Text-independent speaker identification through feature fusion and deep neural network

R Jahangir, YW Teh, NA Memon, G Mujtaba… - IEEE …, 2020 - ieeexplore.ieee.org
Speaker identification refers to the process of recognizing human voice using artificial
intelligence techniques. Speaker identification technologies are widely applied in voice …

An end-to-end speech accent recognition method based on hybrid ctc/attention transformer asr

Q Gao, H Wu, Y Sun, Y Duan - ICASSP 2021-2021 IEEE …, 2021 - ieeexplore.ieee.org
This paper proposes a novel accent recognition system in the framework of a transformer-
based end-to-end speech recognition system. To incorporate the pronunciation and …

Language identification-based evaluation of single channel speech separation of overlapped speeches

Z Aysa, M Ablimit, H Yilahun, A Hamdulla - Information, 2022 - mdpi.com
In multi-lingual, multi-speaker environments (eg, international conference scenarios),
speech, language, and background sounds can overlap. In real-world scenarios, source …

DFNet: Decoupled Fusion Network for Dialectal Speech Recognition

Q Zhu, L Gao, L Qin - Mathematics, 2024 - mdpi.com
Deep learning is often inadequate for achieving effective dialect recognition in situations
where data are limited and model training is complex. Differences between Mandarin and …

Accent recognition by native language using mel-frequency cepstral coefficient and K-Nearest neighbor

DS Widyowaty, A Sunyoto - 2020 3rd International Conference …, 2020 - ieeexplore.ieee.org
Almost all the world use English to communicate. English accents appear in various parts of
the world. Every Country that communicates in English has a different accent, for example …

[PDF][PDF] Speaker Recognition Based on 3DCNN-LSTM.

ZF Hu, XT Si, Y Luo, SS Tang, F Jian - Engineering Letters, 2021 - engineeringletters.com
The traditional speaker recognition method reduces the feature signal from high to low
dimensions, but this often leads to some speaker information loss, resulting in a low speaker …

基于对比预测编码模型的多任务学习语种识别方法.

赵建川, 杨浩铨, 徐勇, 吴恋… - … /Shu Ju Cai Ji Yu Chu Li, 2022 - search.ebscohost.com
语种识别的关键是从语音片段中提取有用的特征. 通过延时神经网络(Time‑delayed neural
network, TDNN) 可以提取包含丰富上下文信息的特征向量, 有效提高系统性能 …

[PDF][PDF] Supervised Learning Approaches for Language and Speaker Recognition

S Ramoji - 2023 - leap.ee.iisc.ac.in
In the age of artificial intelligence, it is important for machines to figure out who is speaking
automatically and in what language-a task humans are naturally capable of. Developing …

English accent detection using hidden Markov model (HMM)

B Sallagundla, KS Gogineni… - Applied Data Science and …, 2025 - taylorfrancis.com
Machine learning techniques are widely used for accent classification. Due to the accent, the
pronunciation differs, and that leads others to think of it as a different language. In this case …

Speaker voice recognition using feature selection and SVM classification

HEK Al Ghazi - 2022 - openaccess.altinbas.edu.tr
Gender recognition based solely on the speaker's voice is a fairly simple task for any human
being, however, it's not as simple as it is for humans compared to any computing systems …