This study addresses the problem of single-channel Automatic Speech Recognition of a target speaker within an overlap speech scenario. In the proposed method, the hidden representations in the acoustic model are modulated by speaker auxiliary information to recognize only the desired speaker. Affine transformation layers are inserted into the acoustic model network to integrate speaker information with the acoustic features. The speaker conditioning process allows the acoustic model to perform computation in the context of target-speaker auxiliary information. The proposed speaker conditioning method is a general approach and can be applied to any acoustic model architecture. Here, we employ speaker conditioning on a ResNet acoustic model. Experiments on the WSJ corpus show that the proposed speaker conditioning method is an effective solution to fuse speaker auxiliary information with acoustic features for multi-speaker speech recognition, achieving +9% and +20% relative WER reduction for clean and overlap speech scenarios, respectively, compared to the original ResNet acoustic model baseline.
A recent trend in speech processing is the use of embeddings created through machine learning models trained on a specific task with large datasets. By leveraging the knowledge already acquired, these models can be reused in new tasks where the amount of available data is small. This paper proposes a pipeline to create a new model, called Mel and Wave Embeddings for Human Voice Tasks (MeWEHV), capable of generating robust embeddings for speech processing. MeWEHV combines the embeddings generated by a pre-trained raw audio waveform encoder model, and deep features extracted from Mel Frequency Cepstral Coefficients (MFCCs) using Convolutional Neural Networks (CNNs). We evaluate the performance of MeWEHV on three tasks: speaker, language, and accent identification. For the first one, we use the VoxCeleb1 dataset and present YouSpeakers204, a new and publicly available dataset for English speaker identification that contains 19607 audio clips from 204 persons speaking in six different accents, allowing other researchers to work with a very balanced dataset, and to create new models that are robust to multiple accents. For evaluating the language identification task, we use the VoxForge and Common Language datasets. Finally, for accent identification, we use the Latin American Spanish Corpora (LASC) and Common Voice datasets. Our approach allows a significant increase in the performance of state-of-the-art models on all the tested datasets, with a low additional computational cost.
We study the problem of inferring user intent from noninvasive electroencephalography (EEG) to restore communication for people with severe speech and physical impairments (SSPI). The focus of this work is improving the estimation of posterior symbol probabilities in a typing task. At each iteration of the typing procedure, a subset of symbols is chosen for the next query based on the current probability estimate. Evidence about the user's response is collected from event-related potentials (ERP) in order to update symbol probabilities, until one symbol exceeds a predefined confidence threshold. We provide a graphical model describing this task, and derive a recursive Bayesian update rule based on a discriminative probability over label vectors for each query, which we approximate using a neural network classifier. We evaluate the proposed method in a simulated typing task and show that it outperforms previous approaches based on generative modeling.
Detecting emotions directly from a speech signal plays an important role in effective human-computer interactions. Existing speech emotion recognition models require massive computational and storage resources, making them hard to implement concurrently with other machine-interactive tasks in embedded systems. In this paper, we propose an efficient and lightweight fully convolutional neural network for speech emotion recognition in systems with limited hardware resources. In the proposed FCNN model, various feature maps are extracted via three parallel paths with different filter sizes. This helps deep convolution blocks to extract high-level features, while ensuring sufficient separability. The extracted features are used to classify the emotion of the input speech segment. While our model has a smaller size than that of the state-of-the-art models, it achieves higher performance on the IEMOCAP and EMO-DB datasets.
Background sound is an informative form of art that is helpful in providing a more immersive experience in real-application voice conversion (VC) scenarios. However, prior research about VC, mainly focusing on clean voices, pay rare attention to VC with background sound. The critical problem for preserving background sound in VC is inevitable speech distortion by the neural separation model and the cascade mismatch between the source separation model and the VC model. In this paper, we propose an end-to-end framework via multi-task learning which sequentially cascades a source separation (SS) module, a bottleneck feature extraction module and a VC module. Specifically, the source separation task explicitly considers critical phase information and confines the distortion caused by the imperfect separation process. The source separation task, the typical VC task and the unified task shares a uniform reconstruction loss constrained by joint training to reduce the mismatch between the SS and VC modules. Experimental results demonstrate that our proposed framework significantly outperforms the baseline systems while achieving comparable quality and speaker similarity to the VC models trained with clean data.
A promising approach for multi-microphone speech separation involves two deep neural networks (DNN), where the predicted target speech from the first DNN is used to compute signal statistics for time-invariant minimum variance distortionless response (MVDR) beamforming, and the MVDR result is then used as extra features for the second DNN to predict target speech. Previous studies suggested that the MVDR result can provide complementary information for the second DNN to better predict target speech. However, on fixed-geometry arrays, both DNNs can take in, for example, the real and imaginary (RI) components of the multi-channel mixture as features to leverage the spatial and spectral information for enhancement. It is not explained clearly why the linear MVDR result can be complementary and why it is still needed, considering that the DNNs and the beamformer use the same input, and the DNNs perform non-linear filtering and could render the linear filtering of MVDR unnecessary. Similarly, in monaural cases, one can replace the MVDR beamformer with a monaural weighted prediction error (WPE) filter. Although the linear WPE filter and the DNNs use the same mixture RI components as input, the WPE result is found to significantly improve the second DNN. This study provides a novel explanation from the perspective of the low-distortion nature of such algorithms, and finds that they can consistently improve phase estimation. Equipped with this understanding, we investigate several low-distortion target estimation algorithms including several beamformers, WPE, forward convolutive prediction, and their combinations, and use their results as extra features to train the second network to achieve better enhancement. Evaluation results on single- and multi-microphone speech dereverberation and enhancement tasks indicate the effectiveness of the proposed approach, and the validity of the proposed view.
In speech enhancement, complex neural network has shown promising performance due to their effectiveness in processing complex-valued spectrum. Most of the recent speech enhancement approaches mainly focus on wide-band signal with a sampling rate of 16K Hz. However, research on super wide band (e.g., 32K Hz) or even full-band (48K) denoising is still lacked due to the difficulty of modeling more frequency bands and particularly high frequency components. In this paper, we extend our previous deep complex convolution recurrent neural network (DCCRN) substantially to a super wide band version -- S-DCCRN, to perform speech denoising on speech of 32K Hz sampling rate. We first employ a cascaded sub-band and full-band processing module, which consists of two small-footprint DCCRNs -- one operates on sub-band signal and one operates on full-band signal, aiming at benefiting from both local and global frequency information. Moreover, instead of simply adopting the STFT feature as input, we use a complex feature encoder trained in an end-to-end manner to refine the information of different frequency bands. We also use a complex feature decoder to revert the feature to time-frequency domain. Finally, a learnable spectrum compression method is adopted to adjust the energy of different frequency bands, which is beneficial for neural network learning. The proposed model, S-DCCRN, has surpassed PercepNet as well as several competitive models and achieves state-of-the-art performance in terms of speech quality and intelligibility. Ablation studies also demonstrate the effectiveness of different contributions.
This work provides a brief description of Human Language Technology (HLT) Laboratory, National University of Singapore (NUS) system submission for 2020 NIST conversational telephone speech (CTS) speaker recognition evaluation (SRE). The challenge focuses on evaluation under CTS data containing multilingual speech. The systems developed at HLT-NUS consider time-delay neural network (TDNN) x-vector and ECAPA-TDNN systems. We also perform domain adaption of probabilistic linear discriminant analysis (PLDA) model and adaptive s-norm on our systems. The score level fusion of TDNN x-vector and ECAPA-TDNN systems is carried out, which improves the final system performance of our submission to 2020 NIST CTS SRE.
The cross-speaker emotion transfer task in TTS particularly aims to synthesize speech for a target speaker with the emotion transferred from reference speech recorded by another (source) speaker. During the emotion transfer process, the identity information of the source speaker could also affect the synthesized results, resulting in the issue of speaker leakage. This paper proposes a new method with the aim to synthesize controllable emotional expressive speech and meanwhile maintain the target speaker's identity in the cross-speaker emotion TTS task. The proposed method is a Tacotron2-based framework with the emotion embedding as the conditioning variable to provide emotion information. Two emotion disentangling modules are contained in our method to 1) get speaker-independent and emotion-discriminative embedding, and 2) explicitly constrain the emotion and speaker identity of synthetic speech to be that as expected. Moreover, we present an intuitive method to control the emotional strength in the synthetic speech for the target speaker. Specifically, the learned emotion embedding is adjusted with a flexible scalar value, which allows controlling the emotion strength conveyed by the embedding. Extensive experiments have been conducted on a Mandarin disjoint corpus, and the results demonstrate that the proposed method is able to synthesize reasonable emotional speech for the target speaker. Compared to the state-of-the-art reference embedding learned methods, our method gets the best performance on the cross-speaker emotion transfer task, indicating that our method achieves the new state-of-the-art performance on learning the speaker-independent emotion embedding. Furthermore, the strength ranking test and pitch trajectories plots demonstrate that the proposed method can effectively control the emotion strength, leading to prosody-diverse synthetic speech.
Many language tasks (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been comparatively little work on interpretability methods for sequence tagging models. In this paper, we extend influence functions - which aim to trace predictions back to the training points that informed them - to sequence tagging tasks. We define the influence of a training instance segment as the effect that perturbing the labels within this segment has on a test segment level prediction. We provide an efficient approximation to compute this, and show that it tracks with the true segment influence, measured empirically. We show the practical utility of segment influence by using the method to identify systematic annotation errors in two named entity recognition corpora. Code to reproduce our results is available at https://github.com/successar/Segment_Influence_Functions.