The effects on speech intelligibility and sound quality of two noise-reduction algorithms were compared: a deep recurrent neural network (RNN) and spectral subtraction (SS). The RNN was trained using sentences spoken by a large number of talkers with a variety of accents, presented in babble. Different talkers were used for testing. Participants with mild-to-moderate hearing loss were tested. Stimuli were given frequency-dependent linear amplification to compensate for the individual hearing losses. A paired-comparison procedure was used to compare all possible combinations of three conditions. The conditions were: speech in babble with no processing (NP) or processed using the RNN or SS. In each trial, the same sentence was played twice using two different conditions. The participants indicated which one was better and by how much in terms of speech intelligibility and (in separate blocks) sound quality. Processing using the RNN was significantly preferred over NP and over SS processing for both subjective intelligibility and sound quality, although the magnitude of the preferences was small. SS processing was not significantly preferred over NP for either subjective intelligibility or sound quality. Objective computational measures of speech intelligibility predicted better intelligibility for RNN than for SS or NP.
References
1.
Abadi
, M.
, Agarwal
, A.
, Barham
, P.
, Brevdo
, E.
, Chen
, Z.
, Citro
, C.
, Corrado
, G. S.
, Davis
, A.
, Dean
, J.
, Devin
, M.
, Ghemawat
, S.
, Goodfellow
, I.
, Harp
, A.
, Irving
, G.
, Isard
, M.
, Jia
, Y.
, Jozefowicz
, R.
, Kaiser
, L.
, Kudlur
, M.
, Levenberg
, J.
, Mane
, D.
, Monga
, R.
, Moore
, S.
, Murray
, D.
, Olah
, C.
, Schuster
, M.
, Shlens
, J.
, Steiner
, B.
, Sutskever
, I.
, Talwar
, K.
, Tucker
, P.
, Vanhoucke
, V.
, Vasudevan
, V.
, Viegas
, F.
, Vinyals
, O.
, Warden
, P.
, Wattenberg
, M.
, Wicke
, M.
, Yu
, Y.
, and Zheng
, X.
(2016
). “TensorFlow: Large-scale machine learning on heterogeneous distributed systems
,” arXiv:1603.004467.2.
Alcántara
, J. I.
, Moore
, B. C. J.
, Kühnel
, V.
, and Launer
, S.
(2003
). “Evaluation of the noise reduction system in a commercial digital hearing aid
,” Int. J. Audiol.
42
, 34
–42
.3.
Allen
, J. B.
(1977
). “Short term spectral analysis, synthesis and modification by discrete Fourier transform
,” IEEE Trans. Acoust. Speech Signal Process.
25
, 235
–238
.4.
Arehart
, K. H.
, Hansen
, J. H.
, Gallant
, S.
, and Kalstein
, L.
(2003
). “Evaluation of an auditory masked threshold noise suppression algorithm in normal-hearing and hearing-impaired listeners
,” Speech Commun.
40
, 575
–592
.5.
Bentler
, R.
, Wu
, Y. H.
, Kettel
, J.
, and Hurtig
, R.
(2008
). “Digital noise reduction: Outcomes from laboratory and field studies
,” Int. J. Audiol.
47
, 447
–460
.6.
Bolner
, F.
, Goehring
, T.
, Monaghan
, J. J.
, Van Dijk
, B.
, Wouters
, J.
, and Bleeck
, S.
(2016
). “Speech enhancement based on neural networks applied to cochlear implant coding strategies
,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
, IEEE, Shanghai, China
, pp. 6520
–6524
.7.
Bramsløw
, L.
, Naithani
, G.
, Hafez
, A.
, Barker
, T.
, Pontoppidan
, N. H.
, and Virtanen
, T.
(2018
). “Improving competing voices segregation for hearing impaired listeners using a low-latency deep neural network algorithm
,” J. Acoust. Soc. Am.
144
, 172
–185
.8.
Brons
, I.
, Houben
, R.
, and Dreschler
, W. A.
(2012
). “Perceptual effects of noise reduction by time-frequency masking of noisy speech
,” J. Acoust. Soc. Am.
132
, 2690
–2699
.9.
Chen
, J.
, and Wang
, D.
(2017
). “Long short-term memory for speaker generalization in supervised speech separation
,” J. Acoust. Soc. Am.
141
, 4705
–4714
.10.
Chen
, J.
, Wang
, Y.
, Yoho
, S. E.
, Wang
, D.
, and Healy
, E. W.
(2016
). “Large-scale training to increase speech intelligibility for hearing-impaired listeners in novel noises
,” J. Acoust. Soc. Am.
139
, 2604
–2612
.11.
Cienkowski
, K. M.
, and Speaks
, C.
(2000
). “Subjective vs. objective intelligibility of sentences in listeners with hearing loss
,” J. Speech Lang. Hear. Res.
43
, 1205
–1210
.12.
Delfarah
, M.
, and Wang
, D. L.
(2017
). “Features for masking-based monaural speech separation in reverberant conditions
,” IEEE Trans. Audio, Speech Lang. Proc.
25
, 1085
–1094
.13.
Elberling
, C.
, Ludvigsen
, C.
, and Keidser
, G.
(1993
). “The design and testing of a noise reduction algorithm based on spectral subtraction
,” Scand. Audiol.
Suppl. 38
, 39
–49
.14.
Festen
, J. M.
, and Plomp
, R.
(1990
). “Effects of fluctuating noise and interfering speech on the speech-reception threshold for impaired and normal hearing
,” J. Acoust. Soc. Am.
88
, 1725
–1736
.15.
Gerkmann
, T.
, and Hendriks
, R. C.
(2013
). “Unbiased MMSE-based noise power estimation with low complexity and low tracking delay
,” IEEE Trans. Audio, Speech Lang. Process.
20
, 1383
–1393
.16.
Glasberg
, B. R.
, and Moore
, B. C. J.
(1990
). “Derivation of auditory filter shapes from notched-noise data
,” Hear. Res.
47
, 103
–138
.17.
Goehring
, T.
, Bolner
, F.
, Monaghan
, J. J.
, van Dijk
, B.
, Zarowski
, A.
, and Bleeck
, S.
(2017
). “Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users
,” Hear. Res.
344
, 183
–194
.18.
Goehring
, T.
, Chapman
, J. L.
, Bleeck
, S.
, and Monaghan
, J. J. M.
(2018
). “Tolerable delay for speech production and perception: Effects of hearing ability and experience with hearing aids
,” Int. J. Audiol.
57
, 61
–68
.19.
Graves
, A.
, Mohamed
, A. R.
, and Hinton
, G.
(2013
). “Speech recognition with deep recurrent neural networks
,” in IEEE International Conference on Acoustics, Speech and Signal Processing
, IEEE
, pp. 6645
–6649
.20.
Green
, D. M.
, and Swets
, J. A.
(1974
). Signal Detection Theory and Psychophysics
(Krieger
, New York
), p. 479
.21.
Hamacher
, V.
, Chalupper
, J.
, Eggers
, J.
, Fischer
, E.
, Kornagel
, U.
, Puder
, H.
, and Rass
, U.
(2005
). “Signal processing in high-end hearing aids: State of the art, challenges, and future trends
,” EURASIP J. Appl. Signal Process.
18
, 2915
–2929
.22.
Hawkins
, D. B.
, and Yacullo
, W. S.
(1984
). “Signal-to-noise ratio advantage of binaural hearing aids and directional microphones under different levels of reverberation
,” J. Speech Hear. Disord.
49
, 278
–286
.23.
Healy
, E. W.
, Delfarah
, M.
, Vasko
, J. L.
, Carter
, B. L.
, and Wang
, D.
(2017
). “An algorithm to increase intelligibility for hearing-impaired listeners in the presence of a competing talker
,” J. Acoust. Soc. Am.
141
, 4230
–4239
.24.
Healy
, E. W.
, Yoho
, S. E.
, Chen
, J.
, Wang
, Y.
, and Wang
, D.
(2015
). “An algorithm to increase speech intelligibility for hearing-impaired listeners in novel segments of the same noise type
,” J. Acoust. Soc. Am.
138
, 1660
–1669
.25.
Healy
, E. W.
, Yoho
, S. E.
, Wang
, Y.
, and Wang
, D.
(2013
). “An algorithm to improve speech recognition in noise for hearing-impaired listeners
,” J. Acoust. Soc. Am.
134
, 3029
–3038
.26.
Hinton
, G. E.
, Osindero
, S.
, and Teh
, Y. W.
(2006
). “A fast learning algorithm for deep belief nets
,” Neur. Comput.
18
, 1527
–1554
.27.
Hochreiter
, S.
, and Schmidhuber
, J.
(1997
). “Long short-term memory
,” Neur. Comput.
9
, 1735
–1780
.28.
Hu
, Y.
, and Loizou
, P. C.
(2007a
). “A comparative intelligibility study of single-microphone noise reduction algorithms
,” J. Acoust. Soc. Am.
122
, 1777
–1786
.29.
Hu
, Y.
, and Loizou
, P. C.
(2007b
). “Subjective comparison and evaluation of speech enhancement algorithms
,” Speech Commun.
49
, 588
–601
.30.
Huang
, P. S.
, Kim
, M.
, Hasegawa-Johnson
, M.
, and Smaragdis
, P.
(2015
). “Joint optimization of masks and deep recurrent neural networks for monaural source separation
,” IEEE Trans. Audio, Speech Lang. Proc.
23
, 2136
–2147
.31.
Itakura
, F.
, and Saito
, S.
(1968
). “Analysis synthesis telephony based on the maximum likelihood method
,” in International Congress on Acoustics
, ICA, Tokyo, Japan
, pp. C17
–C20
.32.
Jamieson
, D. G.
, Brennan
, R. L.
, and Cornelisse
, L. E.
(1995
). “Evaluation of a speech enhancement strategy with normal-hearing and hearing-impaired listeners
,” Ear Hear.
16
, 274
–286
.33.
Jørgensen
, S.
, Ewert
, S. D.
, and Dau
, T.
(2013
). “A multi-resolution envelope-power based model for speech intelligibility
,” J. Acoust. Soc. Am.
134
, 436
–446
.34.
Kamath
, S.
, and Loizou
, P. C.
(2002
). “A multi-band spectral subtraction method for enhancing speech corrupted by colored noise
,” in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
, IEEE, Orlando, FL
, pp. 1
–4
.35.
Kates
, J. M.
(1987
). “The short-time articulation index
,” J. Rehabil. Res. Dev.
24
, 271
–276
.36.
Kates
, J. M.
, and Arehart
, K. H.
(2014
). “The hearing-aid speech quality index (HASQI) version 2
,” J. Audio Eng. Soc.
62
, 99
–117
.37.
Keshavarzi
, M.
, Goehring
, T.
, Zakis
, J.
, Turner
, R. E.
, and Moore
, B. C. J.
(2018
). “Use of a deep recurrent neural network to reduce wind noise: Effects on judged speech intelligibility and sound quality
,” Trends Hear.
22
, 1
–12
.38.
Kim
, G.
, Lu
, Y.
, Hu
, Y.
, and Loizou
, P. C.
(2009
). “An algorithm that improves speech intelligibility in noise for normal-hearing listeners
,” J. Acoust. Soc. Am.
126
, 1486
–1494
.39.
Kolbæk
, M.
, Yu
, D.
, Tan
, Z. H.
, and Jensen
, J.
(2017
). “Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks
,” IEEE Trans. Audio, Speech Lang. Proc.
25
, 1901
–1913
.40.
Krawczyk
, M.
, and Gerkmann
, T.
(2014
). “STFT phase reconstruction in voiced speech for an improved single-channel speech enhancement
,” IEEE/ACM Trans. Audio, Speech, Lang. Process.
22
, 1931
–1940
.41.
Launer
, S.
, Zakis
, J.
, and Moore
, B. C. J.
(2016
). “Hearing aid signal processing
,” in Hearing Aids
, edited by G. R.
Popelka
, B. C. J.
Moore
, A. N.
Popper
, and R. R.
Fay
(Springer
, New York
), pp. 93
–130
.42.
Levitt
, H.
, Bakke
, M.
, Kates
, J.
, Neuman
, A.
, Schwander
, T.
, and Weiss
, M.
(1993
). “Signal processing for hearing impairment
,” Scand. Audiol.
Suppl. 38
, 7
–19
.43.
Lipton
, Z. C.
, Berkowitz
, J.
, and Elkan
, C.
(2015
). “A critical review of recurrent neural networks for sequence learning
,” arXiv:1506.00019v4.44.
Loizou
, P. C.
(2007
). Speech Enhancement: Theory and Practice
(CRC Press
, Boca Raton, LA
), p. 632
.45.
Ma
, J.
, Hu
, Y.
, and Loizou
, P. C.
(2009
). “Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions
,” J. Acoust. Soc. Am.
125
, 3387
–3405
.46.
Monaghan
, J. J.
, Goehring
, T.
, Yang
, X.
, Bolner
, F.
, Wang
, S.
, Wright
, M. C.
, and Bleeck
, S.
(2017
). “Auditory inspired machine learning techniques can improve speech intelligibility and quality for hearing-impaired listeners
,” J. Acoust. Soc. Am.
141
, 1985
–1998
.47.
Moore
, B. C. J.
(2007
). Cochlear Hearing Loss: Physiological, Psychological and Technical Issues
, 2nd ed. (Wiley
, Chichester, UK
), p. 332
.48.
Moore
, B. C. J.
, Baer
, T.
, Ives
, D. T.
, Marriage
, J.
, and Salorio-Corbetto
, M.
(2016
). “Effects of modified hearing-aid fittings on loudness and tone quality for different acoustic scenes
,” Ear Hear.
37
, 483
–491
.49.
Moore
, B. C. J.
, and Glasberg
, B. R.
(1998
). “Use of a loudness model for hearing aid fitting. I. Linear hearing aids
,” Br. J. Audiol.
32
, 317
–335
.50.
Moore
, B. C. J.
, and Sek
, A.
(2013
). “Comparison of the CAM2 and NAL-NL2 hearing-aid fitting methods
,” Ear Hear.
34
, 83
–95
.51.
Moore
, B. C. J.
, and Sek
, A.
(2016
). “Comparison of the CAM2A and NAL-NL2 hearing-aid fitting methods for participants with a wide range of hearing losses
,” Int. J. Audiol.
55
, 93
–100
.52.
Natarajan
, A.
, Hansen
, J. H.
, Arehart
, K. H.
, and Rossi-Katz
, J.
(2005
). “An auditory-masking-threshold-based noise suppression algorithm GMMSE-AMT[ERB] for listeners with sensorineural hearing loss
,” EURASIP J. Adv. Signal Process.
18
, 2938
–2953
.53.
Patterson
, R. D.
, Allerhand
, M. H.
, and Giguère
, C.
(1995
). “Time-domain modeling of peripheral auditory processing: A modular architecture and a software platform
,” J. Acoust. Soc. Am.
98
, 1890
–1894
.54.
Peters
, R. W.
, Moore
, B. C. J.
, and Baer
, T.
(1998
). “Speech reception thresholds in noise with and without spectral and temporal dips for hearing-impaired and normally hearing people
,” J. Acoust. Soc. Am.
103
, 577
–587
.55.
Picou
, E. M.
, Aspell
, E.
, and Ricketts
, T. A.
(2014
). “Potential benefits and limitations of three types of directional processing in hearing aids
,” Ear Hear.
35
, 339
–352
.56.
Picou
, E. M.
, and Ricketts
, T. A.
(2017
). “How directional microphones affect speech recognition, listening effort and localisation for listeners with moderate-to-severe hearing loss
,” Int. J. Audiol.
56
, 909
–918
.57.
Plomp
, R.
(1978
). “Auditory handicap of hearing impairment and the limited benefit of hearing aids
,” J. Acoust. Soc. Am.
63
, 533
–549
.58.
Poulton
, E. C.
(1979
). “Models for the biases in judging sensory magnitude
,” Psychol. Bull.
86
, 777
–803
.59.
Relano-Iborra
, H.
, May
, T.
, Zaar
, J.
, Scheidiger
, C.
, and Dau
, T.
(2016
). “Predicting speech intelligibility based on a correlation metric in the envelope power spectrum domain
,” J. Acoust. Soc. Am.
140
, 2670
–2679
.60.
Riedmiller
, M.
, and Braun
, H.
(1993
). “A direct adaptive method for faster backpropagation learning: The RPROP algorithm
,” in IEEE Conference on Neural Networks
, pp. 586
–591
.61.
Sak
, H.
, Senior
, A.
, and Beaufays
, F.
(2014
). “Long short-term memory recurrent neural network architectures for large scale acoustic modeling
,” in Interspeech 2014
, pp. 338
–342
.62.
Stone
, M. A.
, and Moore
, B. C. J.
(1999
). “Tolerable hearing-aid delays. I. Estimation of limits imposed by the auditory path alone using simulated hearing losses
,” Ear Hear.
20
, 182
–192
.63.
Stone
, M. A.
, and Moore
, B. C. J.
(2002
). “Tolerable hearing-aid delays. II. Estimation of limits imposed during speech production
,” Ear Hear.
23
, 325
–338
.64.
Stone
, M. A.
, and Moore
, B. C. J.
(2005
). “Tolerable hearing-aid delays: IV. Effects on subjective disturbance during speech production by hearing-impaired subjects
,” Ear Hear.
26
, 225
–235
.65.
Taal
, C.
, Hendriks
, R.
, Heusdens
, R.
, and Jensen
, J.
(2011
). “An algorithm for intelligibility prediction of time-frequency weighted noisy speech
,” IEEE Trans. Audio, Speech Lang. Proc.
19
, 2125
–2136
.66.
Tang
, Y.
(2016
). “TF. Learn: TensorFlow's high-level module for distributed machine learning
,” arXiv:1612.04251.67.
Wang
, Y.
, Narayanan
, A.
, and Wang
, D.
(2014
). “On training targets for supervised speech separation
,” IEEE Trans. Audio, Speech Lang. Proc.
22
, 1849
–1858
.68.
Weninger
, F.
, Erdogan
, H.
, Watanabe
, S.
, Vincent
, E.
, Le Roux
, J.
, Hershey
, J. R.
, and Schuller
, B.
(2015
). “Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR
,” in International Conference on Latent Variable Analysis and Signal Separation
, Springer, Liberec, Czech Republic
.69.
Williamson
, D. S.
, Wang
, Y.
, and Wang
, D.
(2016
). “Complex ratio masking for monaural speech separation
,” IEEE/ACM Trans. Audio, Speech, Lang. Process.
24
, 483
–492
.© 2019 Acoustical Society of America.
2019
Acoustical Society of America
You do not currently have access to this content.