Training Strategies for Own Voice Reconstruction in Hearing Protection Devices Using An In-Ear Microphone

Ohlenbusch, Mattes; Rollwage, Christian; Doclo, Simon

doi:10.1109/iwaenc53105.2022.9914801

Cited by 5 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, body-produced noise (e.g., breathing sounds, heartbeats) may be recorded by an in-ear microphone [4]. To enhance the quality of the in-ear microphone signal, several approaches have been proposed aiming at bandwidth extension, equalization and/or noise reduction, either based on signal processing [1] or supervised learning [5]. For supervised learning-based approaches large amounts of training data are typically required, which may be hard to obtain for realistic in-ear recordings.…”

Section: Introductionmentioning

confidence: 99%

“…In [8], it has been proposed to convert airborne to bone-conducted speech using a DNN that accounts for individual differences between talkers using a speaker identification system. In previous work, we have proposed to estimate the transfer characteristics between the entrance of the ear canal and the in-ear microphone using a time-invariant linear model to simulate short segments of in-ear speech for data augmentation in DNN training [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Speech-dependent Modeling of Own Voice Transfer Characteristics for In-ear Microphones in Hearables

Ohlenbusch,

Rollwage,

Doclo

2024

Proceedings of the 10th Convention of the European Acoustics Association Forum Acusticum 2023

View full text Add to dashboard Cite

Many hearables contain an in-ear microphone, which may be used to capture the own voice of its user in noisy environments. Since the in-ear microphone mostly records body-conducted speech due to ear canal occlusion, it suffers from band-limitation effects while only capturing a limited amount of external noise.To enhance the quality of the in-ear microphone signal using algorithms aiming at joint bandwidth extension, equalization, and noise reduction, it is desirable to have an accurate model of the own voice transfer characteristics between the entrance of the ear canal and the in-ear microphone. Such a model can be used, e.g., to simulate a large amount of in-ear recordings to train supervised learning-based algorithms. Since previous research on ear canal occlusion suggests that own voice transfer characteristics depend on speech content, in this contribution we propose a speech-dependent system identification model based on phoneme recognition. We assess the accuracy of simulating own voice speech by speech-dependent and speech-independent modeling and investigate how well modeling approaches are able to generalize to different talkers. Simulation results show that using the proposed speech-dependent model is preferable for simulating in-ear recordings compared to using a speech-independent model.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Speech-dependent Modeling of Own Voice Transfer Characteristics for In-ear Microphones in Hearables

Ohlenbusch,

Rollwage,

Doclo

2024

Proceedings of the 10th Convention of the European Acoustics Association Forum Acusticum 2023

View full text Add to dashboard Cite

show abstract

Modeling of speech-dependent own voice transfer characteristics for hearables with an in-ear microphone

Ohlenbusch,

Rollwage,

Doclo

2024

Acta Acust.

View full text Add to dashboard Cite

Many hearables contain an in-ear microphone, which may be used to capture the own voice of its user. However, due to the hearable occluding the ear canal, the in-ear microphone mostly records body-conducted speech, typically suffering from band-limitation effects and amplification at low frequencies. Since the occlusion effect is determined by the ratio between the air-conducted and body-conducted components of own voice, the own voice transfer characteristics between the outer face of the hearable and the in-ear microphone depend on the speech content and the individual talker. In this paper, we propose a speech-dependent model of the own voice transfer characteristics based on phoneme recognition, assuming a linear time-invariant relative transfer function for each phoneme. We consider both individual models and models averaged over several talkers. Experimental results based on recordings with a prototype hearable show that the proposed speech-dependent model enables to simulate in-ear signals more accurately than a speech-independent model in terms of technical measures, especially under utterance mismatch and talker mismatch. Additionally, simulation results show that talker-averaged models generalize better to different talkers than individual models.

show abstract

Multi-Microphone Noise Data Augmentation for DNN-Based Own Voice Reconstruction for Hearables in Noisy Environments

Ohlenbusch,

Rollwage,

Doclo

2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Training Strategies for Own Voice Reconstruction in Hearing Protection Devices Using An In-Ear Microphone

Cited by 5 publications

References 0 publications

Speech-dependent Modeling of Own Voice Transfer Characteristics for In-ear Microphones in Hearables

Speech-dependent Modeling of Own Voice Transfer Characteristics for In-ear Microphones in Hearables

Modeling of speech-dependent own voice transfer characteristics for hearables with an in-ear microphone

Multi-Microphone Noise Data Augmentation for DNN-Based Own Voice Reconstruction for Hearables in Noisy Environments

Contact Info

Product

Resources

About