Deep Neural Network Embeddings for Text-Independent Speaker Verification

By David Snyder, Daniel Garcia-Romero, Daniel Povey, Sanjeev Khudanpur. 2017

796 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

VoxCeleb2: Deep Speaker Recognition (2018, background): “The success of deep learning in computer vision and speech recognition has motivated the use of deep neural networks (DNN) as feature extractors combined with classifiers, though not trained end-to-end [15, 16, 17, 18, 19].”
Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge (2018, background): “Since that initial report, x-vectors have improved performance significantly with multiclass discriminative training [8] and augmented training data [9].”
Speaker Recognition for Multi-speaker Conversations Using X-vectors (2019, methodology): “The architecture is based on the DNN embedding system described in [1, 10].”
Unspeech: Unsupervised Speech Context Embeddings (2018, background): “Recently, supervised neural network based speaker embeddings also showed good speaker discriminative properties [6, 7, 8], particularly on short utterances.”
Interpretable Convolutional Filters with SincNet (2018, background): “employed in many state-of-the-art systems [19, 20, 21], directly feeding a CNN with spectrogram bins [22, 23, 24] or even with raw audio samples [25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37] is an approach of increasing popularity.”
Attentive Statistics Pooling for Deep Speaker Embedding (2018, methodology): “Probabilistic linear discriminant analysis (PLDA) [13, 14] can also be used for measuring the distance between two utterance-level features [9, 10].”
Approaches to Multi-domain Language Recognition (2018, background): “Recent work in [3, 4] has shown significant advances in the related field of speaker recognition by replacing the i-vector extraction process with speaker embeddings extracted from a DNN trained to directly discriminate speakers.”
Voxceleb: Large-scale speaker verification in the wild (2020, methodology): “, 2017), or a 1D CNN with convolutions applied only to the time domain (Snyder et al., 2017; Shon et al., 2018; Okabe et al., 2018; Snyder et al., 2018).”
In defence of metric learning for speaker recognition (2020, background): “A range of encoders have been proposed to aggregate frame-level informations into utterance-level embeddings, from simple averaging [1] to statistical pooling [4, 7] and dictionary-based encodings [17, 34].”
Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching (2018, background): “Sheffert and Olson [40] suggested that visual information about a person’s particular idiosyncratic speaking style is related to the speaker’s auditory attributes.”
Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification (2018, methodology): “We use the same type of PLDA backend as [16, 17] for comparing pairs of embeddings.”
Teacher-Student Training for Text-Independent Speaker Recognition (2018, methodology): “The x-vec setting follows configuration of a DNN embedding system proposed in [9] and [20].”
X-Vectors: Robust DNN Embeddings for Speaker Recognition (2018, methodology): “This paper builds on our recent DNN embedding architecture [1].”
The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021 (2021, background): “The vanilla idea to achieve this purpose is by calculating the mean and standard derivation along the time axis [15].”
ADI17: A Fine-Grained Arabic Dialect Identification Dataset (2020, methodology): “Details of the DNN structure were described in [19].”