Speaker recognition: an enhanced approach to identify singer voice using neural network

Biswas, Sharmila; Solanki, Sandeep Singh

doi:10.1007/s10772-020-09698-8

Cited by 12 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some early literature classified singing as a speech style and used speaker clustering algorithms to cluster it [5][9] [16]. In another paper [14], the author used the singing voice for speaker recognition.…”

Section: Ii．related Workmentioning

confidence: 99%

Vocal92: Audio Dataset With a Cappella Solo Singing and Speech

Zhou

2023

IEEE Access

View full text Add to dashboard Cite

Singer recognition plays a vital role in music information retrieval systems. Most songs in the singer recognition system are mixed audios of music and voice. In contrast, there is a lack of labeled a cappella solo singing data suitable for singer recognition. Text-independent singer recognition systems successfully encode audio features such as voice pitch, intensity, and timbre to achieve good performance. Most such systems are trained and evaluated using data from music with accompaniment. However, due to the influence of background music, the performance of the singer recognition model was limited. Contrarily, a powerful singer identification system can be trained and evaluated using a cappella solo singing voices with a clear and broad range of qualities. There needs to be labeled clear singing data suitable for singer recognition research. To address this issue, we present Vocal92, a multivariate a cappella solo singing and speech audio dataset spanning around 146.73 hours sourced from volunteers. Furthermore, we use two current state-of-the-art models to construct the singer recognition baseline system. In experiments, the singer recognition model developed by a cappella solo singing data performs well in both single-mode and cross-modal verification data, significantly improving related works. The dataset is accessible to everyone at https://pan.baidu.com/s/1Pn62DHfal2OOZ_5JqgGBdQ with jnz5 as the validation code. For noncommercial use, the dataset will be available free of charge at the IEEE DataPort (after acceptance).

show abstract

Section: Ii．related Workmentioning

confidence: 99%

Vocal92: Audio Dataset With a Cappella Solo Singing and Speech

Zhou

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The authors claimed that the suggested method provided a nicer recognition rate and 93.33% accuracy was achieved. [31] had proposed a multi-layer perceptron neural network to identify singers' voices. The trials for singer identifications were repeated five times in this study, and the analysis was carried out using feature extraction.…”

Section: Chen Et Al (2019)mentioning

confidence: 99%

Speaker Recognition Based on Mutated Monarch Butterfly Optimization Configured Artificial Neural Network

Namburi

M²

2022

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Speaker recognition is the process of extracting speaker-specific details from voice waves to validate the features asserted by system users; in other words, it allows voice-controlled access to a range of services. The research initiates with extraction features from voice signals and employing those features in Artificial Neural Network (ANN) for speaker recognition. Increasing the number of hidden layers and their associated neurons reduces the training error and increases the computational process's complexity. It is essential to have an optimal number of hidden layers and their corresponding, but attaining those optimal configurations through a manual or trial and the process takes time and makes the process more complex. This urges incorporating optimization approaches for finding optimal hidden layers and their corresponding neurons. The technique involve in configuring the ANN is Mutated Monarch Butterfly Optimization (MMBO). The proposed MMBO employed for configuring the ANN achieves the sensitivity of 97.5% in a real- time database that is superior to contest techniques.

show abstract

Speaker Recognition System Using Dynamic Time Warping Matching and Mel-Scale Frequency Cepstral Coefficients

Yang

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Speaker recognition: an enhanced approach to identify singer voice using neural network

Cited by 12 publications

References 11 publications

Vocal92: Audio Dataset With a Cappella Solo Singing and Speech

Vocal92: Audio Dataset With a Cappella Solo Singing and Speech

Speaker Recognition Based on Mutated Monarch Butterfly Optimization Configured Artificial Neural Network

Speaker Recognition System Using Dynamic Time Warping Matching and Mel-Scale Frequency Cepstral Coefficients

Contact Info

Product

Resources

About