A Real Time Noise-Robust Speech Recognition System

RETRACTED: Real time speech recognition algorithm on embedded system based on continuous Markov model

Insects play significant role in the human life. And insects pollinate major food crops consumed in the world. Insect pests consume and destroy major crops in the world. Hence to have control over the disease and pests, researches are going on in the area of entomology using chemical, biological and mechanical approaches. The data relevant to the flying insects often changes over time, and classification of such data is a central issue. And such time series mining tasks along with classification is critical nowadays. Most time series data mining algorithms use similarity search and hence time taken for similarity search is the bottleneck and it does not produce accurate results and also produces very poor performance. In this paper, a novel classification method that is based on the dynamic time warping (DTW) algorithm is proposed. The dynamic time warping algorithm is deterministic and lacks in modeling stochastic signals. The dynamic time warping (DTW) algorithm is improved by implementing a nonlinear median filtering (NMF). Recognition accuracy of conventional DTW algorithms is less than that of the hidden Markov model (HMM) by same voice activity detection (VAD) and noise-reduction. With running spectrum filtering (RSF) and dynamic range adjustment (DRA). NMF seek the median distance of every reference of time series data and the recognition accuracy is much improved. In this research work, optical sensors are used to record the sound of insect flight, with invariance to interference from ambient sounds. The implementation of our tool includes two parts, an optical sensor to record the "sound" of insect flight, and a software that leverages on the sensor information, to automatically detect and identify flying insects.

This paper proposes an improved dynamic time warping (DTW) algorithm with a nonlinear median filtering (NMF). Recognition accuracy of conventional DTW algorithms are less than the hidden Markov model (HMM) by same voice activity detection (VAD) and noise-reduction with running spectrum filtering (RSF) and dynamic range adjustment (DRA). For analyzing some incorrect results, unlike in conventional DTW, we do not use the minimum distance to recognize. we employ NMF and seek the median distance of the every reference word with the unknown speech waveform. All recognition accuracy of conventional DTW algorithms are improved much more by NMF. The recognition accuracy of Itakura's DTW algorithm is the best. Its recognition accuracy similar to that of the HMM approach in 10 dB and 20 dB white noise.

In this study, a real-time automatic speech recognition (ASR) system based on the Kaldi ASR toolkit, with low-latency and customizable models, without any internet connection, was developed. The proposed ASR system includes a voice activity detection (VAD) module and an audio transmitter as a front-end speech processing and a decoder for the received audio signals. The ASR system was evaluated in terms of ASR accuracy and speech processing speed. Consequently, the ASR system achieved high ASR accuracy on the CSJ (Corpus of Spontaneous Japanese) test set with super low-latency.

In addressing the problem of achieving high-accuracy real-time speech recognition systems, we focus on recognizing speech from ARPA's 20,000-word Wall Street Journal (WSJ) task, using current UNIX workstations. We have found that our standard approach---using a narrow beam width in a Viterbi search for simple discrete-density hidden Markov models (HMMs)---works in real time with only very low accuracy. Our most accurate algorithms recognize speech many times slower than real time. Our (yet unattained) goal is to recognize speech in real time at or near full accuracy.We describe the speed/accuracy trade-offs associated with several techniques used in a one-pass speech recognition framework:• Trade-offs associated with reducing the acoustic modeling resolution of the HMMs (e.g., output-distribution type, number of parameters, cross-word modeling)• Trade-offs associated with using lexicon trees, and techniques for implementing full and partial bigram grammars with those trees• Computation of Gaussian probabilities are the most time-consuming aspect of our highest accuracy system, and techniques allowing us to reduce the number of Gaussian probabilities computed with little or no impact on speech recognition accuracy.Our results show that tree-based modeling techniques used with appropriate acoustic modeling approaches achieve real-time performance on current UNIX workstations at about a 30% error rate for the WSJ task. The results also show that we can dramatically reduce the computational complexity of our more accurate but slower modeling alternatives so that they are near the speed necessary for real-time performance in a multipass search. Our near-future goal is to combine these two technologies so that real-time, high-accuracy large-vocabulary speech recognition can be achieved.

It has further shaped the domain of real-time voice-controlled speech recognition systems. Things like language bias, computational expense and background noise have made strides more difficult in the past. This paper provides a novel view on these tasks, allowing for broader accessibility and real-world applicability of state-of-the-art models. We advocate a multi-dimensional methodology, including ad hoc model contextualization, tailored neural designs, and personalized learning strategies, to achieve voice and chip-height optimization. Existing speech recognition systems have a major limitation of being limited to few languages, dialects and accents. This study introduces a multilingual and multicultural model to address this issue and also provides access to the benefit of no-bias technologies to all parts of society. Out of these regional filters, it can work with more and work on them more precisely. In addition to this, the efficient structure also improves computational efficiency, meaning that the model is able to gain speed in real-time processing on low-power devices, fitting to rising demand for speech recognition in mobile and edge computing settings. Performance in contextual understanding remains a problem, errors in pronunciation or deviations from the dialect tend to lead to mistakes. As a result, the current study utilise semantic analysis and natural language processing (NLP) methods to assist understanding across different languages globally. These services are used in applications like medical/legal transcription or customer support, where correct transcription is critical. Additionally, the architecture enhances real-time processing by reducing latency and increasing responsiveness, which is critical in emergency response systems and autonomous vehicles where timely decision-making is crucial. By enhancing the efficiency and accuracy of ANN-based speech recognition, this research drives advancements in increasingly more accessible, effective, and reliable voice-activated technologies.

We present an end-of-utterance detector for real-time automatic speech recognition in far-field scenarios. The proposed system consists of three components: a long short-term memory (LSTM) neural network trained on acoustic features, an LSTM trained on l-best recognition hypotheses of the automatic speech recognition (ASR) decoder, and a feedforward deep neural network (DNN) combining embeddings derived from both LSTMs with pause duration features from the ASR decoder. At inference time, lower and upper latency (pause duration) bounds act as safeguards. Within the latency bounds, the utterance end-point is triggered as soon as the DNN posterior reaches a tuned threshold. Our experimental evaluation is carried out on real recordings of natural human interactions with voice-controlled far-field devices. We show that the acoustic embeddings are the single most powerful feature and particularly suitable for cross-lingual applications. We furthermore show the benefit of ASR decoder features, especially as a low cost alternative to ASR hypothesis em-beddings.

The IEEE 802.11 standard defines two operational modes for WLANs: infrastructure-based and infrastructure-less or ad-hoc. With constrained resources and limited computational capability, it may not be able for a node to serve more number of neighbours at the same time. The Dynamic Transmission Range Adjustment Protocol provides a mechanism for adjusting transmission range of the ad-hoc nodes to register or de-register a communicating node as its neighbour by dynamically varying the transmission range. Coloured Petri Nets is the modelling tool which provides a framework for design, specification, validation and verification of systems. In this paper, this tool is used to model and validate Dynamic Transmission Range Adjustment Protocol.

This paper proposes a speaker-dependent speech recognition algorithm which can classify the gender for male and female speakers in white noise and car noise, using a neural network. The proposed speech recognition algorithm is trained by the neural network to recognize the gender for male and female speakers, using LPC (Linear Predictive Coding) cepstrum coefficients. In the experiment results, the maximal improvement of total speech recognition rate is 96% for white noise and 88% for car noise, respectively, after trained a total of six neural networks. Finally, the proposed speech recognition algorithm is compared with the results of a conventional speech recognition algorithm in the background noisy environment.

The paper reports one microcontroller car which processes speech - LINGYANG SPCE061A microchip forming speech recognition system. The speech recognition system not only has high recognizable veracity, small volume, economy-power consumption, lower cost, high operation speed and real-time speech recognition. Furthermore, the function of speech cue offers a favorable interface for human-computer interaction in the system. These characteristics embody fully predominance of the embedded speech recognition.

Speech recognition in Human-Robot Interaction (HRI) fully relies on audio-based Automatic Speech Recognition. However, speech recognition that relies solely on audio faces significant challenges in noisy environments and may lead to poor performance in such environments. One approach to address this is to also use lipreading in combination with traditional speech recognition. Recent work has shown that audiovisual speech recognition (AVSR) can achieve a Word Error Rate (WER) of only 0.9% on the dataset LRS3. In this paper, we assess the potential of combining audio with lipreading on a social robot platform, Pepper, which has not yet been widely tested for AVSR. Given that prior research has focused on non-robotic domains, it remains unclear whether such models can generalize well to social robot environments. We systematically evaluate and compare the performance of established offline and real-time audiovisual models with their audio-only counterparts. The experiments were conducted in both a controlled laboratory setting and a dynamic and noisy public environment. We evaluated the data using WER and also measured the inference latency of real-time models via Real-Time Factor and Words Per Second rates. The results demonstrate real-time performance for audio-only speech recognition across all latency metrics and near real-time performance for models that combine audio with lipreading. We also explored factors that might influence the inference performance of these models to understand how much video contributes to the audio. This includes factors related to (1) environmental and temporal variations, (2) model behavior, and (3) implementation choices. Our findings indicate that for now the audio-only models outperform the audiovisual models on a social robot platform, in contrast to what has been reported in the benchmarked literature. We conclude that more work is still needed to benefit from lipreading in HRI.

A method for efficient pruning which reduces central processing unit loading during real time speech recognition. A CPU uses a predetermined threshold for discarding not useful or necessary information. Useful information is stored in an available scoring buffer slot. A slot is said to be available if its last-time field does not equal the current time-index. To prevent pruning of a slot in the best path, the current time-index has to be propagated to all slots in the best path. This back-propagation increases CPU loading and is alleviated by referring the backpointer of a state within a model to its start state.

The Digital Image Analysis Laboratory (DIAL) at USAETL is a large scale interactive digital image processing system designed for research in photo- and radar-interpretation, feature extraction, mapmaking, and other remote sensing activities. General techniques such as search, change detection, dynamic range adjustments, geometric corrections, and mensuration have been implemented and applied to digital imagery for evaluation. In particular, the DIAL system was used for a series of four experiments designed to evaluate the utility of soft copy (CRT) exploitation of digital imagery for tactical field army applications. The results of those four experiments were conducive to continued development of the soft copy capability. At USAETL that continued development has taken the form of a van-mounted system, now being implemented, consisting of a control minicomputer, high density tapes, and an advanced digital image display system. The advanced display system provides rapid search, magnification, dynamic range, and filtering capabilities as well as many other now-standard image processing functions. It is expected that the van-mounted system will provide at least a partial solution to the very basic problems encountered in the manipulation and display of very large digital images.

Mel-frequency Cesptral Coefficients (MFCC) and Predictive Linear Prediction (PLP) coefficients are two popular representations of continuous speech in existing Hidden Markov Model (HMM) based Automatic Speech Recognition (ASR) systems. Cepstral Mean Normalization (CMN) is often used as a post-processing step in the extraction of MFCC and PLP features to further enhance noise robustness at almost negligible computational cost. In this paper we build a closed dictionary, large vocabulary HMM-based Indonesian language ASR system using the CMU Sphinx in speech recognition toolkit implementing MFCC and PLP feature extraction, and CMN. We test the effect of various types and levels of noise on the word error rate (WER) of speech recognition. Utilizing CMN, an average improvement of 2% recognition over standard MFCC and PLP extraction methods is obtained at signal-to-noise ratios (SNR) below 24 decibels. A significant drop in recognition is observed between 12 and 6 dB SNR.

Robustness of the automatic speech recognition (ASR) system relies upon the accuracy of feature extraction and classification in training phase. The mismatch between training and testing conditions during classification of large feature vectors causes a low performance. In this paper, the issue of robustness of acoustic information is addressed for practical Punjabi dataset. Traditional feature extraction approaches: mel frequency cepstral coefficients (MFCC) and gammatone frequency cepstral coefficients (GFCC) face the issue of high variance with leakage of spectral information. Also, handling of the huge number of feature information creates chaos for large speech vocabulary. To overcome this dilemma, a Principal component analysis (PCA) based multi-windowing technique is proposed with the incorporation of baseline GFCC and MFCC based feature approaches after the tuning of taper parameter. The proposed integrated approaches result in better feature vectors, which are further processed using differential evolution + hidden Markov model (DE + HMM) based modelling classifier. The integrated approaches show substantial performance for word recognition as compared to the conventional or fused feature extraction systems.