PyAWNeS-Codec: Speech and audio codec for ad-hoc acoustic wireless sensor networks

Abstract

Existing hardware with microphones can potentially be used as sensor networks to capture speech and audio signals for the benefit of better signal quality than possible with a single microphone. A central pre-requisite for such ad-hoc acoustic wireless sensor networks (ASWNs) is an efficient communication protocol with which to transmit audio data between nodes. For that purpose, we present the world's-first speech and audio codec especially designed for ASWNs, which has competitive quality also in single-channel operation. To ensure quality in the single-channel scenario, it closely resembles conventional codecs of the TCX-type, but extended with features to facilitate multi-device operation, including dithered quantization, delay estimation and compensation, as well as multi-channel postfiltering. The codec is intended to become a baseline for future research and we therefore provide it as an open-access library. Our experiments confirm that performance is in the same range as recent commercial single-channel codecs and that added devices improve quality.Index Terms-speech and audio coding, ad-hoc acoustic sensor networks, time difference of arrival estimation, delay compensation, multi-channel post-filtering

Adversarial Guitar Amplifier Modelling with Unpaired Data

“…Particularly, for a constant sound pressure level, low frequencies are perceived more quietly in comparison to frequencies in the most sensitive area around 3000 Hz. One pre-processing technique that is commonly used for speech processing is pre-emphasis filtering [102]. This was initially applied to neural network modelling of guitar amplifiers by Dämskägg et al [75], where a first-order high-pass filter was applied to both model output and target data before computing the loss.…”

Speech Localization at Low Bitrates in Wireless Acoustics Sensor Networks

“…Since we are interested in speech data, our investigations are focused on selected speech audio codecs. Namely, we use the 3GPP Enhanced Voice Services (EVS) codec (Bruhn et al, 2012), Opus (Valin et al, 2012), our own PyAWNeS-codec (Bäckström et al, 2021), and the neural codec Lyra (Kleijn et al, 2021). In particular,…”

“…A delay compensation mode is integrated into the EVS codec, allowing the compensation of the integrated delay of about 32 ms within the encoded output signal. •The Python acoustic wireless network of sensors (PyAWNeS) codec is a speech and audio codec especially designed for distributed scenarios, where multiple independent devices sense and transmit the signal simultaneously (Bäckström et al, 2021). In contrast to prior codecs, it is designed to provide competitive quality in a single channel mode, but such that quality is improved with every added sensor.…”

“…The proposed localization scheme is motivated by the speech codec we recently published (Bäckström et al, 2021), where we estimated the TDoA from a multi-channel, coded mixture. This method of front-end processing opens up avenues for processing audio not just from microphones from the same sensor array but from microphones from distinct devices.…”

“…In this paper, we consider a speaker target positioning as a DoA classification task. Our contribution is to study how our recently proposed simple DNN architecture (Zarazaga et al, 2020) performance varies with the different bitrate encoding of recent communication codecs including PyAWNeS (Bäckström et al, 2021), OPUS (Valin et al, 2012), the Enhanced Voice Services (EVS) (Bruhn et al, 2012), and Lyra (Kleijn et al, 2021). We analyze the performance of both considered scenarios as a function of the audio input bitrate.…”