Speech Processing Applications Research Articles

Exploring Hybrid Techniques for Enhanced Pitch Estimation in Speech Processing

aims: 1. To develop a hybrid approach combining the Pitch Estimation Filter (PEF) and Cepstrum Pitch Determination (CPD) methods for pitch detection in audio signals. 2. To conduct comparative analysis with existing pitch detection methodologies, including Normalized Correlation Function (NCF), Pitch Estimation Filter (PEF), Log-Harmonic Summation (LHS), Summation of Residual Harmonics (SRH) and Cepstrum Pitch Determination (CEP), to assess the performance and accuracy of the proposed hybrid approach. 3. To evaluate the effectiveness of the hybrid approach in various real-world applications such as speech recognition and music transcription, using performance metrics including Gross Pitch Error (GPE) and classification accuracy through a K-Nearest Neighbors (KNN) classifier. background: The study discussed the difficulties in assessing pitch detection algorithms in real-world applications, especially when it comes to audio synthesis and music production. Prominent performance metrics and criteria pertinent to pitch tracking in interactive music applications were identified by the authors through comprehensive user studies and surveys with audio engineers and professional musicians. The results demonstrated the need for user-centered design approaches in algorithm development and evaluation by emphasizing the significance of taking user preferences and practical requirements into account when evaluating the effectiveness of pitch detection algorithms. objective: 1. To develop a hybrid approach combining the Pitch Estimation Filter (PEF) and Cepstrum Pitch Determination (CPD) methods for pitch detection in audio signals. 2. To conduct comparative analysis with existing pitch detection methodologies, including Normalized Correlation Function (NCF), Pitch Estimation Filter (PEF), Log-Harmonic Summation (LHS), Summation of Residual Harmonics (SRH) and Cepstrum Pitch Determination (CEP), to assess the performance and accuracy of the proposed hybrid approach. 3. To evaluate the effectiveness of the hybrid approach in various real-world applications such as speech recognition and music transcription, using performance metrics including Gross Pitch Error (GPE) and classification accuracy through a K-Nearest Neighbors (KNN) classifier. method: Proposed PEF+CEP result: Finally, a comparison and analysis of different pitch detection techniques revealed how well they performed in terms of important evaluation metrics like accuracy, specificity, sensitivity, and gross pitch error (GPE). Conventional methods such as Normalized Correlation Function (NCF), Pitch Estimation Filter (PEF), Log-Harmonic Summation (LHS), Summation of Residual Harmonics(SRH) and Cepstrum Pitch Determination (CEP) perform admirably in terms of specificity and accuracy, but they are not very effective in terms of sensitivity and GPE. On the other hand, the suggested hybrid approach, Proposed PEF+CEP, offers a noteworthy enhancement in accuracy, attaining a remarkable 98.8%, in addition to a sensitivity of 99.2%. The hybrid approach exhibits a slightly higher GPE than some traditional methods, but these minor deviations are outweighed by the significant improvements in accuracy and sensitivity that it offers. Furthermore, the Proposed PEF+CEP method is a promising solution for reliable and accurate pitch detection in speech processing applications because it strikes a strong balance between computational efficiency, training time, model size, and convergence rate. The suggested method offers notable improvements in pitch detection accuracy and reliability while addressing the drawbacks of separate approaches by utilizing the advantages of both PEF and CEP techniques. As a result, the suggested PEF+CEP approach stands out as a significant advancement in speech processing, offering enhanced functionality and versatility in a range of real-world settings. conclusion: Finally, a comparison and analysis of different pitch detection techniques revealed how well they performed in terms of important evaluation metrics like accuracy, specificity, sensitivity, and gross pitch error (GPE). Conventional methods such as Normalized Correlation Function (NCF), Pitch Estimation Filter (PEF), Log-Harmonic Summation (LHS), Summation of Residual Harmonics(SRH) and Cepstrum Pitch Determination (CEP) perform admirably in terms of specificity and accuracy, but they are not very effective in terms of sensitivity and GPE. On the other hand, the suggested hybrid approach, Proposed PEF+CEP, offers a noteworthy enhancement in accuracy, attaining a remarkable 98.8%, in addition to a sensitivity of 99.2%. The hybrid approach exhibits a slightly higher GPE than some traditional methods, but these minor deviations are outweighed by the significant improvements in accuracy and sensitivity that it offers. Furthermore, the Proposed PEF+CEP method is a promising solution for reliable and accurate pitch detection in speech processing applications because it strikes a strong balance between computational efficiency, training time, model size, and convergence rate. The suggested method offers notable improvements in pitch detection accuracy and reliability while addressing the drawbacks of separate approaches by utilizing the advantages of both PEF and CEP techniques. As a result, the suggested PEF+CEP approach stands out as a significant advancement in speech processing, offering enhanced functionality and versatility in a range of real-world settings. Pitch detection algorithms could become even more complex and effective with more research and development in this area, enabling improvements in text-to-speech synthesis, speaker Identification, And Speech Recognition, Among Other Fields. other: Nil

Deep learning restores speech intelligibility in multi-talker interference for cochlear implant users

Cochlear implants (CIs) do not offer the same level of effectiveness in noisy environments as in quiet settings. Current single-microphone noise reduction algorithms in hearing aids and CIs only remove predictable, stationary noise, and are ineffective against realistic, non-stationary noise such as multi-talker interference. Recent developments in deep neural network (DNN) algorithms have achieved noteworthy performance in speech enhancement and separation, especially in removing speech noise. However, more work is needed to investigate the potential of DNN algorithms in removing speech noise when tested with listeners fitted with CIs. Here, we implemented two DNN algorithms that are well suited for applications in speech audio processing: (1) recurrent neural network (RNN) and (2) SepFormer. The algorithms were trained with a customized dataset (∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim$$\\end{document} 30 h), and then tested with thirteen CI listeners. Both RNN and SepFormer algorithms significantly improved CI listener’s speech intelligibility in noise without compromising the perceived quality of speech overall. These algorithms not only increased the intelligibility in stationary non-speech noise, but also introduced a substantial improvement in non-stationary noise, where conventional signal processing strategies fall short with little benefits. These results show the promise of using DNN algorithms as a solution for listening challenges in multi-talker noise interference.

Comparative Study on Noisy Speech Preprocessing Algorithms

Speech Enhancement and noise reduction have wide applications in speech processing. They are often employed as pre-processing stage in various applications. The work to be presented in this paper is denoising a single-channel speech signal at the presence of a highly non-stationary background noise in order to improve the perceptible quality and intelligibility of the speech. Real world noise is mostly highly non-stationary and does not affect the speech signal uniformly over the spectrum. This paper investigates various Discrete Fourier Transform-based algorithms as single-channel pre-processing techniques consisting of: Spectral Subtraction using over-subtraction and spectral floor, Multi-Band Spectral Subtraction (MBSS), Wiener Filter, MMSE of Short-Time Spectral Amplitude (MMSE-STSA) estimator with, and without using SPU modifier, MMSE Log-Spectral Amplitude Estimator with, and without using SPU modifier, Optimally-Modified Log-Spectral Amplitude estimator (OM-LSA). The processed speeches from these algorithms are compared at the same set of conditions using visual examinations of signals in the time domain and the spectrograms, and also the objective and subjective tests for quality and perceptual evaluation. All the implemented algorithms provide considerable, different degrees of flexibility and control on noise elimination levels that reduces artifacts in the enhanced speech, resulting in the improved quality, and intelligibility.

Modern Standard Arabic speech disorders corpus for digital speech processing applications

Modern Standard Arabic speech disorders corpus for digital speech processing applications

Noise estimation based on optimal smoothing and minimum controlled through recursive averaging for speech enhancement

One of the most significant challenges in the real time speech processing applications is the elimination of noise in the corrupted speech data. This noise can significantly impact the efficacy/performance of the applications of speech processing. However, developing a robust noise reduction algorithm is crucial for improving the accuracy of automatic speech recognition (ASR) and other speech processing systems under uncontrolled conditions. In this paper, we propose an algorithm to reduce the background noise in the degraded speech data under highly non-stationary conditions. The proposed optimal smoothing and minima controlled (OSMC) technique uses recursive averaging to enhance degraded speech data. Initially, a smoothed periodogram and local minima of the degraded speech data are computed and determined the time-frequency dependent threshold factor. The ratio of smoothed periodogram to local minima is used to find the active regions of speech in the degraded speech data by adapting the Bayesian minimum cost decision rule. To calculate the estimated noise spectrum for each frequency bin, a time-frequency smoothing factors are used. The perceptual evaluation of speech quality (PESQ) and normalized covariance metric (NCM) are used to evaluate the speech quality and intelligibility of the proposed technique over competing algorithms after speech enhancement. The experimental results demonstrated that the proposed algorithm has given a significant improvement in terms of average values of PESQ by 15.03% and 16.71% and NCM by 3.45% and 5.73% for NOIZEUS and Kannada speech databases at 5 dB and 10 dB respectively, over unprocessed speech under highly non-stationary noisy environments.

Deep learning methods and integrated digital image processing techniques for detecting and evaluating wheat stripe rust disease

In recent years, signal processing and deep learning convergence has sparked transformative synergies across various domains, including image and speech recognition, natural language processing, autonomous systems, and healthcare diagnostics. This fusion capitalizes on the strength of signal processing in extracting meaningful features from raw data and the prowess of deep learning in unraveling intricate patterns, driving innovation and research into uncharted territories. This paper explores literature spanning the past three years to illuminate the dynamic landscape of scholarly endeavors that leverage the integration of signal processing techniques within deep learning architectures. The resulting paradigm shift magnifies the precision and efficiency of applications in computer vision, speech and audio processing, natural language comprehension, and interdisciplinary domains like healthcare. Notable advances include synergizing wavelet transformations with convolutional neural networks (CNNs) for enhanced image classification accuracy, integrating spectrogram-based features with deep learning architectures for improved speech-to-text accuracy, and pioneering the fusion of wavelet packet decomposition into recurrent architectures for sentiment analysis. Moreover, the paper delves into developing and evaluating a U-Net neural network model for image segmentation, investigating its performance under varying training conditions using metrics such as confusion matrices, heat maps, and precision-recall curves. The comprehensive survey identifies research gaps, notably within the context of wheat rust detection, and emphasizes the need for tailored innovations to enhance accuracy and efficiency. Overall, the synthesis of signal processing techniques with deep learning architectures propels innovation, poised to address complex challenges across diverse domains

Exploiting auditory filter models as interpretable convolutional frontends to obtain optimal architectures for speaker gender recognition

Identifying the gender of a speaker is an important problem which can be considered as a preliminary task in many speech processing applications such as speaker identification and emotion recognition. Although many accurate models have been developed through the progress of Deep Neural networks (DNNs), the computational complexity of these models makes them unsuitable for some situations with limited hardware resources. Pruning the designed architecture of DNNs to achieve the same initial accuracies by reducing the number of network parameters is a way to create more efficient architectures. In this paper, Auditory Filter Models (AFMs) are exploited to be used as frontend convolutional filters. In addition to the fact that these meaningful filters can be represented by a few parameters, they also provide better performance compared to traditional conventional filters. The proposed method can increase efficiency, improve the generalizability of the models, and reduce the number of parameters for gender recognition. Moreover, by utilizing a clustering approach to reduce the number of learnable filters of the AFM in the first convolutional layer, the network parameters can be reduced even further. Experimental results conducted on four well-known datasets, namely TIMIT, LibriSpeech, VoxCeleb1, and RAVDESS, prove the validity of the claims made earlier. The results show that the use of this technique not only enhances the performance of the models but also facilitates the learning of a rich and informative representation of speech data. This finding emphasizes the effectiveness and robustness of the proposed approach in handling diverse datasets and real-world scenarios.

A Compact and Ultra-Low-Power Low-Pass Filter Based on Band-to-Band Tunneling Effect

Continuous-time filters with low-frequency cutoff are crucial building blocks in analog signal processing circuits for speech processing and biomedical applications. The design of an integrated continuous-time filter with a cutoff frequency spanning from sub-Hz to a few kHz is constrained by the ultra-low power and area minimization requirement. In this article, we have experimentally demonstrated a low pass filter response using only a single partially depleted (PD) silicon on insulator (SOI) transistor. The proposed novel filter is based on band to band tunnelling (BTBT). This low pass filter is on-chip tunable to provide a wide cutoff frequency ranging from 2 Hz to 20 kHz, with a silicon footprint of 9 μm2 and the maximum power consumption of 0.6 nW in Global Foundries’ (GF) 45 nm RFSOI technology. The proposed tunneling-based filter is less prone to process variations and mismatches as compared to traditional integrated analog filters. The proposed BTBT-based passive RC filter with spurious free dynamic range (SFDR) of 29 dbc, outperforms previously reported filters in the literature in terms of power consumption and area. The ultra-low power consumption and area efficiency make this proposed low pass filter suitable for the multichannel analog front-end low-frequency filters for noise-tolerant neural network-based applications such as speech recognition and electrophysiological signal recognition.

Information technology for gender recognition by voice

Gender recognition from voice is a challenging problem in speech processing. This task involves extracting meaningful features from speech signals and classifying them into male or female categories. In this article, was implemented a gender recognition system using Python programming. I first recorded voice samples from both male and female speakers and extracted Mel-frequency cepstral coefficients (MFCC) as features. Then trained, a Support VectorMachine (SVM) classifier was on these features and evaluated its performance using accuracy, precision, recall, and F1-score metrics. These experiments demonstrated that proposed system should achieve high accuracy on the test set and will accurately predict the gender of a speaker based on their voice. I also explored using pre-trained models to reduce the need for large amounts of training data and found that they can provide good performance while requiring less computation. This study highlights the potential of using machine learning techniques for gender recognition from voice and can be extended to other speech processing applications.

TPTS: Text pre-processing Techniques for Sindhi Language

The Internet is a significant source of textual data, with users generating vast amounts of information through social media and news agencies daily. The extraction of meaningful information from large datasets is a challenging and costly process. Text pre-processing is a crucial initial step in any Natural Language Processing (NLP) task, as it can impact the overall performance of the study. The main objective of text pre-processing is to transform unstructured text into a linguistically meaningful (standard form) format, making extracting information for any text-processing task easier. This paper introduces TPTS, a model for text pre-processing in the Sindhi language. TPTS performs essential NLP tasks such as text tokenization, normalization, stop-word removal, stemming, and POS tagging for the Sindhi language. The Sindhi Text Corpus (STC), consisting of 1.5k Sindhi text documents collected from various online news websites, is used for experimentation. The TF-IDF approach is employed to identify high-frequency stop-words in the Sindhi language. Furthermore, a rule-based system tags words with their part of speech in Sindhi input text. The ROUGE evaluation metric is used to assess the effectiveness of the proposed TPTS technique, achieving 89% accuracy on the STC corpus. The Sindhi language is spoken by over 30 million people globally, and the lack of adequate NLP tools and resources limits the development of technology and natural language applications that can benefit Sindhi speakers. The proposed TPTS model can aid in developing such applications, making it beneficial not only for text pre-processing tasks but also for other Sindhi language text-processing tasks such as text summarization, sentiment analysis, speech-processing applications, text mining, and information retrieval systems.

Formant estimation of high-pitched noisy speech using homomorphic deconvolution of higher-order group delay spectrum

Estimating the formant frequencies of high-pitched speech is essential in many speech processing applications. Unfortunately, most existing methods cannot accurately estimate the formant frequencies from high-pitched speech. Moreover, the available formant estimators do not show noise immunity. In this paper, we propose a higher-order group delay (GD) spectrum-based deconvolution method for formant estimation of high-pitched noisy speech with higher accuracy. Although cepstrum is known to provide a source-filter separation, to some extent, it gets affected by ambient noise. We employ the spectral-root-deconvolution technique on the third-order GD spectrum that yields a noise-robust cepstrum. The resulting cepstrum is found to produce significant improvement when estimating formant frequencies. We evaluated the proposed method on five synthetic vowels and some natural vowels spoken by male and female speakers by calculating the estimation error of the formant frequencies and standard F2–F1 plots, respectively. An utterance from the Texas Instruments and Massachusetts Institute of Technology (TIMIT) database has been utilized to plot the formant contours on the respective spectrogram. We compared the results with the three state-of-the-art methods. Our proposed technique outperforms all approaches, particularly with high-pitched speaking in a noisy environment.

Hardware Implementations for Voice Activity Detection: Trends, Challenges and Outlook

Voice Activity Detection (VAD) is a technique used to identify the presence of human voice in an audio signal. It is implemented as an always-on component in most speech processing applications. As speech is absent most of the time, this component typically dominates the overall average power consumption of the system (excluding microphone). The widespread usage in speech applications and the need for ultra low power VAD have led to a plethora of algorithms and implementations in the hardware domain, necessitating a comprehensive study and analysis to understand (real-time) requirements, different design parameters, testing strategies, but also to identify design trends, challenges and guidelines for future implementations and testing of VAD devices. A scoping review was conducted to identify the articles for hardware implementations of VAD from January 2010 - December 2021, the results of which are presented in this article. The results highlight a big design space being used for VAD along with a lack of standard testing methodology and usage of application-dependent performance metrics. An increased usage of filter-based feature extractors along with neural-network-based classifiers is observed. Due to lack of standardisation, no other trends can be established from the results. A set of rules and guidelines are therefore provided to facilitate the future development and benchmarking of VADs.

A Time-Frequency Attention Module for Neural Speech Enhancement

Speech enhancement plays an essential role in a wide range of speech processing applications. Recent studies on speech enhancement tend to investigate how to effectively capture the long-term contextual dependencies of speech signals to boost performance. However, these studies generally neglect the time-frequency (T-F) distribution information of speech spectral components, which is equally important for speech enhancement. In this paper, we propose a simple yet very effective network module, which we term the T-F attention (TFA) module, that uses two parallel attention branches, i.e., time-frame attention and frequency-channel attention, to explicitly exploit position information to generate a 2-D attention map to characterise the salient T-F speech distribution. We validate our TFA module as part of two widely used backbone networks (residual temporal convolution network and Transformer) and conduct speech enhancement with four most popular training objectives. Our extensive experiments demonstrate that our proposed TFA module consistently leads to substantial enhancement performance improvements in terms of the five most widely used objective metrics, with negligible parameter overheads. In addition, we further evaluate the efficacy of speech enhancement as a front-end for a downstream speech recognition task. Our evaluation results show that the TFA module significantly improves the robustness of the system to noisy conditions.

Development of Small Vocabulary Continuous Speech-to-Text System for Kannada Language/Dialects

Objectives: To develop a speech-to-text (STT) system using Kaldi speech recognition toolkit for continuous Kannada language/dialects. Methods: A continuous Kannada speech data is collected from 100 speakers/farmers of Karnataka state in field. The lexicon/dictionary and set of phonemes for Kannada language/dialects are created and transcribed the collected speech data using transcriber tool. The ASR models are developed at different phoneme levels using Kaldi. Findings: In this work, an effort is made to develop a robust small vocabulary STT system for continuous Kannada language using Kaldi. The various acoustic modelling techniques are used to develop a robust ASR model and achieved a word error rate (WER) of 0.23%. The performance of the developed ASR model is compared with existing works and analyzed by offline speech recognition. Novelty: Many STT systems have been developed for Indian and International languages/dialects, but not for Kannada language. This work is first of its kind using Kaldi in Kannada language under the constraints of limited data. The developed ASR model could be used further in the development of end-to-end ASR system for speech processing applications. Keywords: Automatic Speech Recognition (ASR); Word Error Rate (WER); Continuous Kannada Speech Data; Kannada Language/Dialects; Lexicon

Is AI at human parity yet? A case study on speech recognition

AbstractClaims have been made that speech recognition has achieved human parity, yet this does not appear to be the case in the real‐world applications that rely on it, especially for non‐native speakers. This then begs the questions: What does it even mean for an AI system to reach human parity? How is progress towards that goal being measured? This article focuses on the current state of speech recognition and the recent developments in benchmarking and measuring performance of AI models built for speech processing. Through the shift away from single metric benchmarks and specialized models and towards evaluating collections of diverse challenging tasks and generalized models, the ultimate goal of true human parity in commercial speech processing applications is hopefully on the near horizon.

Spectral Methods for Single Channel Speech Enhancement in Multi-Source Environment

Speech communication for both humans and automatic devices can be negatively impacted by background noise, which is common in real environments. Among many techniques, speech separation using a single microphone is the most desirable from an application standpoint. The resulting monaural speech separation problem has been a central one in speech processing for several decades. However, its success has been limited thus far. This research presents work that develops speech separation systems using combinations of T-F masking, DNNs, and model-based reconstruction. The aim of each system is to improve the perceptual quality of the speech estimates. The performance of many speech processing applications is severely degraded when both noise and reverberation are present. The proposed solution has been tested in the simulation environment and based on the simulation result, it is observed that the speech enhancement can easily be performed through the integration of the solution. This research suggests two staged noise reducing systems in order to reduce the background noise through a single microphone recording in a low-SNR based on ideal binary masking and Wiener filter. It has two stages. Firstly, for background noise reduction, a Wiener filter with an enhanced SNR is utilised on noisy speech. Secondly, IBM is calculated in each time–frequency channel through utilisation of the pre–processed speech from the first stage and the matching of the time–frequency channels to a pre-selected threshold in order to minimise residual noise. These channels meeting the threshold requirement are conserved while all the other ones are attenuated.

RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information

AbstractIn this article, we introduce an extended, freely available resource for the Romanian language, named RoLEX. The dataset was developed mainly for speech processing applications, yet its applicability extends beyond this domain. RoLEX includes over 330,000 curated entries with information regarding lemma, morphosyntactic description, syllabification, lexical stress and phonemic transcription. The process of selecting the list of word entries and semi-automatically annotating the complete lexical information associated with each of the entries is thoroughly described.The dataset’s inherent knowledge is then evaluated in a task of concurrent prediction of syllabification, lexical stress marking and phonemic transcription. The evaluation looked into several dataset design factors, such as the minimum viable number of entries for correct prediction, the optimisation of the minimum number of required entries through expert selection and the augmentation of the input with morphosyntactic information, as well as the influence of each task in the overall accuracy. The best results were obtained when the orthographic form of the entries was augmented with the complete morphosyntactic tags. A word error rate of 3.08% and a character error rate of 1.08% were obtained this way. We show that using a carefully selected subset of entries for training can result in a similar performance to the performance obtained by a larger set of randomly selected entries (twice as many). In terms of prediction complexity, the lexical stress marking posed most problems and accounts for around 60% of the errors in the predicted sequence.

Frequency, Time, Representation and Modeling Aspects for Major Speech and Audio Processing Applications.

There are many speech and audio processing applications and their number is growing. They may cover a wide range of tasks, each having different requirements on the processed speech or audio signals and, therefore, indirectly, on the audio sensors as well. This article reports on tests and evaluation of the effect of basic physical properties of speech and audio signals on the recognition accuracy of major speech/audio processing applications, i.e., speech recognition, speaker recognition, speech emotion recognition, and audio event recognition. A particular focus is on frequency ranges, time intervals, a precision of representation (quantization), and complexities of models suitable for each class of applications. Using domain-specific datasets, eligible feature extraction methods and complex neural network models, it was possible to test and evaluate the effect of basic speech and audio signal properties on the achieved accuracies for each group of applications. The tests confirmed that the basic parameters do affect the overall performance and, moreover, this effect is domain-dependent. Therefore, accurate knowledge of the extent of these effects can be valuable for system designers when selecting appropriate hardware, sensors, architecture, and software for a particular application, especially in the case of limited resources.

A surrogate gradient spiking baseline for speech command recognition.

Artificial neural networks (ANNs) are the basis of recent advances in artificial intelligence (AI); they typically use real valued neuron responses. By contrast, biological neurons are known to operate using spike trains. In principle, spiking neural networks (SNNs) may have a greater representational capability than ANNs, especially for time series such as speech; however their adoption has been held back by both a lack of stable training algorithms and a lack of compatible baselines. We begin with a fairly thorough review of literature around the conjunction of ANNs and SNNs. Focusing on surrogate gradient approaches, we proceed to define a simple but relevant evaluation based on recent speech command tasks. After evaluating a representative selection of architectures, we show that a combination of adaptation, recurrence and surrogate gradients can yield light spiking architectures that are not only able to compete with ANN solutions, but also retain a high degree of compatibility with them in modern deep learning frameworks. We conclude tangibly that SNNs are appropriate for future research in AI, in particular for speech processing applications, and more speculatively that they may also assist in inference about biological function.

Multi-label bird species classification from audio recordings using attention framework

For the conservation of avian biodiversity, bird detection is vital since it allows ornithologists to quantify which species exist in a particular area. Analyzing their acoustic signals enables the efficient identification of multiple bird species from overlapping recordings. This paper addresses classifying bird vocalizations in real-time audio recording using acoustic analysis. Schemes based on recurrent neural networks (RNN) are presented in the proposed work. Gated-recurrent units (GRU) are a particular type of RNN that has shown remarkable performance in acoustic classification. We propose a hierarchical Attention-based bidirectional gated recurrent unit (BiGRU) model for classifying acoustic signals of birds by using Mel-frequency cepstral coefficients (MFCC). The attention mechanism has proved its superior efficacy in many acoustic, speech and music processing applications. The attention mechanism is employed to give a different focus to the information outputted from the hidden layers of BiGRU. We adopted a short-time sliding-aggregation approach to decide on the test data, in which probability outcomes are species-wise summed and normalized. Species with the highest probability scores are assumed to be the dominant species in the recording. Our Attention-BiGRU classifier achieves pretty high performance in the Xeno-Canto dataset, with an F1-score of 0.84, with competing performance to the state-of-the-art multi-label classifiers.