A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research

Eurasip Journal on Advances in Signal Processing

Volumn 2016, Issue 1, 2016, Pages 1-19

  Kinoshita, Keisuke ^a   Delcroix, Marc ^a   Gannot, Sharon ^b   P Habets, Emanuël A ^c   Haeb Umbach, Reinhold ^d   Kellermann, Walter ^e   Leutnant, Volker ^d   Maas, Roland ^e   Nakatani, Tomohiro ^a   Raj, Bhiksha ^f   Sehr, Armin ^g   Yoshioka, Takuya ^a  

^a Nippon Telegraph and Telephone Corporation   (Japan)

^b BAR ILAN UNIVERSITY   (Israel)

^c INTERNATIONAL AUDIO LABORATORIES ERLANGEN   (Germany)

^d UNIVERSITY OF PADERBORN   (Germany)

^e UNIVERSITY OF ERLANGEN NUREMBERG   (Germany)

^f CARNEGIE MELLON UNIVERSITY   (United States)

^g UNIVERSITY OF APPLIED SCIENCES REGENSBURG   (Germany)

Author keywords

Automatic speech recognition; Dereverberation; Evaluation campaign; REVERB challenge; Reverberation

Indexed keywords

REVERBERATION; SIGNAL PROCESSING; SPEECH; SPEECH ENHANCEMENT; SPEECH PROCESSING;

AUTOMATIC SPEECH RECOGNITION; DEREVERBERATION; EVALUATION CAMPAIGN; FUTURE RESEARCH DIRECTIONS; MULTICHANNEL DEREVERBERATION; REVERB CHALLENGE; SPEECH SIGNAL PROCESSING; STATE-OF-THE-ART TECHNIQUES;

SPEECH RECOGNITION;

EID: 84955495546     PISSN: 16876172     EISSN: 16876180     Source Type: Journal    
DOI: 10.1186/s13634-016-0306-6     Document Type: Article

References (49)

1. I Tashev, Sound capture and processing (Wiley, New Jersey, 2009).
2. X Huang, A Acero, H-W Hong, Spoken language processing: a guide to theory, algorithm and system development (Prentice Hall, New Jersey, 2001).
3. M Wölfel, J McDonough, Distant speech recognition (Wiley, New Jersey, 2009).
4. PA Naylor, ND Gaubitch, Speech dereverberation (Springer, Berlin, 2010).
5. T Yoshioka, A Sehr, M Delcroix, K Kinoshita, R Maas, T Nakatani, W Kellermann, Making machines understand us in reverberant rooms: robustness against reverberation for automatic speech recognition. IEEE Signal Process. Mag.29(6), 114–126 (2012).
6. K Kinoshita, M Delcroix, T Yoshioka, T Nakatani, E Habets, R Haeb-Umbach, V Leutnant, A Sehr, W Kellermann, R Maas, BR S. Gannot, in Proceedings of Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). The REVERB challenge: a common evaluation framework for dereverberation and recognition of reverberant speech, (2013).
7. REVERB Challenge Webpage. http://reverb2014.dereverberation.com/. Accessed 13 Jan 2016.
8. D Pearce, H-G Hirsch, in Proceedings of International Conference on Spoken Language Processing (ICSLP). The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions, (2000), pp. 29–32.
9. E Vincent, S Araki, FJ Theis, G Nolte, P Bofill, H Sawada, A Ozerov, BV Gowreesunker, D Lutter, The signal separation evaluation campaign (2007–2010): achievements and remaining challenges. Signal Process.92:, 1928–1936 (2012).
10. J Barker, E Vincent, N Ma, C Christensen, P Green, The PASCAL CHiME speech separation and recognition challenge. Comput. Speech and Lang.27(3), 621–633 (2013).
11. T Robinson, J Fransen, D Pye, J Foote, S Renals, in Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP). WSJCAM0: A British English speech corpus for large vocabulary continuous speech recognition, (1995), pp. 81–84.
12. M Lincoln, I McCowan, J Vepa, HK Maganti, in Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). The multi-channel Wall Street Journal audio visual corpus (MC-WSJ-AV): specification and initial experiments, (2005), pp. 357–362.
13. Y Hu, PC Loizou, Evaluation of objective quality measures for speech enhancement. IEEE Trans. Audio, Speech, Lang. Process.16(1), 229–238 (2008).
14. TH Falk, C Zheng, W-Y Chan, A non-intrusive quality and intelligibility measure of reverberant and dereverberated speech. IEEE Trans. Audio, Speech, Lang. Process.18(7), 1766–1774 (2010).
15. ITU-T Recommendation P.862: Perceptual evaluation of speech quality (PESQ): an objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs.
16. ITU-R Recommendation BS.1534: method for the subjective assessment of intermediate quality levels of coding systems.
17. MJ Alam, V Gupta, P Kenny, P Dumouchel, in Proceedings of REVERB Challenge Workshop, p2.10. Use of multiple front-ends and I-vector-based speaker adaptation for robust speech recognition, (2014).
18. RF Astudillo, S Braun, E Habets, in Proceedings of REVERB Challenge Workshop, o1.3. A multichannel feature compensation approach for robust ASR in noisy and reverberant environments, (2014).
19. B Cauchi, I Kodrasi, R Rehr, S Gerlach, A Jukić, T Gerkmann, S Doclo, S Goetze, in Proceedings of REVERB Challenge Workshop, o1.2. Joint dereverberation and noise reduction using beamforming and a single-channel speech enhancement scheme, (2014).
20. M Delcroix, T Yoshioka, A Ogawa, Y Kubo, M Fujimoto, I Nobutaka, K Kinoshita, M Espi, T Hori, T Nakatani, A Nakamura, in Proceedings of REVERB Challenge Workshop, o2.3. Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the REVERB challenge, (2014).
21. N Epain, T Noohi, C Jin, in Proceedings of REVERB Challenge Workshop, p2.7. Sparse recovery method for dereverberation, (2014).
22. X Feng, K Kumatani, J McDonough, in Proceedings of REVERB Challenge Workshop, p1.9. The CMU-MIT REVERB challenge 2014 system: description and results, (2014).
23. JT Geiger, E Marchi, BW Schuller, G Rigoll, in Proceedings of REVERB Challenge Workshop, p1.6. The TUM system for the REVERB challenge: recognition of reverberated speech using multi-channel correlation shaping dereverberation and blstm recurrent neural networks, (2014).
24. DR Gonzalez, SC Arias, JRC de Lara, in Proceedings of REVERB Challenge Workshop, p2.2. Single channel speech enhancement based on zero phase transformation in reverberated environments, (2014).
25. H-G Hirsch, in Proceedings of REVERB Challenge Workshop, p2.9. Extraction of robust features by combining noise reduction and FDLP for the recognition of noisy speech signals in hands-free mode, (2014).
26. H Kallasjoki, J Gemmeke, K Palomäki, A Beeston, G Brown, in Proceedings of REVERB Challenge Workshop, o2.1. Recognition of reverberant speech by missing data imputation and NMF feature enhancement, (2014).
27. K Kondo, in Proceedings of REVERB Challenge Workshop, p2.4. A computationally restrained and single-channel blind dereverberation method utilizing iterative spectral modifications, (2014).
28. YR Leng, J Dennis, WZT Ng, TH Dat, in Proceedings of REVERB Challenge Workshop, p2.11. PBF-GSC beamforming for ASR and speech enhancement in reverberant environments, (2014).
29. N López, G Richard, Y Grenier, I Bourmeyster, in Proceedings of REVERB Challenge Workshop, p2.3. Reverberation suppression based on sparse linear prediction in noisy environments, (2014).
30. M Mimura, S Sakai, T Kawahara, in Proceedings of REVERB Challenge Workshop, p1.8. Reverberant speech recognition combining deep neural networks and deep autoencoders, (2014).
31. V Mitra, W Wang, Y Lei, A Kathol, G Sivaraman, C Espy-Wilson, in Proceedings of REVERB Challenge Workshop, p2.5. Robust features and system fusion for reverberation-robust speech recognition, (2014).
32. M Moshirynia, F Razzazi, A Haghbin, in Proceedings of REVERB Challenge Workshop, p1.2. A speech dereverberation method using adaptive sparse dictionary learning, (2014).
33. K Ohtani, T Komatsu, T Nishino, K Takeda, in Proceedings of REVERB Challenge Workshop, p1.5. Adaptive dereverberation method based on complementary Wiener filter and modulation transfer function, (2014).
34. K Palomäki, in Proceedings of REVERB Challenge Workshop, p1.10. Reverberation robust speech recognition by matching distributions of spectrally and temporally decorrelated features, (2014).
35. PP Parada, D Sharma, PA Naylor, T van Waterschoot, in Proceedings of REVERB Challenge Workshop, p1.4. Single-channel reverberant speech recognition using C50 estimation, (2014).
36. Y Tachioka, T Narita, FJ Weninger, S Watanabe, in Proceedings of REVERB Challenge Workshop, p1.3. Dual system combination approach for various reverberant environments with dereverberation techniques, (2014).
37. J Veras, T Prego, A Lima, T Ferreira, S Netto, in Proceedings of REVERB Challenge Workshop, p1.7. Speech quality enhancement based on spectral subtraction, (2014).
38. X Wang, Y Guo, X Yang, Q Fu, Y Yan, in Proceedings of REVERB Challenge Workshop, p2.1. Acoustic scene aware dereverberation using 2-channel spectral enhancement for REVERB challenge, (2014).
39. FJ Weninger, S Watanabe, J Le Roux, J Hershey, Y Tachioka, JT Geiger, BW Schuller, G Rigoll, in Proceedings of REVERB Challenge Workshop, o1.1. The MERL/MELCO/TUM system for the REVERB challenge using deep recurrent neural network feature enhancement, (2014).
40. S Wisdom, T Powers, L Atlas, J Pitton, in Proceedings of REVERB Challenge Workshop, p1.11. Enhancement of reverberant and noisy speech by extending its coherence, (2014).
41. X Xiao, Z Shengkui, DHH Nguyen, Z Xionghu, D Jones, E-S Chng, H Li, in Proceedings of REVERB Challenge Workshop, o2.2. The NTU-ADSC systems for reverberation challenge 2014, (2014).
42. F Xiong, N Moritz, R Rehr, J Anemueller, B Meyer, T Gerkmann, S Doclo, S Goetze, in Proceedings of REVERB Challenge Workshop, p2.8. Robust ASR in reverberant environments using temporal cepstrum smoothing for speech enhancement and an amplitude modulation filterbank for feature extraction, (2014).
43. M Yu, F Soong, in Proceedings of REVERB Challenge Workshop, p2.6. Speech dereverberation by constrained and regularized multi-channel spectral decomposition: evaluated on REVERB challenge, (2014).
44. K Lebart, JM Boucher, PN Denbigh, A new method based on spectral subtraction for speech de-reverberation. Acta Acoustica. 87:, 359–366 (2001).
45. P Swietojanski, A Ghoshal, S Renals, in Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). Hybrid acoustic models for distant and multichannel large vocabulary speech recognition, (2013), pp. 285–290.
46. M Seltzer, D Yu, Y Wang, in Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP). An investigation of deep neural networks for noise robust speech recognition, (2013), pp. 7398–7402.
47. T Zernicki, M Bartkowiak, M Doma, in Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP). Enhanced coding of high-frequency tonal components in MPEG-D USAC through joint application of ESBR and sinusoidal modeling, (2011), pp. 501–504.
48. LDC Site for The Multi-channel Wall Street Journal Audio Visual Corpus (MC-WSJ-AV). https://catalog.ldc.upenn.edu/LDC2014S03. Accessed 13 Jan 2016.
49. LDC Site for WSJCAM0. https://catalog.ldc.upenn.edu/LDC95S24. Accessed 13 Jan 2016.