Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"speech": models, code, and papers

Visually Guided Self Supervised Learning of Speech Representations

Jan 13, 2020
Abhinav Shukla, Konstantinos Vougioukas, Pingchuan Ma, Stavros Petridis, Maja Pantic

Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very limited work that studies the interaction between the two modalities for learning self supervised representations. We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip and optimize the generated video to be as close as possible to the real video of the speech segment. Through this process, the audio encoder network learns useful speech representations that we evaluate on emotion recognition and speech recognition. We achieve state of the art results for emotion recognition and competitive results for speech recognition. This demonstrates the potential of visual supervision for learning audio representations as a novel way for self-supervised learning which has not been explored in the past. The proposed unsupervised audio features can leverage a virtually unlimited amount of training data of unlabelled audiovisual speech and have a large number of potentially promising applications.

* Submitted to ICASSP 2020 

  Access Paper or Ask Questions

Inductive biases, pretraining and fine-tuning jointly account for brain responses to speech

Feb 25, 2021
Juliette Millet, Jean-Remi King

Our ability to comprehend speech remains, to date, unrivaled by deep learning models. This feat could result from the brain's ability to fine-tune generic sound representations for speech-specific processes. To test this hypothesis, we compare i) five types of deep neural networks to ii) human brain responses elicited by spoken sentences and recorded in 102 Dutch subjects using functional Magnetic Resonance Imaging (fMRI). Each network was either trained on an acoustics scene classification, a speech-to-text task (based on Bengali, English, or Dutch), or not trained. The similarity between each model and the brain is assessed by correlating their respective activations after an optimal linear projection. The differences in brain-similarity across networks revealed three main results. First, speech representations in the brain can be accounted for by random deep networks. Second, learning to classify acoustic scenes leads deep nets to increase their brain similarity. Third, learning to process phonetically-related speech inputs (i.e., Dutch vs English) leads deep nets to reach higher levels of brain-similarity than learning to process phonetically-distant speech inputs (i.e. Dutch vs Bengali). Together, these results suggest that the human brain fine-tunes its heavily-trained auditory hierarchy to learn to process speech.

* 10 pages, 3 figures 

  Access Paper or Ask Questions

Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement

Aug 27, 2021
Yuzi Yan, Wei-Qiang Zhang, Michael T. Johnson

As the cornerstone of other important technologies, such as speech recognition and speech synthesis, speech enhancement is a critical area in audio signal processing. In this paper, a new deep learning structure for speech enhancement is demonstrated. The model introduces a "full" attention mechanism to a bidirectional sequence-to-sequence method to make use of latent information after each focal frame. This is an extension of the previous attention-based RNN method. The proposed bidirectional attention-based architecture achieves better performance in terms of speech quality (PESQ), compared with OM-LSA, CNN-LSTM, T-GSA and the unidirectional attention-based LSTM baseline.

* 4 pages 

  Access Paper or Ask Questions

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

Apr 21, 2022
Rongjie Huang, Max W. Y. Lam, Jun Wang, Dan Su, Dong Yu, Yi Ren, Zhou Zhao

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e.g., Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4.28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time. We further show that FastDiff generalized well to the mel-spectrogram inversion of unseen speakers, and FastDiff-TTS outperformed other competing methods in end-to-end text-to-speech synthesis. Audio samples are available at \url{}.

* Accepted by IJCAI 2022 

  Access Paper or Ask Questions

Controllable Context-aware Conversational Speech Synthesis

Jun 21, 2021
Jian Cong, Shan Yang, Na Hu, Guangzhi Li, Lei Xie, Dan Su

In spoken conversations, spontaneous behaviors like filled pause and prolongations always happen. Conversational partner tends to align features of their speech with their interlocutor which is known as entrainment. To produce human-like conversations, we propose a unified controllable spontaneous conversational speech synthesis framework to model the above two phenomena. Specifically, we use explicit labels to represent two typical spontaneous behaviors filled-pause and prolongation in the acoustic model and develop a neural network based predictor to predict the occurrences of the two behaviors from text. We subsequently develop an algorithm based on the predictor to control the occurrence frequency of the behaviors, making the synthesized speech vary from less disfluent to more disfluent. To model the speech entrainment at acoustic level, we utilize a context acoustic encoder to extract a global style embedding from the previous speech conditioning on the synthesizing of current speech. Furthermore, since the current and previous utterances belong to the different speakers in a conversation, we add a domain adversarial training module to eliminate the speaker-related information in the acoustic encoder while maintaining the style-related information. Experiments show that our proposed approach can synthesize realistic conversations and control the occurrences of the spontaneous behaviors naturally.

* Accepted to INTERSPEECH 2021 

  Access Paper or Ask Questions

CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism

Jul 28, 2021
Guochen Yu, Yutian Wang, Chengshi Zheng, Hui Wang, Qin Zhang

Non-parallel training is a difficult but essential task for DNN-based speech enhancement methods, for the lack of adequate noisy and paired clean speech corpus in many real scenarios. In this paper, we propose a novel adaptive attention-in-attention CycleGAN (AIA-CycleGAN) for non-parallel speech enhancement. In previous CycleGAN-based non-parallel speech enhancement methods, the limited mapping ability of the generator may cause performance degradation and insufficient feature learning. To alleviate this degradation, we propose an integration of adaptive time-frequency attention (ATFA) and adaptive hierarchical attention (AHA) to form an attention-in-attention (AIA) module for more flexible feature learning during the mapping procedure. More specifically, ATFA can capture the long-range temporal-spectral contextual information for more effective feature representations, while AHA can flexibly aggregate different intermediate feature maps by weights depending on the global context. Numerous experimental results demonstrate that the proposed approach achieves consistently more superior performance over previous GAN-based and CycleGAN-based methods in non-parallel training. Moreover, experiments in parallel training verify that the proposed AIA-CycleGAN also outperforms most advanced GAN-based speech enhancement approaches, especially in maintaining speech integrity and reducing speech distortion.

* Submitted to APSIPA-ASC 2021 

  Access Paper or Ask Questions

Visual Speech Enhancement Without A Real Visual Stream

Dec 20, 2020
Sindhu B Hegde, K R Prajwal, Rudrabha Mukhopadhyay, Vinay Namboodiri, C. V. Jawahar

In this work, we re-think the task of speech enhancement in unconstrained real-world environments. Current state-of-the-art methods use only the audio stream and are limited in their performance in a wide range of real-world noises. Recent works using lip movements as additional cues improve the quality of generated speech over "audio-only" methods. But, these methods cannot be used for several applications where the visual stream is unreliable or completely absent. We propose a new paradigm for speech enhancement by exploiting recent breakthroughs in speech-driven lip synthesis. Using one such model as a teacher network, we train a robust student network to produce accurate lip movements that mask away the noise, thus acting as a "visual noise filter". The intelligibility of the speech enhanced by our pseudo-lip approach is comparable (< 3% difference) to the case of using real lips. This implies that we can exploit the advantages of using lip movements even in the absence of a real video stream. We rigorously evaluate our model using quantitative metrics as well as human evaluations. Additional ablation studies and a demo video on our website containing qualitative comparisons and results clearly illustrate the effectiveness of our approach. We provide a demo video which clearly illustrates the effectiveness of our proposed approach on our website: \url{}. The code and models are also released for future research: \url{}.

* 10 pages, 4 figures, Accepted in WACV 2021 

  Access Paper or Ask Questions

Speaker Separation Using Speaker Inventories and Estimated Speech

Oct 20, 2020
Peidong Wang, Zhuo Chen, DeLiang Wang, Jinyu Li, Yifan Gong

We propose speaker separation using speaker inventories and estimated speech (SSUSIES), a framework leveraging speaker profiles and estimated speech for speaker separation. SSUSIES contains two methods, speaker separation using speaker inventories (SSUSI) and speaker separation using estimated speech (SSUES). SSUSI performs speaker separation with the help of speaker inventory. By combining the advantages of permutation invariant training (PIT) and speech extraction, SSUSI significantly outperforms conventional approaches. SSUES is a widely applicable technique that can substantially improve speaker separation performance using the output of first-pass separation. We evaluate the models on both speaker separation and speech recognition metrics.

  Access Paper or Ask Questions

Direct multimodal few-shot learning of speech and images

Dec 10, 2020
Leanne Nortje, Herman Kamper

We propose direct multimodal few-shot models that learn a shared embedding space of spoken words and images from only a few paired examples. Imagine an agent is shown an image along with a spoken word describing the object in the picture, e.g. pen, book and eraser. After observing a few paired examples of each class, the model is asked to identify the "book" in a set of unseen pictures. Previous work used a two-step indirect approach relying on learned unimodal representations: speech-speech and image-image comparisons are performed across the support set of given speech-image pairs. We propose two direct models which instead learn a single multimodal space where inputs from different modalities are directly comparable: a multimodal triplet network (MTriplet) and a multimodal correspondence autoencoder (MCAE). To train these direct models, we mine speech-image pairs: the support set is used to pair up unlabelled in-domain speech and images. In a speech-to-image digit matching task, direct models outperform indirect models, with the MTriplet achieving the best multimodal five-shot accuracy. We show that the improvements are due to the combination of unsupervised and transfer learning in the direct models, and the absence of two-step compounding errors.

* 3 figures, 2 tables 

  Access Paper or Ask Questions

Task-aware Warping Factors in Mask-based Speech Enhancement

Aug 27, 2021
Qiongqiong Wang, Kong Aik Lee, Takafumi Koshinaka, Koji Okabe, Hitoshi Yamamoto

This paper proposes the use of two task-aware warping factors in mask-based speech enhancement (SE). One controls the balance between speech-maintenance and noise-removal in training phases, while the other controls SE power applied to specific downstream tasks in testing phases. Our intention is to alleviate the problem that SE systems trained to improve speech quality often fail to improve other downstream tasks, such as automatic speaker verification (ASV) and automatic speech recognition (ASR), because they do not share the same objects. It is easy to apply the proposed dual-warping factors approach to any mask-based SE method, and it allows a single SE system to handle multiple tasks without task-dependent training. The effectiveness of our proposed approach has been confirmed on the SITW dataset for ASV evaluation and the LibriSpeech dataset for ASR and speech quality evaluations of 0-20dB. We show that different warping values are necessary for a single SE to achieve optimal performance w.r.t. the three tasks. With the use of task-dependent warping factors, speech quality was improved by an 84.7% PESQ increase, ASV had a 22.4% EER reduction, and ASR had a 52.2% WER reduction, on 0dB speech. The effectiveness of the task-dependent warping factors were also cross-validated on VoxCeleb-1 test set for ASV and LibriSpeech dev-clean set for ASV and quality evaluations. The proposed method is highly effective and easy to apply in practice.

* EUSIPCO 2021 (the 29th European Signal Processing Conference) 

  Access Paper or Ask Questions