Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSerialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
196
0
0.0
(
0
)
Added by
Hongning Zhu
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
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. Inspired 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.
rate research
Read More
We propose the multi-head convolutional neural network (MCNN) architecture for waveform synthesis from spectrograms. Nonlinear interpolation in MCNN is employed with transposed convolution layers in parallel heads. MCNN achieves more than an order of magnitude higher compute intensity than commonly-used iterative algorithms like Griffin-Lim, yielding efficient utilization for modern multi-core processors, and very fast (more than 300x real-time) waveform synthesis. For training of MCNN, we use a large-scale speech recognition dataset and losses defined on waveforms that are related to perceptual audio quality. We demonstrate that MCNN constitutes a very promising approach for high-quality speech synthesis, without any iterative algorithms or autoregression in computations.
Text-to-speech systems recently achieved almost indistinguishable quality from human speech. However, the prosody of those systems is generally flatter than natural speech, producing samples with low expressiveness. Disentanglement of speaker id and prosody is crucial in text-to-speech systems to improve on naturalness and produce more variable syntheses. This paper proposes a new neural text-to-speech model that approaches the disentanglement problem by conditioning a Tacotron2-like architecture on flow-normalized speaker embeddings, and by substituting the reference encoder with a new learned latent distribution responsible for modeling the intra-sentence variability due to the prosody. By removing the reference encoder dependency, the speaker-leakage problem typically happening in this kind of systems disappears, producing more distinctive syntheses at inference time. The new model achieves significantly higher prosody variance than the baseline in a set of quantitative prosody features, as well as higher speaker distinctiveness, without decreasing the speaker intelligibility. Finally, we observe that the normalized speaker embeddings enable much richer speaker interpolations, substantially improving the distinctiveness of the new interpolated speakers.
Most of the recent state-of-the-art results for speaker verification are achieved by X-vector and its subsequent variants. In this paper, we propose a new network architecture which aggregates the channel and context interdependence features from multi aspect based on Time Delay Neural Network (TDNN). Firstly, we use the SE-Res2Blocks as in ECAPA-TDNN to explicitly model the channel interdependence to realize adaptive calibration of channel features, and process local context features in a multi-scale way at a more granular level compared with conventional TDNN-based methods. Secondly, we explore to use the encoder structure of Transformer to model the global context interdependence features at an utterance level which can capture better long term temporal characteristics. Before the pooling layer, we aggregate the outputs of SE-Res2Blocks and Transformer encoder to leverage the complementary channel and context interdependence features learned by themself respectively. Finally, instead of performing a single attentive statistics pooling, we also find it beneficial to extend the pooling method in a multi-head way which can discriminate features from multiple aspect. The proposed MACCIF-TDNN architecture can outperform most of the state-of-the-art TDNN-based systems on VoxCeleb1 test sets.
Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR by replacing the matrix inversion and eigenvalue decomposition with two recurrent neural networks. In this work, we present a self-attentive RNN beamformer to further improve our previous RNN-based beamformer by leveraging on the powerful modeling capability of self-attention. Temporal-spatial self-attention module is proposed to better learn the beamforming weights from the speech and noise spatial covariance matrices. The temporal self-attention module could help RNN to learn global statistics of covariance matrices. The spatial self-attention module is designed to attend on the cross-channel correlation in the covariance matrices. Furthermore, a multi-channel input with multi-speaker directional features and multi-speaker speech separation outputs (MIMO) model is developed to improve the inference efficiency. The evaluations demonstrate that our proposed MIMO self-attentive RNN beamformer improves both the automatic speech recognition (ASR) accuracy and the perceptual estimation of speech quality (PESQ) against prior arts.
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).
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
