processing of adjacent frames together with the computational simplicity of scalar quantization. The proposed coder is bit-rate scalable, which means that the bitrate can be adjusted without the need for re-training of the quantizers. Static parameters such as the probability density function (PDF) model and KLT orthogonal matrices are stored at the encoder and decoder and bit allocations are calculated 'on-the-fly' without intensive processing. This coding scheme is evaluated in this paper on the Aurora-2 database in a DSR framework. It is shown that this coding scheme achieves high recognition performance at lower bitrates, with a word error rate (WER) of 2.5% at 800 bps, which is less than 1% degradation from the baseline word recognition accuracy, and graceful degradation down to a WER of 7% at 300 bps.

In this paper, we propose to operate the sub-band division via discrete wavelet transform (DWT) before the process of gain normalization (GN) in producing speech features. In the presented approach, we apply the DWT to decompose the temporal-domain cepstral feature sequence, and then perform the gain normalization on each sub-band feature stream. Finally, the new feature stream is obtained by the inverse DWT of all sub-band streams. Compared with the gain normalization process directly performed on the original full-band stream, the presented approach can deal with the sub-band distortions individually and is expected to be more noise-robust. In the Aurora-2 database and task, this new sub-band GN outperforms the baseline process and the original full-band GN by 65.51% and 18.20% in relative word error reduction.

In this paper, we propose a joint optimal method for automatic speech recognition (ASR) and ideal binary mask (IBM) estimation in transformed into the cepstral domain through a newly derived generalized expectation maximization algorithm. First, cepstral domain missing feature marginalization is established using a linear transformation, after tying the mean and variance of non-existing cepstral coefficients. Second, IBM estimation is formulated using a generalized expectation maximization algorithm directly to optimize the ASR performance. Experimental results show that even in highly non-stationary mismatch condition (dance music as background noise), the proposed method achieves much higher absolute ASR accuracy improvement ranging from 14.69% at 0 dB SNR to 40.10% at 15 dB SNR compared with the conventional noise suppression method.

Code-switching is the frequent alternation between two or more languages within a single utterance and is a widespread phenomenon among bilingual and multilingual speakers. In India, more than 250 million people are estimated to engage in code-switched communication, especially blending English with Hindi (Hinglish), making it one of the largest bilingual populations globally, making challenging for developing accurate and robust Automatic Speech Recognition (ASR) systems. Existing ASR models, typically trained on monolingual corpus, struggle with code-switched input due to a lack of large, balanced, and representative datasets—particularly for diverse age groups. Recent evaluations have shown that ASR models experience a relative increase in Word Error Rate (WER) of 30–50 % when exposed to code-switched speech compared to monolingual input. To address this resource gap, we introduce a benchmark Hinglish speech corpus, HiACC, to improve ASR performance in resource-constrained settings. While several monolingual Hindi and English corpus exist, publicly available code-switched datasets remain scarce, and none till date include children's speech. Our corpus fills this gap by providing the first code-switched Hinglish speech dataset with recordings from both adults and children. It comprises 3,318 audio segments from adult participants and 1,858 segments from children, covering 5.24 hours of read and spontaneous speech. The transcriptions include detailed annotations and code-switching tags to assist in linguistic and computational analysis. The corpus is publicly available at [https://zenodo.org/records/15551669], offering segmented audio and aligned transcripts for open research. We also present baseline ASR experiments, which show that standard models trained on monolingual data underperform by approximately 42 % WER on our test set, highlighting the complexity of the task. To our knowledge, this is the first publicly available resource on code-switched Hinglish speech encompassing both adult and child speakers, designed to catalyse progress in this challenging yet important area of speech recognition.

A common metric for evaluating Automatic Speech Recognition (ASR) is Word Error Rate (WER) which solely takes into account discrepancies at the word-level. Although WER is useful, it is not guaranteed to correlate well with intelligibility or performance on downstream tasks that make use of ASR. Meaningful assess- ment of ASR mistakes becomes even more important in high-stake scenarios such as health-care. I propose 2 general measures to evaluate the quality or severity of mistakes made by ASR systems, one based on sentiment analysis and another based on text embeddings. Both have the potential to overcome the limitations of WER. I evaluate these measures on simulated patient-doctor conversations. Measures of severity based on sentiment ratings and text embeddings correlate with human ratings of severity. Measures based on text embeddings have the capability to predict human severity ratings better than WER. These measures are used in metrics in the overall evaluation of 5 ASR engines alongside WER. Results show that these metrics capture characteristics of ASR errors that WER does not. Furthermore, I train an ASR system using severity as a penalty in the loss function and demonstrate the potential for using severity not only in the evaluation, but in the development of ASR. Advantages and limitations of this methodology are analyzed and discussed.