Real-time Speaker Identification Research Articles

Real-Time Speaker Identification and Subtitle Overlay with Multithreaded Audio Video Processing

Active Speaker Detection is pivotal in a multitude of applications, particularly in processing live Audio-Video (AV) streams. Current implementations predominantly focus on processing saved video files, limiting their real-time applicability. Addressing this gap, the proposed model leverages a multi-threading-based system to detect active speakers in live AV streams. This system forms a critical component in an innovative software solution designed to generate real-time subtitles and elegantly overlay them aside from the active speaker. This feature is especially beneficial for individuals with hearing impairments and facilitates the transcription of foreign languages into English, thereby improving human interaction and understanding. Our approach stands out for its ability to process live AV streams promptly for immediate speaker identification and subtitle overlay, marking a significant advancement in real-time communication assistance.

Modified layer deep convolution neural network for text-independent speaker recognition

peaker recognition is the task of identifying the spokesman automatically using speaker-specific features. It has been a popular and most involved topic in the field of speech technology. This field opens a wide opportunity for research and finds its application in the areas such as forensics, authentication, security, etc. In this work, a modified deep-convolutional neural network structure has been proposed for speaker identification that has improved convolution, activation, and pooling layers along with Adam’s optimiser. The proposed architecture yielded the increase of prediction accuracy and reduction of Loss function when compared to the generic Convolutional Neural Network scheme. The execution of the proposed architecture is validated by various datasets and the outcomes show that the modified CNN performs better than the other state-of-the-art models regarding both accuracy (avg 99%) and loss function (avg 1%). From the analysis, it is found that the Modified-CNN suits the best for real-time speaker identification applications as the efficacy of the model does not degrade due to the effects of noise and interferences that are caused in the recording environment. Relevance of the work: Speaker Recognition is an area of interest in which ML and DL schemes, when combined, have the potential to make history in the areas of Automation and Authentication. Using a modified CNN can enhance the process by ignoring many issues such as false positives, background noise, and so on. This process can be expanded to create a Raga Identification and Therapy mechanism that can be used to treat diseases.

A Novel Approach to Increase the Efficiency of a Multi-lingual Real-time Speaker Identification System

Nowadays, the real-time speaker recognition system is very popular due to its cost-effective nature. However, it is a very challenging one to produce a more efficient speaker identification system. In our work, we work on a multi-lingual real-time speaker identification system. We work in a novel way to enhance the efficiency of the said system. We take some real speech signals and use different speech enhancement methods and our proposed voice activity method (VAD) to enhance the efficiency of said system. By doing so, we increase the accuracy of the said system relatively by 2% as compared to existing methods.

Spectral entropy and spectral shape based pre-quantization for real time speaker identification system

Pre-processing is one of the vital steps for developing robust and efficient recognition system. Better pre-processing not only aid in better data selection but also in significant reduction of computational complexity. Further an efficient frame selection technique can improve the overall performance of the system. Pre-quantization (PQ) is the technique of selecting less number of frames in the pre-processing stage to reduce the computational burden in the post processing stages of speaker identification (SI). In this paper, we develop PQ techniques based on spectral entropy and spectral shape to pick suitable frames containing speaker specific information that varies from frame to frame depending on spoken text and environmental conditions. The attempt is to exploit the statistical properties of distributions of speech frames at the pre-processing stage of speaker recognition. Our aim is not only to reduce the frame rate but also to maintain identification accuracy reasonably high. Further we have also analyzed the robustness of our proposed techniques on noisy utterances. To establish the efficacy of our proposed methods, we used two different databases, POLYCOST (telephone speech) and YOHO (microphone speech).

Probabilistic scoring using decision trees for fast and scalable speaker recognition

In the context of fast and low cost speaker recognition, this article investigates several techniques based on decision trees. A new approach is introduced where the trees are used to estimate a score function rather than returning a decision among classes. This technique is developed to approximate the GMM log-likelihood ratio (LLR) score function. On top of this approach, different solutions are derived to improve the accuracy of the proposed trees. The first one studies the quantization of the LLR function to create classification trees on the LLR values. The second one makes use of knowledge on the GMM distribution of the acoustic features in order to build oblique trees. A third extension consists in using a low-complexity score function in each of the tree leaves. Series of comparative experiments are performed on the NIST 2005 speaker recognition evaluation data in order to evaluate the impact of the proposed improvements in terms of efficiency, execution time and algorithmic complexity. Considering a baseline system with an Equal Error Rate (EER) of 9.6% on the NIST 2005 evaluation, the best tree-based configuration achieves an EER of 12.9%, with a computational cost adapted to embedded devices and an execution time suitable for real-time speaker identification.

Real-time speaker identification and verification

In speaker identification, most of the computation originates from the distance or likelihood computations between the feature vectors of the unknown speaker and the models in the database. The identification time depends on the number of feature vectors, their dimensionality, the complexity of the speaker models and the number of speakers. In this paper, we concentrate on optimizing vector quantization (VQ) based speaker identification. We reduce the number of test vectors by pre-quantizing the test sequence prior to matching, and the number of speakers by pruning out unlikely speakers during the identification process. The best variants are then generalized to Gaussian mixture model (GMM) based modeling. We apply the algorithms also to efficient cohort set search for score normalization in speaker verification. We obtain a speed-up factor of 16:1 in the case of VQ-based modeling with minor degradation in the identification accuracy, and 34:1 in the case of GMM-based modeling. An equal error rate of 7% can be reached in 0.84 s on average when the length of test utterance is 30.4 s.

Pitch Correlogram Clustering for Fast Speaker Identification

Gaussian mixture models (GMMs) are commonly used in text-independent speaker identification systems. However, for large speaker databases, their high computational run-time limits their use in online or real-time speaker identification situations. Two-stage identification systems, in which the database is partitioned into clusters based on some proximity criteria and only a single-cluster GMM is run in every test, have been suggested in literature to speed up the identification process. However, most clustering algorithms used have shown limited success, apparently because the clustering and GMM feature spaces used are derived from similar speech characteristics. This paper presents a new clustering approach based on the concept of a pitch correlogram that captures frame-to-frame pitch variations of a speaker rather than short-time spectral characteristics like cepstral coefficient, spectral slopes, and so forth. The effectiveness of this two-stage identification process is demonstrated on the IVIE corpus of 110 speakers. The overall system achieves a run-time advantage of 500% as well as a 10% reduction of error in overall speaker identification.