Deep neural network-based speaker embeddings for end-to-end speaker verification

By David Snyder, Pegah Ghahremani, Daniel Povey, Daniel Garcia-Romero, Yishay Carmiel, Sanjeev Khudanpur. 2016

362 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

Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System (2018, methodology): “In recent years, with the merit of large labeled datasets, enormous computation capability, and effective network architectures, emerging progress towards end-to-end learning opens up a new area for exploration [19, 20, 21, 22, 23].”
Neural Voice Cloning with a Few Samples (2018, methodology): “In particular, it performs binary classiﬁcation to identify whether the test audio and enrolled audios are from the same speaker [e.g., Snyder et al., 2016].”
Deep Speaker: an End-to-End Neural Speaker Embedding System (2017, methodology): “Though many algorithms have pushed the state-of-the-art over the past couple years [1][2][3][4][5][6][7], speaker recognition is still a challenging task.”
The Second DIHARD Diarization Challenge: Dataset, task, and baselines (2019, methodology): “At a high level, the system performs diarization by dividing each recording into short overlapping segments, extracting x-vectors [33, 34], scoring with probabilistic linear discriminant analysis (PLDA) [35], and clustering using agglomerative hierarchical clustering (AHC) [36].”
Speaker Recognition for Multi-speaker Conversations Using X-vectors (2019, background): “, generalized this framework to text-independent speaker recognition and inserted a temporal pooling layer into the network to handle variable-length segments [9].”
Deep Speaker Feature Learning for Text-Independent Speaker Verification (2017, methodology): “It is also different from the observation in [14], where the d-vector system obtained more performance improvement than the i-vector system when the number of speakers got very large (102k).”
X-Vectors: Robust DNN Embeddings for Speaker Recognition (2018, methodology): “, adapted this approach to a text-independent application and inserted a temporal pooling layer into the network to handle variable-length segments [17].”
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.”
Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification (2018, methodology): “The system was then adapted to the more general task of text-independent SV in [15].”
Deep Neural Network Embeddings for Text-Independent Speaker Verification (2017, methodology): “Recently, [23] showed that an end-to-end system that jointly learns embeddings along with a similarity metric could outperform a traditional i-vector baseline for text-independent SV.”
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.”
A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification (2018, background): “To deal with this issue, recently, in both [17, 18], similar temporal average pooling(TAP) layer is adopted in their neural network architectures.”
Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge (2018, methodology): “The initial system utilized i-vectors as the speaker representation, but recent work has shown that DNN-based representations called x-vectors [6] can also be effective for diarization [7].”
Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech (2021, methodology): “The proposed method was compared with state-of-the-art methods, namely, x-vector clustering with PLDA scoring and variational Bayesian resegmentation [1, 4, 6], EDA-EEND [9] and Region-Proposal Network based Speaker Diarization (RPNSD) [16].”
From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint (2020, methodology): “Among deep speaker embedding systems that are developed with various DNN architectures [17, 19, 20], we follow the ResNet-based verification system [20] in our work for embedding extraction to extract time-invariant speaker embedding.”