Deep learning based speech enhancement in the short-term Fourier transform (STFT) domain typically uses a large window length such as 32 ms. A larger window contains more samples and the frequency resolution can be higher for potentially better enhancement. This however incurs an algorithmic latency of 32 ms in an online setup, because the overlap-add algorithm used in the inverse STFT (iSTFT) is also performed based on the same 32 ms window size. To reduce this inherent latency, we adapt a conventional dual window size approach, where a regular input window size is used for STFT but a shorter output window is used for the overlap-add in the iSTFT, for STFT-domain deep learning based frame-online speech enhancement. Based on this STFT and iSTFT configuration, we employ single- or multi-microphone complex spectral mapping for frame-online enhancement, where a deep neural network (DNN) is trained to predict the real and imaginary (RI) components of target speech from the mixture RI components. In addition, we use the RI components predicted by the DNN to conduct frame-online beamforming, the results of which are then used as extra features for a second DNN to perform frame-online post-filtering. The frequency-domain beamforming in between the two DNNs can be easily integrated with complex spectral mapping and is designed to not incur any algorithmic latency. Additionally, we propose a future-frame prediction technique to further reduce the algorithmic latency. Evaluation results on a noisy-reverberant speech enhancement task demonstrate the effectiveness of the proposed algorithms. Compared with Conv-TasNet, our STFT-domain system can achieve better enhancement performance for a comparable amount of computation, or comparable performance with less computation, maintaining strong performance at an algorithmic latency as low as 2 ms.
Although Transformers have gained success in several speech processing tasks like spoken language understanding (SLU) and speech translation (ST), achieving online processing while keeping competitive performance is still essential for real-world interaction. In this paper, we take the first step on streaming SLU and simultaneous ST using a blockwise streaming Transformer, which is based on contextual block processing and blockwise synchronous beam search. Furthermore, we design an automatic speech recognition (ASR)-based intermediate loss regularization for the streaming SLU task to improve the classification performance further. As for the simultaneous ST task, we propose a cross-lingual encoding method, which employs a CTC branch optimized with target language translations. In addition, the CTC translation output is also used to refine the search space with CTC prefix score, achieving joint CTC/attention simultaneous translation for the first time. Experiments for SLU are conducted on FSC and SLURP corpora, while the ST task is evaluated on Fisher-CallHome Spanish and MuST-C En-De corpora. Experimental results show that the blockwise streaming Transformer achieves competitive results compared to offline models, especially with our proposed methods that further yield a 2.4% accuracy gain on the SLU task and a 4.3 BLEU gain on the ST task over streaming baselines.
Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the relatedness between the SSL training domain(s) and the target data domain. On the contrary, spectral feature (SF) extractors such as log Mel-filterbanks are hand-crafted non-learnable components, and could be more robust to domain shifts. The present work examines the assumption that combining non-learnable SF extractors to SSL models is an effective approach to low resource speech tasks. We propose a learnable and interpretable framework to combine SF and SSL representations. The proposed framework outperforms significantly both baseline and SSL models on Automatic Speech Recognition (ASR) and Speech Translation (ST) tasks on three low resource datasets. We additionally design a mixture of experts based combination model. This last model reveals that the relative contribution of SSL models over conventional SF extractors is very small in case of domain mismatch between SSL training set and the target language data.
Frame-online speech enhancement systems in the short-time Fourier transform (STFT) domain usually have an algorithmic latency equal to the window size due to the use of the overlap-add algorithm in the inverse STFT (iSTFT). This algorithmic latency allows the enhancement models to leverage future contextual information up to a length equal to the window size. However, current frame-online systems only partially leverage this future information. To fully exploit this information, this study proposes an overlapped-frame prediction technique for deep learning based frame-online speech enhancement, where at each frame our deep neural network (DNN) predicts the current and several past frames that are necessary for overlap-add, instead of only predicting the current frame. In addition, we propose a novel loss function to account for the scale difference between predicted and oracle target signals. Evaluations results on a noisy-reverberant speech enhancement task show the effectiveness of the proposed algorithms.
This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS). Compared with conventional E2E ASR models, the proposed E2E model integrates two important modules including a speech enhancement (SE) module and a self-supervised learning representation (SSLR) module. The SE module enhances the noisy speech. Then the SSLR module extracts features from enhanced speech to be used for speech recognition (ASR). To train the proposed model, we establish an efficient learning scheme. Evaluation results on the monaural CHiME-4 task show that the IRIS model achieves the best performance reported in the literature for the single-channel CHiME-4 benchmark (2.0% for the real development and 3.9% for the real test) thanks to the powerful pre-trained SSLR module and the fine-tuned SE module.
We develop an end-to-end system for multi-channel, multi-speaker automatic speech recognition. We propose a frontend for joint source separation and dereverberation based on the independent vector analysis (IVA) paradigm. It uses the fast and stable iterative source steering algorithm together with a neural source model. The parameters from the ASR module and the neural source model are optimized jointly from the ASR loss itself. We demonstrate competitive performance with previous systems using neural beamforming frontends. First, we explore the trade-offs when using various number of channels for training and testing. Second, we demonstrate that the proposed IVA frontend performs well on noisy data, even when trained on clean mixtures only. Furthermore, it extends without retraining to the separation of more speakers, which is demonstrated on mixtures of three and four speakers.
This paper proposes a method for improved CTC inference with searched intermediates and multi-pass conditioning. The paper first formulates self-conditioned CTC as a probabilistic model with an intermediate prediction as a latent representation and provides a tractable conditioning framework. We then propose two new conditioning methods based on the new formulation: (1) Searched intermediate conditioning that refines intermediate predictions with beam-search, (2) Multi-pass conditioning that uses predictions of previous inference for conditioning the next inference. These new approaches enable better conditioning than the original self-conditioned CTC during inference and improve the final performance. Experiments with the LibriSpeech dataset show relative 3%/12% performance improvement at the maximum in test clean/other sets compared to the original self-conditioned CTC.
In this paper, we present a novel framework that jointly performs speaker diarization, speech separation, and speaker counting. Our proposed method combines end-to-end speaker diarization and speech separation methods, namely, End-to-End Neural Speaker Diarization with Encoder-Decoder-based Attractor calculation (EEND-EDA) and the Convolutional Time-domain Audio Separation Network (ConvTasNet) as multi-tasking joint model. We also propose the multiple 1x1 convolutional layer architecture for estimating the separation masks corresponding to the number of speakers, and a post-processing technique for refining the separated speech signal with speech activity. Experiments using LibriMix dataset show that our proposed method outperforms the baselines in terms of diarization and separation performance for both fixed and flexible numbers of speakers, as well as speaker counting performance for flexible numbers of speakers. All materials will be open-sourced and reproducible in ESPnet toolkit.
Deep learning based singing voice synthesis (SVS) systems have been demonstrated to flexibly generate singing with better qualities, compared to conventional statistical parametric based methods. However, neural systems are generally data-hungry and have difficulty to reach reasonable singing quality with limited public available training data. In this work, we explore different data augmentation methods to boost the training of SVS systems, including several strategies customized to SVS based on pitch augmentation and mix-up augmentation. To further stabilize the training, we introduce the cycle-consistent training strategy. Extensive experiments on two public singing databases demonstrate that our proposed augmentation methods and the stabilizing training strategy can significantly improve the performance on both objective and subjective evaluations.