The PASCAL CHiME speech separation and recognition challenge

By Jon Barker, Emmanuel Vincent, Ning Ma, Heidi Christensen, Phil D. Green. 2013

272 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.”
Light Gated Recurrent Units for Speech Recognition (2018, positive): “In this sub-section we extend the results to the CHiME corpus, that is an important benchmark in the ASR field, thanks to the success of CHiME challenges [23], [66].”
The DIRHA-ENGLISH corpus and related tasks for distant-speech recognition in domestic environments (2015, background): “Along this direction, strong efforts have been spent recently by the international scientiﬁc community, through the development of corpora and challenges, such as REVERB [15], CHIME [16, 17] and ASpIRE.”
A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research (2016, background): “Although existing benchmark tasks and challenges [8–10] mainly focus on the noise robustness issue and sometimes only in a single-channel scenario, a particular novelty of the REVERB challenge is that it is carefully designed to test robustness against reverberation , based on both single-channel…”
The Automatic Speech recogition In Reverberant Environments (ASpIRE) challenge (2015, background): “The 1st CHiME Speech Separation and Recognition challenge [9] posed the task of recognizing digits and letters in spoken sentences mixed with reverberant backgrounds that were binaurally recorded in a domestic environment with no variability in the location of the speaker.”
A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, unknown): “Moreover, several source separation methods were used as pre-processing for speech recognition within a series of speech separation and recognition challenges [305].”
Batch-normalized joint training for DNN-based distant speech recognition (2016, background): “The progress in the ﬁeld was also fostered by the considerable success of some international challenges such as CHiME [5, 6] and REVERB [7].”
SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures (2019, methodology): “The noises were randomly selected from the CHiME-1 [51] and CHiME-3 [52] corpora.”
Chime-home: A dataset for sound source recognition in a domestic environment (2015, methodology): “The recordings comprise audio data previously made available for the Computational Hearing in Multisource Environments (CHiME) project [17, 18](1) .”
An analysis of environment, microphone and data simulation mismatches in robust speech recognition (2017, unknown): “Regarding ASR, the variation of the word error rate (WER) as a function of the SNR was studied in several evaluation challenges, e.g., (Hirsch and Pearce, 2000; Barker et al., 2013).”
VoiceHome-2, an extended corpus for multichannel speech processing in real homes (2019, unknown): “The ﬁrst two corpora, CHiME-1 (Barker et al., 2013) and CHiME-2 (Vincent et al., 2013) feature real noise backgrounds collected in daily situations in a family home over the course of several weeks.”
Recognition of overlapping speech using digital MEMS microphone arrays (2013, methodology): “the CHiME challenge [8], this has typically involved the artificial creation of data by convolving close-talking speech recordings with a multi-channel room impulse response and then adding noise.”
Acoustic Scene Classification: Classifying environments from the sounds they produce (2014, background): “Similar challenges have been organised in the areas of music information retrieval [36], speech recognition [5] and source separation [46].”
Deep Learning for Environmentally Robust Speech Recognition (2017, methodology): “More specifically, the 1st and 2nd CHiME databases [7], [11] include two tracks: one is for small vocabulary digit recognition based on Grid database, and the other is for LVCSR based on WSJ0; whereas the 3rd and 4th CHiME databases [8], [10] only include the data for LVCSR.”
Voices Obscured in Complex Environmental Settings (VOICES) corpus (2018, methodology): “Early CHiME datsets[3] were constructed by convolving clean speech with a simulated room response (based on measured data for 2 rooms), assuming the speaker to be 2m from the recorded audio.”
Detection and Classification of Acoustic Scenes and Events (2015, background): “Within ASR, researchers continue to advance recognition quality, in challenging audio conditions such as distant speech against noisy backgrounds [2].”
The third 'CHiME' speech separation and recognition challenge: Analysis and outcomes (2017, methodology): “The same experiment was also conducted on the background noise data from the 1st and 2nd ‘CHiME’ challenges (Barker et al., 2013), consisting of recordings from a distant microphone in a family home, containing noise from televisions and radios, children playing, vacuum cleaners, and outdoors noises”
Contaminated speech training methods for robust DNN-HMM distant speech recognition (2017, methodology): “This approach has also been adopted recently in [3, 4, 23, 24].”