Speech enhancement for cochlear implant recipients

D Wang, JHL Hansen - The Journal of the Acoustical Society of …, 2018 - pubs.aip.org
In this study, a single microphone speech enhancement algorithm is proposed to improve
speech intelligibility for cochlear implant recipients. The proposed algorithm combines …

Robust harmonic features for classification-based pitch estimation

D Wang, C Yu, JHL Hansen - IEEE/ACM transactions on audio …, 2017 - ieeexplore.ieee.org
Pitch estimation in diverse naturalistic audio streams remains a challenge for speech
processing and spoken language technology. In this study, we investigate the use of robust …

Extraction of fundamental frequency from degraded speech using temporal envelopes at high SNR frequencies

G Aneeja, B Yegnanarayana - IEEE/ACM Transactions on …, 2017 - ieeexplore.ieee.org
In this paper we propose a method for extracting the fundamental frequency (fo) from
degraded speech signals using single frequency filtering (SFF) approach. The SFF of …

Robust pitch estimation and tracking for speakers based on subband encoding and the generalized labeled multi-bernoulli filter

S Lin - IEEE/ACM Transactions on Audio, Speech, and …, 2019 - ieeexplore.ieee.org
This paper proposes a new pitch estimator and a novel pitch tracker for speakers. We first
decompose the sound signal into subbands using an auditory filterbank, assuming time …

Statistical regression models for noise robust F0 estimation using recurrent deep neural networks

A Kato, TH Kinnunen - IEEE/ACM Transactions on Audio …, 2019 - ieeexplore.ieee.org
The fundamental frequency (F0) in a speech signal, which corresponds to pitch, is one of the
key features involved in a variety of speech processing tasks. Therefore, accurate F0 …

F0 estimation for noisy speech by exploring temporal harmonic structures in local time frequency spectrum segment

D Wang, JHL Hansen - 2016 IEEE International Conference on …, 2016 - ieeexplore.ieee.org
In this paper, we propose a noise robust F0 estimation approach by exploring the temporal
harmonic structures in local time-frequency (TF) spectrum segment. Since the speech …

Waveform to single sinusoid regression to estimate the F0 contour from noisy speech using recurrent deep neural networks

A Kato, T Kinnunen - Proceedings of Interspeech 2018, 2018 - erepo.uef.fi
The fundamental frequency (F0) represents pitch in speech that determines prosodic
characteristics of speech and is needed in various tasks for speech analysis and synthesis …

[PDF][PDF] Speech Enhancement Based on Harmonic Estimation Combined with MMSE to Improve Speech Intelligibility for Cochlear Implant Recipients.

D Wang, JHL Hansen - INTERSPEECH, 2017 - researchgate.net
In this paper, a speech enhancement algorithm is proposed to improve the speech
intelligibility for cochlear implant recipients. Our method is based on combination of …

A regression model of recurrent deep neural networks for noise robust estimation of the fundamental frequency contour of speech

A Kato, T Kinnunen - arXiv preprint arXiv:1805.02958, 2018 - arxiv.org
The fundamental frequency (F0) contour of speech is a key aspect to represent speech
prosody that finds use in speech and spoken language analysis such as voice conversion …

: A Hybrid Pitch Extraction Method for Multimodal Voice

P Rengaswamy, MG Reddy, KS Rao… - Circuits, Systems, and …, 2021 - Springer
Pitch or fundamental frequency (f_0 f 0) estimation is a fundamental problem extensively
studied for its potential speech and clinical applications. The existing f_0 f 0 estimation …