Speaker Diarization: A Review of Recent Research

By Xavier Anguera Miró, Simon Bozonnet, N. Evans, Corinne Fredouille, Gerald Friedland, Oriol Vinyals. 2010

756 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Speech & Audio, 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 Speech & Audio

In Signal Processing

Citations in the corpus

CHiME-6 Challenge: Tackling Multispeaker Speech Recognition for Unsegmented Recordings (2020, positive): “Agglomerative hierarchical clustering (AHC) [48] is performed.”
Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, neutral): “Meanwhile, visual information is increasingly used in historically audio-only tasks like speech transcription, voice recognition, audio spatialization [5,80,104,161], speaker diarization [10,83], and source separation [57,78,82].”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “In the speech recognition literature, this is the subtask of speaker diarisation (Miro et al., 2012; Tranter et al., 2006).”
Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone (2021, methodology): “To handle this, one approach is to first apply speaker diarization [11, 12, 13] to detect the utterance boundaries for each speaker and then perform ASR for each utterance.”
Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion (2016, methodology): “A number of diarization methods were recently proposed, e.g. [1].”
Wavesplit: End-to-End Speech Separation by Speaker Clustering (2020, neutral): “(Luo et al., 2018) 9.1 9.4 Conv-TasNet (Luo & Mesgarani, 2019) 12 This suggests that our model could address diarization (Anguera et al., 2012).”
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals (2020, methodology): “, speaker diarization [40, 1, 32]), which lose an end-to-end transduction function, unlike our proposed method.”
A Review of Speaker Diarization: Recent Advances with Deep Learning (2021, background): “In contrast, the focus of [3] was put more on speaker diarization for meeting speech and its respective challenges.”
Speaker recognition based on deep learning: An overview (2020, methodology): “he rst two layers do not use dropout while the last two layers drop 50 percent of activations after dropout, as shown in Figure 1. Regarding other conguration parameters, we used rectied linear units [21] as the non-linear activation function on hidden units and a learning rate of 0:001 with exponen”
Neural Speaker Diarization with Speaker-Wise Chain Rule (2020, background): “eaker diarization is the process of partitioning audio according to the speaker identity, which is an essential step for multispeaker audio applications such as generating written minutes of meetings [1, 2]. Related techniques have been evaluated in telephone conversations (CALLHOME [3]), meetings (”
Artificial neural network features for speaker diarization (2014, background): “It has been studied in various domains such as broadcast news [3], telephone calls [4], and more recently focusing on spontaneous meeting-room conversations [2, 5, 6].”
End-to-End Neural Speaker Diarization with Permutation-Free Objectives (2019, background): “eech segments according to the speaker identity. It is an important process for a wide variety of applications such as information retrieval from broadcast news, meetings, and telephone conversations [1, 2]. It also helps automatic speech recognition performance in multi-speaker conversation scenari”