Single Channel Target Speaker Extraction and Recognition with Speaker Beam

By Marc Delcroix, Kateřina Žmolíková, Keisuke Kinoshita, Atsunori Ogawa, Tomohiro Nakatani. 2018

204 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

1. Jinyu Li
2. Shinji Watanabe
3. Dong Yu
4. Li Deng
5. Zhuo Chen
6. Yossi Adi
7. Lior Wolf
8. Yoshua Bengio

In Signal Processing

1. Shinji Watanabe
2. Jinyu Li
3. Dong Yu
4. Zhuo Chen
5. Yossi Adi
6. Yusuke Fujita
7. Naoyuki Kanda
8. Marc Delcroix

Citations in the corpus

• Voice Separation with an Unknown Number of Multiple Speakers (2020, methodology): “In (Zmolikova et al., 2017; Delcroix et al., 2018) a neural network employed estimated i-vectors (Dehak et al.”
• SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures (2019, methodology): “We gradually built and refined the SpeakerBeam approach over several studies [28]–[31].”
• Continuous Speech Separation with Conformer (2020, background): “In [17, 18, 19], the additional speaker identification module is introduced to enhance the separation performance for both perceptual and recognition.”
• Personalized speech enhancement: new models and Comprehensive evaluation (2021, background): “Delcroix et al. [7] investigated the SpeakerBeam for single-channel target speaker extraction.”
• A Review of Speaker Diarization: Recent Advances with Deep Learning (2021, background): “(35) is modeled by the target speaker ASR [181, 182, 183, 71] and”
• Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches (2019, methodology): “We internally evaluated deep clustering [19], permutation invariant training [20], chimera++ networks [21], and a speakeraware neural beamformer [22, 23], but none of them successfully improved the accuracy for the CHiME-5 dataset.”
• Multimodal SpeakerBeam: Single Channel Target Speech Extraction with Audio-Visual Speaker Clues (2019, background): “, SpeakerBeam [3, 4], assume that only the audio stream (for input mixture and speaker clue) is available to extract the target speaker, and the speaker clue, i.”
• Neural Target Speech Extraction: An overview (2023, background): “These integrated TS-ASR systems avoid any explicit signal extraction step, a decision that reduces the computational cost, although such systems may be less interpretable than cascade systems.”