Advances in deep neural network approaches to speaker recognition

By Mitchell McLaren, Yun Lei, Luciana Ferrer. 2015

129 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation (2018, background): “nication devices. Conv-TasNet can also serve as a front-end module for tandem systems in other audio processing tasks, such as multitalker speech recognition [57]–[60] and speaker identiﬁcation [61], [62]. On the other hand, several limitations of Conv-TasNet must be addressed before it can be actua”
Learning Speaker Representations with Mutual Information (2018, background): “Deep learning has shown remarkable success in numerous speech tasks, including speech recognition [1–4] and speaker recognition [5, 6].”
Speaker recognition based on deep learning: An overview (2020, methodology): “One can find that no matter whether we apply BNF alone [41] or concatenate it with other acoustic features [39], DNN-BNF/i-vector can significantly outperform the conventional GMM/i-vector, which indicates the effectiveness of the framework [36].”
X-Vectors: Robust DNN Embeddings for Speaker Recognition (2018, methodology): “This i-vector system incorporates phonetic bottleneck features (BNF) from an ASR DNN acoustic model and is similar to [9].”
Attentive Statistics Pooling for Deep Speaker Embedding (2018, methodology): “In early studies [2, 3], deep neural networks (DNNs) derived from acoustic models for ASR have been employed as a universal background model (UBM) to provide phoneme posteriors as well as bottleneck features, which are used for, respectively, zeroth- and first-order statistics in i-vector extraction”
Speaker Recognition from Raw Waveform with SincNet (2018, background): “Deep learning has shown remarkable success in numerous speech tasks [4–7], including recent studies in speaker recognition [8, 9].”
Delving into VoxCeleb: environment invariant speaker recognition (2019, methodology): “search [15, 16], these techniques have not been commonly applied to deep learning based methods since they require direct update of model statistics such as mean and covariance of GMM. As reported in [17, 18], the use of mid-level features of DNN has generally yielded higher performance compared to ”
A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification (2018, background): “Each component in the dictionary represents a phoneme (or senone) physically, and the statistics is accumulated through senone posteriors, as is done in recently popular DNN i-vector approach [8, 9, 10].”