Fast estimation of a precise dereverberation filter based on the harmonic structure of speech
スポンサーリンク
概要
- 論文の詳細を見る
A speech signal captured by a distant microphone is generally smeared by reverberation. This severely degrades both the speech intelligibility and the Automatic Speech Recognition (ASR) performance. We have already proposed a novel dereverberation technique named "Harmonicity based dEReverBeration (HERB)," which utilizes an essential feature of speech, namely harmonics, and estimates an inverse filter for an unknown impulse response. If a large amount of acoustically stable training data is available, HERB is able to estimate an accurate inverse filter even in severely reverberant environments. In general, however, a dereverberation algorithm has to work with small amounts of training data, because the acoustic property of a real world environment changes according to various factors such as the speaker's position and room temperature. In this paper, we propose a new dereverberation scheme based on HERB, aiming primarily at reducing the amount of training data needed to estimate an inverse filter. The proposed method re-estimates a more accurate source signal based on the output signal of conventional HERB, and re-calculates the inverse filter. We show experimentally that our new dereverberation scheme successfully achieves high quality dereverberation with much smaller amounts of training data, and is very effective at improving both audible quality and ASR performance, even in unknown severely reverberant environments.
- 社団法人日本音響学会の論文
著者
-
Kinoshita Keisuke
Ntt Communication Science Laboratories
-
Miyoshi Masato
Ntt Corp. Kyoto‐fu Jpn
-
Miyoshi Masato
Ntt Communication Science Laboratories Ntt Corporation
-
Nakatani Tomohiro
NTT Communication Science Laboratories
-
Miyoshi Masato
NTT Communication Science Laboratories
関連論文
- Sound image rendering using a loudspeaker and a fully open-air headphone-set
- On a Blind Speech Dereverberation Algorithm Using Multi-Channel Linear Prediction(Engineering Acoustics)
- Speech dereverberation algorithm using transfer function estimates with overestimated order
- Blind dereverberation algorithm for speech signals based on multi-channel linear prediction
- Common Acoustical Pole Estimation from Multi-Channel Musical Audio Signals(Engineering Acoustics)
- A Study on Frequency Characteristics and Transmission Path of Audible Sound Perceived when the Tragus is Vibrated by Amplitude-Modulated Ultrasound
- Fast estimation of a precise dereverberation filter based on the harmonic structure of speech
- Harmonicity Based Dereverberation for Improving Automatic Speech Recognition Performance and Speech Intelligibility(Speech Enhancement, Multi-channel Acoustic Signal Processing)
- Sparse source separation based on simultaneous clustering of source locational and spectral features
- Calculating Inverse Filters for Speech Dereverberation
- A new algorithm for blind estimation of common poles in multiple transmission paths based on linear prediction
- Sound timbre control using estimates of room resonance modes
- Acoustic Nonlinear Effect on Auricular Cartilage Vibrated with Amplitude-Modulated Ultrasound