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

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

Feb 09, 2022
Ioannis Tsiamas, Gerard I. Gállego, José A. R. Fonollosa, Marta R. Costa-jussà

Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in real-world scenarios, and existing segmentation methods usually significantly reduce translation quality at inference time. To bridge the gap between the manual segmentation of training and the automatic one at inference, we propose Supervised Hybrid Audio Segmentation (SHAS), a method that can effectively learn the optimal segmentation from any manually segmented speech corpus. First, we train a classifier to identify the included frames in a segmentation, using speech representations from a pre-trained wav2vec 2.0. The optimal splitting points are then found by a probabilistic Divide-and-Conquer algorithm that progressively splits at the frame of lowest probability until all segments are below a pre-specified length. Experiments on MuST-C and mTEDx show that the translation of the segments produced by our method approaches the quality of the manual segmentation on 5 languages pairs. Namely, SHAS retains 95-98% of the manual segmentation's BLEU score, compared to the 87-93% of the best existing methods. Our method is additionally generalizable to different domains and achieves high zero-shot performance in unseen languages.

* 7 pages including appendix 

  Access Paper or Ask Questions

Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization

Jul 09, 2021
Lu Zhang, Mingjiang Wang, Andong Li, Zehua Zhang, Xuyi Zhuang

Recent single-channel speech enhancement methods based on deep neural networks (DNNs) have achieved remarkable results, but there are still generalization problems in real scenes. Like other data-driven methods, DNN-based speech enhancement models produce significant performance degradation on untrained data. In this study, we make full use of the contribution of multi-target joint learning to the model generalization capability, and propose a lightweight and low-computing dilated convolutional network (DCN) model for a more robust speech denoising task. Our goal is to integrate the masking target, the mapping target, and the parameters of the traditional speech enhancement estimator into a DCN model to maximize their complementary advantages. To do this, we build a multi-stage learning framework to deal with multiple targets in stages to achieve their joint learning, namely `MT-in-MS'. Our experimental results show that compared with the state-of-the-art time domain and time-frequency domain models, this proposed low-cost DCN model can achieve better generalization performance in speaker, noise, and channel mismatch cases.

* Submitted to APSIPA-ASC 2021 

  Access Paper or Ask Questions

Diarization of Legal Proceedings. Identifying and Transcribing Judicial Speech from Recorded Court Audio

Apr 03, 2021
Jeffrey Tumminia, Amanda Kuznecov, Sophia Tsilerides, Ilana Weinstein, Brian McFee, Michael Picheny, Aaron R. Kaufman

United States Courts make audio recordings of oral arguments available as public record, but these recordings rarely include speaker annotations. This paper addresses the Speech Audio Diarization problem, answering the question of "Who spoke when?" in the domain of judicial oral argument proceedings. We present a workflow for diarizing the speech of judges using audio recordings of oral arguments, a process we call Reference-Dependent Speaker Verification. We utilize a speech embedding network trained with the Generalized End-to-End Loss to encode speech into d-vectors and a pre-defined reference audio library based on annotated data. We find that by encoding reference audio for speakers and full arguments and computing similarity scores we achieve a 13.8% Diarization Error Rate for speakers covered by the reference audio library on a held-out test set. We evaluate our method on the Supreme Court of the United States oral arguments, accessed through the Oyez Project, and outline future work for diarizing legal proceedings. A code repository for this research is available at

* Under review for InterSpeech 2021 

  Access Paper or Ask Questions

Ask2Mask: Guided Data Selection for Masked Speech Modeling

Feb 24, 2022
Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Yu Zhang, Pedro Moreno

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems, they have one major limitation. They treat all unsupervised speech samples with equal weight, which hinders learning as not all samples have relevant information to learn meaningful representations. In this work, we address this limitation. We propose ask2mask (ATM), a novel approach to focus on specific samples during MSM pre-training. ATM employs an external ASR model or \textit{scorer} to weight unsupervised input samples in two different ways: 1) A fine-grained data selection is performed by masking over the highly confident input frames as chosen by the scorer. This allows the model to learn meaningful representations. 2) ATM is further extended to focus at utterance-level by weighting the final MSM loss with the utterance-level confidence score. We conduct fine-tuning experiments on two well-benchmarked corpora: LibriSpeech (matching the pre-training data) and Commonvoice, TED-LIUM, AMI and CHiME-6 (not matching the pre-training data). The results substantiate the efficacy of ATM on significantly improving the recognition performance under mismatched conditions (up to 11.6\% relative over published results and upto 4.46\% relative over our internal baseline) while still yielding modest improvements under matched conditions.

  Access Paper or Ask Questions

A deep representation learning speech enhancement method using $β$-VAE

May 11, 2022
Yang Xiang, Jesper Lisby Højvang, Morten Højfeldt Rasmussen, Mads Græsbøll Christensen

In previous work, we proposed a variational autoencoder-based (VAE) Bayesian permutation training speech enhancement (SE) method (PVAE) which indicated that the SE performance of the traditional deep neural network-based (DNN) method could be improved by deep representation learning (DRL). Based on our previous work, we in this paper propose to use $\beta$-VAE to further improve PVAE's ability of representation learning. More specifically, our $\beta$-VAE can improve PVAE's capacity of disentangling different latent variables from the observed signal without the trade-off problem between disentanglement and signal reconstruction. This trade-off problem widely exists in previous $\beta$-VAE algorithms. Unlike the previous $\beta$-VAE algorithms, the proposed $\beta$-VAE strategy can also be used to optimize the DNN's structure. This means that the proposed method can not only improve PVAE's SE performance but also reduce the number of PVAE training parameters. The experimental results show that the proposed method can acquire better speech and noise latent representation than PVAE. Meanwhile, it also obtains a higher scale-invariant signal-to-distortion ratio, speech quality, and speech intelligibility.

* Submitted to Eurosipco 

  Access Paper or Ask Questions

MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation

Apr 26, 2021
Xiyun Li, Yong Xu, Meng Yu, Shi-Xiong Zhang, Jiaming Xu, Bo Xu, Dong Yu

Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR by replacing the matrix inversion and eigenvalue decomposition with two recurrent neural networks. In this work, we present a self-attentive RNN beamformer to further improve our previous RNN-based beamformer by leveraging on the powerful modeling capability of self-attention. Temporal-spatial self-attention module is proposed to better learn the beamforming weights from the speech and noise spatial covariance matrices. The temporal self-attention module could help RNN to learn global statistics of covariance matrices. The spatial self-attention module is designed to attend on the cross-channel correlation in the covariance matrices. Furthermore, a multi-channel input with multi-speaker directional features and multi-speaker speech separation outputs (MIMO) model is developed to improve the inference efficiency. The evaluations demonstrate that our proposed MIMO self-attentive RNN beamformer improves both the automatic speech recognition (ASR) accuracy and the perceptual estimation of speech quality (PESQ) against prior arts.

  Access Paper or Ask Questions

STEPs-RL: Speech-Text Entanglement for Phonetically Sound Representation Learning

Nov 23, 2020
Prakamya Mishra

In this paper, we present a novel multi-modal deep neural network architecture that uses speech and text entanglement for learning phonetically sound spoken-word representations. STEPs-RL is trained in a supervised manner to predict the phonetic sequence of a target spoken-word using its contextual spoken word's speech and text, such that the model encodes its meaningful latent representations. Unlike existing work, we have used text along with speech for auditory representation learning to capture semantical and syntactical information along with the acoustic and temporal information. The latent representations produced by our model were not only able to predict the target phonetic sequences with an accuracy of 89.47% but were also able to achieve competitive results to textual word representation models, Word2Vec & FastText (trained on textual transcripts), when evaluated on four widely used word similarity benchmark datasets. In addition, investigation of the generated vector space also demonstrated the capability of the proposed model to capture the phonetic structure of the spoken-words. To the best of our knowledge, none of the existing works use speech and text entanglement for learning spoken-word representation, which makes this work first of its kind.

  Access Paper or Ask Questions

Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation

Apr 18, 2022
Dan Berrebbi, Jiatong Shi, Brian Yan, Osbel Lopez-Francisco, Jonathan D. Amith, Shinji Watanabe

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.

* 5 pages, 2 figures, submitted to Interspeech 2022 

  Access Paper or Ask Questions

Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System

Oct 03, 2019
Kai Fan, Jiayi Wang, Bo Li, Boxing Chen, Niyu Ge

The performances of automatic speech recognition (ASR) systems are usually evaluated by the metric word error rate (WER) when the manually transcribed data are provided, which are, however, expensively available in the real scenario. In addition, the empirical distribution of WER for most ASR systems usually tends to put a significant mass near zero, making it difficult to simulate with a single continuous distribution. In order to address the two issues of ASR quality estimation (QE), we propose a novel neural zero-inflated model to predict the WER of the ASR result without transcripts. We design a neural zero-inflated beta regression on top of a bidirectional transformer language model conditional on speech features (speech-BERT). We adopt the pre-training strategy of token level mask language modeling for speech-BERT as well, and further fine-tune with our zero-inflated layer for the mixture of discrete and continuous outputs. The experimental results show that our approach achieves better performance on WER prediction in the metrics of Pearson and MAE, compared with most existed quality estimation algorithms for ASR or machine translation.

  Access Paper or Ask Questions