Deep Neural Networks for Single-Channel Multi-Talker Speech Recognition

By Chao Weng, Dong Yu, M. Seltzer, Jasha Droppo. 2015

101 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. Nima Mesgarani
5. Yi Luo
6. Zhuo Chen
7. Marc Delcroix
8. John R. Hershey

In Signal Processing

1. Jinyu Li
2. Shinji Watanabe
3. Dong Yu
4. Nima Mesgarani
5. Yi Luo
6. Zhuo Chen
7. Deliang Wang
8. Marc Delcroix

Citations in the corpus

• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation (2018, background): “s and wearable hearing and telecommunication devices. Conv-TasNet can also serve as a front-end module for tandem systems in other audio processing tasks, such as multitalker speech recognition [61], [62], [63], [64] and speaker identification [65], [66]. On the other hand, several limitations of Tas”
• Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural Networks (2017, methodology): “A natural, and commonly used, approach for deep learning based speech separation is to cast the problem as a multi-class [30], [35], [46] regression problem as depicted in Fig.”
• A Survey on Deep Learning (2018, methodology): “A DNN-based approach is proposed to attack the single-channel multitalker speech recognition problem in [165].”
• Recent progresses in deep learning based acoustic models (2017, methodology): “It is well known that the current ASR systems perform poorly when the speech is corrupted with heavy noise or interfering speech [122], [123].”
• Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures (2017, background): “This ambiguity can be avoided if the target signal has a special characteristic as being the most dominant one [14] or having a specific gender [15].”
• Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals (2020, background): “Multi-speaker speech recognition Multi-speaker speech recognition [44, 50, 31, 33], which aims to directly recognize the texts of each individual speaker from the mixture speech, has recently become a hot topic.”
• A Deep Ensemble Learning Method for Monaural Speech Separation (2016, background): “A solution is important for a wide range of applications, such as speech communication, speech coding, speaker recognition, and speech recognition (e.g. [23], [33]).”
• Wavesplit: End-to-End Speech Separation by Speaker Clustering (2020, unknown): “This experiment stems from research prior to PIT (Weng et al., 2015) which suggested that average energy was a good rule for channel assignment, applicable when one channel consistently dominates the other.”