اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدSpeech Separation Based on Multi-Stage Elaborated Dual-Path Deep BiLSTM with Auxiliary Identity Loss
87
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Deep neural network with dual-path bi-directional long short-term memory (BiLSTM) block has been proved to be very effective in sequence modeling, especially in speech separation. This work investigates how to extend dual-path BiLSTM to result in a new state-of-the-art approach, called TasTas, for multi-talker monaural speech separation (a.k.a cocktail party problem). TasTas introduces two simple but effective improvements, one is an iterative multi-stage refinement scheme, and the other is to correct the speech with imperfect separation through a loss of speaker identity consistency between the separated speech and original speech, to boost the performance of dual-path BiLSTM based networks. TasTas takes the mixed utterance of two speakers and maps it to two separated utterances, where each utterance contains only one speakers voice. Our experiments on the notable benchmark WSJ0-2mix data corpus result in 20.55dB SDR improvement, 20.35dB SI-SDR improvement, 3.69 of PESQ, and 94.86% of ESTOI, which shows that our proposed networks can lead to big performance improvement on the speaker separation task. We have open sourced our re-implementation of the DPRNN-TasNet here (https://github.com/ShiZiqiang/dual-path-RNNs-DPRNNs-based-speech-separation), and our TasTas is realized based on this implementation of DPRNN-TasNet, it is believed that the results in this paper can be reproduced with ease.
قيم البحث
اقرأ أيضاً
The continuous speech separation (CSS) is a task to separate the speech sources from a long, partially overlapped recording, which involves a varying number of speakers. A straightforward extension of conventional utterance-level speech separation to
the CSS task is to segment the long recording with a size-fixed window and process each window separately. Though effective, this extension fails to model the long dependency in speech and thus leads to sub-optimum performance. The recent proposed dual-path modeling could be a remedy to this problem, thanks to its capability in jointly modeling the cross-window dependency and the local-window processing. In this work, we further extend the dual-path modeling framework for CSS task. A transformer-based dual-path system is proposed, which integrates transform layers for global modeling. The proposed models are applied to LibriCSS, a real recorded multi-talk dataset, and consistent WER reduction can be observed in the ASR evaluation for separated speech. Also, a dual-path transformer equipped with convolutional layers is proposed. It significantly reduces the computation amount by 30% with better WER evaluation. Furthermore, the online processing dual-path models are investigated, which shows 10% relative WER reduction compared to the baseline.
Target speech separation refers to extracting a target speakers voice from an overlapped audio of simultaneous talkers. Previously the use of visual modality for target speech separation has demonstrated great potentials. This work proposes a general
multi-modal framework for target speech separation by utilizing all the available information of the target speaker, including his/her spatial location, voice characteristics and lip movements. Also, under this framework, we investigate on the fusion methods for multi-modal joint modeling. A factorized attention-based fusion method is proposed to aggregate the high-level semantic information of multi-modalities at embedding level. This method firstly factorizes the mixture audio into a set of acoustic subspaces, then leverages the targets information from other modalities to enhance these subspace acoustic embeddings with a learnable attention scheme. To validate the robustness of proposed multi-modal separation model in practical scenarios, the system was evaluated under the condition that one of the modalities is temporarily missing, invalid or corrupted. Experiments are conducted on a large-scale audio-visual dataset collected from YouTube (to be released) that spatialized by simulated room impulse responses (RIRs). Experiment results illustrate that our proposed multi-modal framework significantly outperforms single-modal and bi-modal speech separation approaches, while can still support real-time processing.
Deep learning technology has been widely applied to speech enhancement. While testing the effectiveness of various network structures, researchers are also exploring the improvement of the loss function used in network training. Although the existing
methods have considered the auditory characteristics of speech or the reasonable expression of signal-to-noise ratio, the correlation with the auditory evaluation score and the applicability of the calculation for gradient optimization still need to be improved. In this paper, a signal-to-noise ratio loss function based on auditory power compression is proposed. The experimental results show that the overall correlation between the proposed function and the indexes of objective speech intelligibility, which is better than other loss functions. For the same speech enhancement model, the training effect of this method is also better than other comparison methods.
Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper, we propose the usage of an asymmetric analysis-synthesis window pair
which allows for training with targets with better frequency resolution, while retaining the low-latency during inference suitable for real-time speech enhancement or assisted hearing applications. In order to assess our approach across various model types and datasets, we evaluate it with both speaker-independent deep clustering (DC) model and a speaker-dependent mask inference (MI) model. We report an improvement in separation performance of up to 1.5 dB in terms of source-to-distortion ratio (SDR) while maintaining an algorithmic latency of 8 ms.
Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy condition during
testing, i.e., the performance is generally sub-optimal when models are tested with unseen noise types that are not involved in the training data; (2) local focus on specific noisy conditions, i.e., models trained using multiple types of noises cannot optimally remove a specific noise type even though the noise type has been involved in the training data. These problems are common in real applications. In this paper, we propose a novel denoising autoencoder with a multi-branched encoder (termed DAEME) model to deal with these two problems. In the DAEME model, two stages are involved: training and testing. In the training stage, we build multiple component models to form a multi-branched encoder based on a decision tree (DSDT). The DSDT is built based on prior knowledge of speech and noisy conditions (the speaker, environment, and signal factors are considered in this paper), where each component of the multi-branched encoder performs a particular mapping from noisy to clean speech along the branch in the DSDT. Finally, a decoder is trained on top of the multi-branched encoder. In the testing stage, noisy speech is first processed by each component model. The multiple outputs from these models are then integrated into the decoder to determine the final enhanced speech. Experimental results show that DAEME is superior to several baseline models in terms of objective evaluation metrics, automatic speech recognition results, and quality in subjective human listening tests.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
