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

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

Apr 02, 2021
Adam Polyak, Yossi Adi, Jade Copet, Eugene Kharitonov, Kushal Lakhotia, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (for both resynthesis and voice conversion), recordings' intelligibility, and overall quality using subjective human evaluation. Lastly, we demonstrate how these representations can be used for an ultra-lightweight speech codec. Using the obtained representations, we can get to a rate of 365 bits per second while providing better speech quality than the baseline methods. Audio samples can be found under

  Access Paper or Ask Questions

Towards Multi-Scale Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis

Apr 06, 2022
Shun Lei, Yixuan Zhou, Liyang Chen, Jiankun Hu, Zhiyong Wu, Shiyin Kang, Helen Meng

Previous works on expressive speech synthesis focus on modelling the mono-scale style embedding from the current sentence or context, but the multi-scale nature of speaking style in human speech is neglected. In this paper, we propose a multi-scale speaking style modelling method to capture and predict multi-scale speaking style for improving the naturalness and expressiveness of synthetic speech. A multi-scale extractor is proposed to extract speaking style embeddings at three different levels from the ground-truth speech, and explicitly guide the training of a multi-scale style predictor based on hierarchical context information. Both objective and subjective evaluations on a Mandarin audiobooks dataset demonstrate that our proposed method can significantly improve the naturalness and expressiveness of the synthesized speech.

* Submitted to INTERSPEECH 2022 

  Access Paper or Ask Questions

Automated rating of recorded classroom presentations using speech analysis in kazakh

Jan 01, 2018
Akzharkyn Izbassarova, Aidana Irmanova, A. P. James

Effective presentation skills can help to succeed in business, career and academy. This paper presents the design of speech assessment during the oral presentation and the algorithm for speech evaluation based on criteria of optimal intonation. As the pace of the speech and its optimal intonation varies from language to language, developing an automatic identification of language during the presentation is required. Proposed algorithm was tested with presentations delivered in Kazakh language. For testing purposes the features of Kazakh phonemes were extracted using MFCC and PLP methods and created a Hidden Markov Model (HMM) [5], [5] of Kazakh phonemes. Kazakh vowel formants were defined and the correlation between the deviation rate in fundamental frequency and the liveliness of the speech to evaluate intonation of the presentation was analyzed. It was established that the threshold value between monotone and dynamic speech is 0.16 and the error for intonation evaluation is 19%.

* 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Udupi, 2017, pp. 393-397 

  Access Paper or Ask Questions

Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement

Dec 21, 2021
Yichao Du, Zhirui Zhang, Weizhi Wang, Boxing Chen, Jun Xie, Tong Xu

End-to-end speech-to-text translation~(E2E-ST) is becoming increasingly popular due to the potential of its less error propagation, lower latency, and fewer parameters. Given the triplet training corpus $\langle speech, transcription, translation\rangle$, the conventional high-quality E2E-ST system leverages the $\langle speech, transcription\rangle$ pair to pre-train the model and then utilizes the $\langle speech, translation\rangle$ pair to optimize it further. However, this process only involves two-tuple data at each stage, and this loose coupling fails to fully exploit the association between triplet data. In this paper, we attempt to model the joint probability of transcription and translation based on the speech input to directly leverage such triplet data. Based on that, we propose a novel regularization method for model training to improve the agreement of dual-path decomposition within triplet data, which should be equal in theory. To achieve this goal, we introduce two Kullback-Leibler divergence regularization terms into the model training objective to reduce the mismatch between output probabilities of dual-path. Then the well-trained model can be naturally transformed as the E2E-ST models by the pre-defined early stop tag. Experiments on the MuST-C benchmark demonstrate that our proposed approach significantly outperforms state-of-the-art E2E-ST baselines on all 8 language pairs, while achieving better performance in the automatic speech recognition task. Our code is open-sourced at

* AAAI 2022 

  Access Paper or Ask Questions

Speech Synthesis using EEG

Feb 22, 2020
Gautam Krishna, Co Tran, Yan Han, Mason Carnahan

In this paper we demonstrate speech synthesis using different electroencephalography (EEG) feature sets recently introduced in [1]. We make use of a recurrent neural network (RNN) regression model to predict acoustic features directly from EEG features. We demonstrate our results using EEG features recorded in parallel with spoken speech as well as using EEG recorded in parallel with listening utterances. We provide EEG based speech synthesis results for four subjects in this paper and our results demonstrate the feasibility of synthesizing speech directly from EEG features.

* Accepted for publication at IEEE ICASSP 2020 

  Access Paper or Ask Questions

Unsupervised Learning of Disentangled Speech Content and Style Representation

Oct 24, 2020
Andros Tjandra, Ruoming Pang, Yu Zhang, Shigeki Karita

We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captures per-utterance information; and (3) a conditional decoder that reconstructs speech given local and global latent variables. Our experiments show that (1) the local latent variables encode speech contents, as reconstructed speech can be recognized by ASR with low word error rates (WER), even with a different global encoding; (2) the global latent variables encode speaker style, as reconstructed speech shares speaker identity with the source utterance of the global encoding. Additionally, we demonstrate an useful application from our pre-trained model, where we can train a speaker recognition model from the global latent variables and achieve high accuracy by fine-tuning with as few data as one label per speaker.

* Submitted to ICASSP 2021 

  Access Paper or Ask Questions

Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion

Mar 13, 2018
Matthijs Van keirsbilck, Bert Moons, Marian Verhelst

Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video simultaneously - significantly enhances the performance of such systems, especially in noisy environments. This work presents the design of such an audio-visual system for Automated Speech Recognition, taking memory and computation requirements into account. First, a Long-Short-Term-Memory neural network for acoustic speech recognition is designed. Second, Convolutional Neural Networks are used to model lip-reading features. These are combined with an LSTM network to model temporal dependencies and perform automatic lip-reading on video. Finally, acoustic-speech and visual lip-reading networks are combined to process acoustic and visual features simultaneously. An attention mechanism ensures performance of the model in noisy environments. This system is evaluated on the TCD-TIMIT 'lipspeaker' dataset for audio-visual phoneme recognition with clean audio and with additive white noise at an SNR of 0dB. It achieves 75.70% and 58.55% phoneme accuracy respectively, over 14 percentage points better than the state-of-the-art for all noise levels.

* Tech. report 

  Access Paper or Ask Questions

Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition

Mar 09, 2022
Yi Chang, Sofiane Laridi, Zhao Ren, Gregory Palmer, Björn W. Schuller, Marco Fisichella

Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and processed on servers in the internet-of-things applications of speech emotion recognition. Furthermore, deep neural networks have proven to be vulnerable to human-indistinguishable adversarial perturbations. The adversarial attacks generated from the perturbations may result in deep neural networks wrongly predicting the emotional states. We propose a novel federated adversarial learning framework for protecting both data and deep neural networks. The proposed framework consists of i) federated learning for data privacy, and ii) adversarial training at the training stage and randomisation at the testing stage for model robustness. The experiments show that our proposed framework can effectively protect the speech data locally and improve the model robustness against a series of adversarial attacks.

* 11 pages, 6 figures, 3 tables 

  Access Paper or Ask Questions

Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement

Feb 24, 2022
Doyeon Kim, Hyewon Han, Hyeon-Kyeong Shin, Soo-Whan Chung, Hong-Goo Kang

Modern neural speech enhancement models usually include various forms of phase information in their training loss terms, either explicitly or implicitly. However, these loss terms are typically designed to reduce the distortion of phase spectrum values at specific frequencies, which ensures they do not significantly affect the quality of the enhanced speech. In this paper, we propose an effective phase reconstruction strategy for neural speech enhancement that can operate in noisy environments. Specifically, we introduce a phase continuity loss that considers relative phase variations across the time and frequency axes. By including this phase continuity loss in a state-of-the-art neural speech enhancement system trained with reconstruction loss and a number of magnitude spectral losses, we show that our proposed method further improves the quality of enhanced speech signals over the baseline, especially when training is done jointly with a magnitude spectrum loss.

* Accepted by ICASSP 2022 

  Access Paper or Ask Questions

Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies

Nov 01, 2020
Alexander H. Liu, Yu-An Chung, James Glass

Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies while generating the representation. In this work, we propose Non-Autoregressive Predictive Coding (NPC), a self-supervised method, to learn a speech representation in a non-autoregressive manner by relying only on local dependencies of speech. NPC has a conceptually simple objective and can be implemented easily with the introduced Masked Convolution Blocks. NPC offers a significant speedup for inference since it is parallelizable in time and has a fixed inference time for each time step regardless of the input sequence length. We discuss and verify the effectiveness of NPC by theoretically and empirically comparing it with other methods. We show that the NPC representation is comparable to other methods in speech experiments on phonetic and speaker classification while being more efficient.

* Preprint 

  Access Paper or Ask Questions