اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدStream Attention for far-field multi-microphone ASR
243
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
A stream attention framework has been applied to the posterior probabilities of the deep neural network (DNN) to improve the far-field automatic speech recognition (ASR) performance in the multi-microphone configuration. The stream attention scheme has been realized through an attention vector, which is derived by predicting the ASR performance from the phoneme posterior distribution of individual microphone stream, focusing the recognizers attention to more reliable microphones. Investigation on the various ASR performance measures has been carried out using the real recorded dataset. Experiments results show that the proposed framework has yielded substantial improvements in word error rate (WER).
قيم البحث
اقرأ أيضاً
Performance degradation of an Automatic Speech Recognition (ASR) system is commonly observed when the test acoustic condition is different from training. Hence, it is essential to make ASR systems robust against various environmental distortions, suc
h as background noises and reverberations. In a multi-stream paradigm, improving robustness takes account of handling a variety of unseen single-stream conditions and inter-stream dynamics. Previously, a practical two-stage training strategy was proposed within multi-stream end-to-end ASR, where Stage-2 formulates the multi-stream model with features from Stage-1 Universal Feature Extractor (UFE). In this paper, as an extension, we introduce a two-stage augmentation scheme focusing on mismatch scenarios: Stage-1 Augmentation aims to address single-stream input varieties with data augmentation techniques; Stage-2 Time Masking applies temporal masks on UFE features of randomly selected streams to simulate diverse stream combinations. During inference, we also present adaptive Connectionist Temporal Classification (CTC) fusion with the help of hierarchical attention mechanisms. Experiments have been conducted on two datasets, DIRHA and AMI, as a multi-stream scenario. Compared with the previous training strategy, substantial improvements are reported with relative word error rate reductions of 29.7-59.3% across several unseen stream combinations.
We propose a straightforward and cost-effective method to perform diffuse soundfield measurements for calibrating the magnitude response of a microphone array. Typically, such calibration is performed in a diffuse soundfield created in reverberation
chambers, an expensive and time-consuming process. A method is proposed for obtaining diffuse field measurements in untreated environments. First, a closed-form expression for the spatial correlation of a wideband signal in a diffuse field is derived. Next, we describe a practical procedure for obtaining the diffuse field response of a microphone array in the presence of a non-diffuse soundfield by the introduction of random perturbations in the microphone location. Experimental spatial correlation data obtained is compared with the theoretical model, confirming that it is possible to obtain diffuse field measurements in untreated environments with relatively few loudspeakers. A 30 second test signal played from 4-8 loudspeakers is shown to be sufficient in obtaining a diffuse field measurement using the proposed method. An Eigenmike is then successfully calibrated at two different geographical locations.
Recently, ad-hoc microphone array has been widely studied. Unlike traditional microphone array settings, the spatial arrangement and number of microphones of ad-hoc microphone arrays are not known in advance, which hinders the adaptation of tradition
al speaker verification technologies to ad-hoc microphone arrays. To overcome this weakness, in this paper, we propose attention-based multi-channel speaker verification with ad-hoc microphone arrays. Specifically, we add an inter-channel processing layer and a global fusion layer after the pooling layer of a single-channel speaker verification system. The inter-channel processing layer applies a so-called residual self-attention along the channel dimension for allocating weights to different microphones. The global fusion layer integrates all channels in a way that is independent to the number of the input channels. We further replace the softmax operator in the residual self-attention with sparsemax, which forces the channel weights of very noisy channels to zero. Experimental results with ad-hoc microphone arrays of over 30 channels demonstrate the effectiveness of the proposed methods. For example, the multi-channel speaker verification with sparsemax achieves an equal error rate (EER) of over 20% lower than oracle one-best system on semi-real data sets, and over 30% lower on simulation data sets, in test scenarios with both matched and mismatched channel numbers.
In order to evaluate the performance of the attention based neural ASR under noisy conditions, the current trend is to present hours of various noisy speech data to the model and measure the overall word/phoneme error rate (W/PER). In general, it is
unclear how these models perform when exposed to a cocktail party setup in which two or more speakers are active. In this paper, we present the mixtures of speech signals to a popular attention-based neural ASR, known as Listen, Attend, and Spell (LAS), at different target-to-interference ratio (TIR) and measure the phoneme error rate. In particular, we investigate in details when two phonemes are mixed what will be the predicted phoneme; in this fashion we build a model in which the most probable predictions for a phoneme are given. We found a 65% relative increase in PER when LAS was presented with mixed speech signals at TIR = 0 dB and the performance approaches the unmixed scenario at TIR = 30 dB. Our results show the model, when presented with mixed phonemes signals, tend to predict those that have higher accuracies during evaluation of original phoneme signals.
This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utterance-level representation. Ins
pired by the Transformer network, our proposed method utilizes the hierarchical architecture of stacked self-attention mechanisms to derive refined features that are more correlated with speakers. Serialized attention mechanism contains a stack of self-attention modules to create fixed-dimensional representations of speakers. Instead of utilizing multi-head attention in parallel, the proposed serialized multi-layer multi-head attention is designed to aggregate and propagate attentive statistics from one layer to the next in a serialized manner. In addition, we employ an input-aware query for each utterance with the statistics pooling. With more layers stacked, the neural network can learn more discriminative speaker embeddings. Experiment results on VoxCeleb1 dataset and SITW dataset show that our proposed method outperforms other baseline methods, including x-vectors and other x-vectors + conventional attentive pooling approaches by 9.7% in EER and 8.1% in DCF0.01.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
