Classification techniques for automatic speech recognition (ASR) algorithms used with real time speech translation

Nasereddin, Hebah H. O.; Omari, Ayoub Abdel Rahman

doi:10.1109/sai.2017.8252104

Cited by 12 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several classification methods have been employed for ASR, with some still in use, some evolving, and new methods emerging. Deep Neural Networks (DNN) and Hidden Markov Models (HMM) are considered the most effective algorithms and classification methods in learning vocal signals [6], [7]. The choice of learning methods (HMM, GMM, DTW, SVM, DNN, etc.)…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

WITHDRAWN: An Experiment of Moroccan Dialect speech recognition in noisy environments using PocketSphinx

OUISAADANE,

SAFI,

FRIKEL

2023

Preprint

View full text Add to dashboard Cite

In this study, we introduce an experimental framework for Moroccan Dialect speech recognition under various additive noise conditions using the open-source tool PocketSphinx. We curated a corpus comprising the ten most commonly used greetings in the Moroccan dialect, extracted from telephone conversations. This corpus was recorded with 60 speakers (30 males and 30 females). Each speaker articulated each expression three times in natural and noisy conditions. Feature extraction utilized Mel Scale Cepstral Coefficients (MFCC), and acoustic modeling, based on monophony, was implemented using Hidden Markov Models (HMM). While automatic speech recognition systems demonstrate commendable performance in noise-free conditions, their efficacy noticeably diminishes in the presence of noise.

show abstract

Section: Introductionmentioning

confidence: 99%

“…The choice of learning methods (HMM, GMM, DTW, SVM, DNN, etc.) [7] [8] depend on the analysis parameters, data size, and generalization capacity. In essence, one must consider testing and generalization methods to validate the learning model.…”

Section: Introductionmentioning

confidence: 99%

WITHDRAWN: An Experiment of Moroccan Dialect speech recognition in noisy environments using PocketSphinx

OUISAADANE,

SAFI,

FRIKEL

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Mean classification accuracy is 95.70 % when using a combination model of Phoneme with a fusion of MFCC and proposed features as a features vector. Nasereddin et al [8] proposed research for classifying speech signals into 4 classes using HMM, Dynamic time warping (DTW) and Dynamic Bayesian Network (DBN) with MFCC feature extraction. DBN outperformed in recognizing one class while HMM is achieving higher recognition rate for the other classes.…”

Section: Related Workmentioning

confidence: 99%

Broad Phonetic Classification of ASR using Visual Based Features

Lehabik¹,

Merzban

Saad³

et al. 2020

The Egyptian Journal of Language Engineering

View full text Add to dashboard Cite

This paper presents a novel method of classifying speech phonemes. Four hybrid techniques based on the acousticphonetic approach and pattern recognition approach are used to emphasize the principle idea of this research. The first hybrid model is constructed of fixed state, structured Hidden Markov Model, Gaussian Mixture, Mel scaled Best Tree Image, Convolution Neural network, Vector Quantization (FS-HMM-GM-MBTI-CNN-VQ). The second hybrid model is constructed of variable state, dynamically structured Hidden Markov Model, Gaussian Mixture, Mel scaled Best Tree Image, Convolution Neural network, Vector Quantization (VS-HMM-GM-MBTI-CNN-VQ). The third hybrid model is constructed of fixed state, structured Hidden Markov Model, Gaussian Mixture, Mel scaled Best Tree Image, Convolution Neural network (FS-HMM-GM-MBTI-CNN). The fourth hybrid model is constructed of variable state, dynamically structured Hidden Markov Model, Gaussian Mixture, Mel scaled Best Tree Image, Convolution Neural network (VS-HMM-GM-MBTI-CNN). TIMIT database is used in this paper. All phones are classified into five classes and segregated into Vowels, Plosives, Fricatives, Nasals, and Silences. The results show that using (VS-HMM-GM-MBTI-CNN-VQ) is an available method for classification of phonemes, with the potential for use in applications such as automatic speech recognition and automatic language identification. Competitive results are achieved especially in nasals, plosives, and silence high successive rates than others.

show abstract

“…With the emergence of the fifth-generation mobile communication system (5G), many computing-intensive services have been developed, such as face recognition [1], self-driving cars [2], and real-time translation [3]. However, the existing civil devices cannot provide sufficient computing resources for these computing-intensive tasks.…”

Section: Introductionmentioning

confidence: 99%

Decentralized Offloading Strategies Based on Reinforcement Learning for Multi-Access Edge Computing

Shi

et al. 2021

Information

View full text Add to dashboard Cite

Using reinforcement learning technologies to learn offloading strategies for multi-access edge computing systems has been developed by researchers. However, large-scale systems are unsuitable for reinforcement learning, due to their huge state spaces and offloading behaviors. For this reason, this work introduces the centralized training and decentralized execution mechanism, designing a decentralized reinforcement learning model for multi-access edge computing systems. Considering a cloud server and several edge servers, we separate the training and execution in the reinforcement learning model. The execution happens in edge devices of the system, and edge servers need no communication. Conversely, the training process occurs at the cloud device, which causes a lower transmission latency. The developed method uses a deep deterministic policy gradient algorithm to optimize offloading strategies. The simulated experiment shows that our method can learn the offloading strategy for each edge device efficiently.

show abstract

Classification techniques for automatic speech recognition (ASR) algorithms used with real time speech translation

Cited by 12 publications

References 15 publications

WITHDRAWN: An Experiment of Moroccan Dialect speech recognition in noisy environments using PocketSphinx

WITHDRAWN: An Experiment of Moroccan Dialect speech recognition in noisy environments using PocketSphinx

Broad Phonetic Classification of ASR using Visual Based Features

Decentralized Offloading Strategies Based on Reinforcement Learning for Multi-Access Edge Computing

Contact Info

Product

Resources

About