The second ‘chime’ speech separation and recognition challenge: Datasets, tasks and baselines

By Emmanuel Vincent, Jon Barker, Shinji Watanabe, Jonathan Le Roux, F. Nesta, M. Matassoni. 2013

315 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Evaluation & Benchmarks, 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 Evaluation & Benchmarks

In Speech & Audio

In Signal Processing

Citations in the corpus

CHiME-6 Challenge: Tackling Multispeaker Speech Recognition for Unsegmented Recordings (2020, neutral): “The CHiME-1 [15] and CHiME-2 [16] challenges and corpora have contributed to popularizing research on this topic, together with the DICIT [17], Sweet-Home [18], and DIRHA [19] corpora.”
Voice Separation with an Unknown Number of Multiple Speakers (2020, methodology): “A phase-sensitive objective function with an LSTM neural network was presented in Erdogan et al. (2015), showing an improvement of SDR over the CHiME-2 (Vincent et al., 2013) dataset.”
Looking to listen at the cocktail party (2018, neutral): “When trained and evaluated on the CHiME-2 dataset [Vincent et al. 2013], which is widely used for speech enhancement work, our AO base-line achieved a signal-to-distortion ratio of 14.6 dB, nearly as good as the state-of-the-art single channel result of 14.75 dB reported by Erdogan et al. [2015].”
End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks (2017, background): “The last corpus was the 2nd CHiME speech separation and recognition challenge (CHiME2) medium vocabulary track database [62], which is a”
Speech acoustic modeling from raw multichannel waveforms (2015, background): “Results from the recent REVERB [6] and CHIME [7] challenges demonstrate how these techniques can be used in combination, e.g. [8] who combine a speech enhancement frontend comprised of linear prediction derever-beration, beamforming, and model-based noise reduction at the input to an ASR system.”
Filterbank learning for deep neural network based polyphonic sound event detection (2016, background): “In addition, the speech samples are the clean samples from the training set (all speakers) of the 2nd CHiME challenge [33] and the music samples are 15-20 second randomly selected excerpts from music tracks with various genres [34].”
Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modelling (2014, methodology): “Experiments are performed using the database of the medium-vocabulary recognition track of the 2nd CHiME Speech Separation and Recognition Challenge [7].”
Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks (2015, methodology): “To investigate the performance of various ideal masking functions and filters, we performed oracle experiments on the CHiME-2 development set [19].”
Recurrent deep neural networks for robust speech recognition (2014, methodology): “Track 2 of the 2 CHiME challenge [24] is a medium vocabulary (5k) task under reverberated and noisy environment.”
Hearing aid Research Data Set for Acoustic Environment Recognition (2020, methodology): “, the CHiME challenges for automatic speech recognition [7, 8], the MIREX challenge for music information retrieval (MIR) [9], an MIR database called GTZAN [10], a wind database by the RWTH Aachen [11]).”
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR (2015, methodology): “Our methods are evaluated on the corpus of the 2nd CHiME Speech Separation and Recognition Challenge (Track 2: medium vocabulary) [13].”
Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks (2015, methodology): “The proposed models were evaluated on the mediumvocabulary track in 2nd CHiME speech separation and recognition challenge[12].”
Can we Automatically Transform Speech Recorded on Common Consumer Devices in Real-World Environments into Professional Production Quality Speech?—A Dataset, Insights, and Challenges (2015, methodology): “To get around these consistency and labor intensive issues, we could take a more typical approach [18]–[20] used in cre-”