اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدBinaural rendering from microphone array signals of arbitrary geometry
60
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
A method of binaural rendering from microphone array signals of arbitrary geometry is proposed. To reproduce binaural signals from microphone array recordings at a remote location, a spherical microphone array is generally used for capturing a soundfield. However, owing to the lack of flexibility in the microphone arrangement, the single spherical array is sometimes impractical for estimating a large region of a soundfield. We propose a method based on harmonic analysis of infinite order, which allows the use of arbitrarily placed microphones. In the synthesis of the estimated soundfield, a spherical-wave-decomposition-based binaural rendering is also formulated to take into consideration the distance in measuring head-related transfer functions. We develop and evaluate a composite microphone array consisting of multiple small arrays. Experimental results including those of listening tests indicate that our proposed method is robust against change in listening position in the recording area.
قيم البحث
اقرأ أيضاً
This paper addresses the problem of microphone array generalization for deep-learning-based end-to-end multichannel speech enhancement. We aim to train a unique deep neural network (DNN) potentially performing well on unseen microphone arrays. The mi
crophone array geometry shapes the networks parameters when training on a fixed microphone array, and thus restricts the generalization of the trained network to another microphone array. To resolve this problem, a single network is trained using data recorded by various microphone arrays of different geometries. We design three variants of our recently proposed narrowband network to cope with the agnostic number of microphones. Overall, the goal is to make the network learn the universal information for speech enhancement that is available for any array geometry, rather than learn the one-array-dedicated characteristics. The experiments on both simulated and real room impulse responses (RIR) demonstrate the excellent across-array generalization capability of the proposed networks, in the sense that their performance measures are very close to, or even exceed the network trained with test arrays. Moreover, they notably outperform various beamforming methods and other advanced deep-learning-based methods.
For 6-DOF (degrees of freedom) interactive virtual acoustic environments (VAEs), the spatial rendering of diffuse late reverberation in addition to early (specular) reflections is important. In the interest of computational efficiency, the acoustic s
imulation of the late reverberation can be simplified by using a limited number of spatially distributed virtual reverb sources (VRS) each radiating incoherent signals. A sufficient number of VRS is needed to approximate spatially anisotropic late reverberation, e.g., in a room with inhomogeneous distribution of absorption at the boundaries. Here, a highly efficient and perceptually plausible method to generate and spatially render late reverberation is suggested, extending the room acoustics simulator RAZR [Wendt et al., J. Audio Eng. Soc., 62, 11 (2014)]. The room dimensions and frequency-dependent absorption coefficients at the wall boundaries are used to determine the parameters of a physically-based feedback delay network (FDN) to generate the incoherent VRS signals. The VRS are spatially distributed around the listener with weighting factors representing the spatially subsampled distribution of absorption coefficients on the wall boundaries. The minimum number of VRS required to be perceptually distinguishable from the maximum (reference) number of 96 VRS was assessed in a listening test conducted with a spherical loudspeaker array within an anechoic room. For the resulting low numbers of VRS suited for spatial rendering, optimal physically-based parameter choices for the FDN are discussed.
Automatic transcription of meetings requires handling of overlapped speech, which calls for continuous speech separation (CSS) systems. The uPIT criterion was proposed for utterance-level separation with neural networks and introduces the constraint
that the total number of speakers must not exceed the number of output channels. When processing meeting-like data in a segment-wise manner, i.e., by separating overlapping segments independently and stitching adjacent segments to continuous output streams, this constraint has to be fulfilled for any segment. In this contribution, we show that this constraint can be significantly relaxed. We propose a novel graph-based PIT criterion, which casts the assignment of utterances to output channels in a graph coloring problem. It only requires that the number of concurrently active speakers must not exceed the number of output channels. As a consequence, the system can process an arbitrary number of speakers and arbitrarily long segments and thus can handle more diverse scenarios. Further, the stitching algorithm for obtaining a consistent output order in neighboring segments is of less importance and can even be eliminated completely, not the least reducing the computational effort. Experiments on meeting-style WSJ data show improvements in recognition performance over using the uPIT criterion.
The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrade speech enhancement performance when there is an array geometry misma
tch between design and test conditions. Moreover, such speech enhancement techniques do not always yield ASR accuracy improvement due to the difference between speech enhancement and ASR optimization objectives. In this work, we propose to unify an acoustic model framework by optimizing spatial filtering and long short-term memory (LSTM) layers from multi-channel (MC) input. Our acoustic model subsumes beamformers with multiple types of array geometry. In contrast to deep clustering methods that treat a neural network as a black box tool, the network encoding the spatial filters can process streaming audio data in real time without the accumulation of target signal statistics. We demonstrate the effectiveness of such MC neural networks through ASR experiments on the real-world far-field data. We show that our two-channel acoustic model can on average reduce word error rates (WERs) by~13.4 and~12.7% compared to a single channel ASR system with the log-mel filter bank energy (LFBE) feature under the matched and mismatched microphone placement conditions, respectively. Our result also shows that our two-channel network achieves a relative WER reduction of over~7.0% compared to conventional beamforming with seven microphones overall.
Recently, there is a research trend on ad-hoc microphone arrays. However, most research was conducted on simulated data. Although some data sets were collected with a small number of distributed devices, they were not synchronized which hinders the f
undamental theoretical research to ad-hoc microphone arrays. To address this issue, this paper presents a synchronized speech corpus, named Libri-adhoc40, which collects the replayed Librispeech data from loudspeakers by ad-hoc microphone arrays of 40 strongly synchronized distributed nodes in a real office environment. Besides, to provide the evaluation target for speech frontend processing and other applications, we also recorded the replayed speech in an anechoic chamber. We trained several multi-device speech recognition systems on both the Libri-adhoc40 dataset and a simulated dataset. Experimental results demonstrate the validness of the proposed corpus which can be used as a benchmark to reflect the trend and difference of the models with different ad-hoc microphone arrays. The dataset is online available at https://github.com/ISmallFish/Libri-adhoc40.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
